CN107944025A - Information-pushing method and device - Google Patents
Information-pushing method and device Download PDFInfo
- Publication number
- CN107944025A CN107944025A CN201711319980.1A CN201711319980A CN107944025A CN 107944025 A CN107944025 A CN 107944025A CN 201711319980 A CN201711319980 A CN 201711319980A CN 107944025 A CN107944025 A CN 107944025A
- Authority
- CN
- China
- Prior art keywords
- word
- instance
- attribute
- entity
- 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.)
- Pending
Links
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
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Abstract
The embodiment of the present application discloses information-pushing method and device.One embodiment of this method includes：Searching request in response to receiving user, in the search key included from searching request extraction be used for the first instance word for characterizing entity；The relation chosen from multiple second instance words between first instance word meets the second instance word of predetermined condition as target entity word；The attribute word of entity attributes characterized for describing target entity word is determined from information to be pushed；With the presence or absence of the property value corresponding to attribute word in the web data with target entity word association for determining to obtain in advance；If it is determined that there is the property value corresponding to attribute word in web data, to the terminal pushed information of user, wherein, information includes target entity word, attribute word and property value.The embodiment can improve the quality of the information of push.
Description
Technical field
The invention relates to field of computer technology, and in particular to Internet technical field, more particularly to information push away
Delivery method and device.
Background technology
With the development of Internet technology, user can obtain various information by internet.For example, user can
Relevant information is obtained to carry out information retrieval by search engine.Furthermore it is also possible to according to the searching request of user to user
Push and the relevant information of searching request.Can be by the letter of push side's pre-edit in the information pushed at present to user
Breath.
When some word match in the keyword and the information of pre-edit in the searching request of user, can to
Family pushes the information of above-mentioned pre-edit.After user clicks on the information of push, the information that can jump to above-mentioned push corresponds to
Webpage read further information for user.
The content of the invention
The embodiment of the present application proposes a kind of information-pushing method and device.
In a first aspect, the embodiment of the present application provides a kind of information-pushing method, this method includes：In response to receiving use
The searching request at family, in the search key included from searching request extraction be used for the first instance word for characterizing entity；From more
The relation chosen in a second instance word between first instance word meets the second instance word of predetermined condition as target entity
Word, wherein, second instance word is the word for being used to characterize entity in the information to be pushed obtained in advance；Determined from information to be pushed
Go out the attribute word of the entity attributes characterized for describing target entity word；Determine obtain in advance with target entity word association
Web data in the presence or absence of the property value corresponding to attribute word；If it is determined that in web data exist with attribute word corresponding to
Property value, to the terminal pushed information of user, wherein, information includes target entity word, attribute word and property value.
In certain embodiments, the degree of association that predetermined condition is included between first instance word and second instance word is more than default
Degree of association threshold value.
In certain embodiments, the degree of association between first instance word and second instance word with the knowledge graph pre-established
The number of nodes included by shortest path in spectrum between first instance word and second instance word is inversely proportional；And from multiple second
The relation between first instance word is chosen in entity word meets the second instance word of predetermined condition as target entity word, bag
Include：The shortest path being chosen in multiple second instance words in the knowledge mapping pre-established between first instance word is wrapped
The second instance word of the number of nodes included at least is as target entity word.
In certain embodiments, it whether there is attribute in the web data with target entity word association for determining to obtain in advance
Property value corresponding to word, including：Determine to whether there is attribute word in web data based on text analyzing model trained in advance
Corresponding property value.
In certain embodiments, it whether there is attribute in the web data with target entity word association for determining to obtain in advance
Property value corresponding to word, including：Data mining is carried out to web data using the method for data mining, according to data mining
As a result determine in web data with the presence or absence of the property value corresponding to attribute word.
In certain embodiments, information-pushing method further includes：Knowledge is built based on internet mass web page text data
Collection of illustrative plates, knowledge mapping include upper between multiple entity words, the corresponding attribute word of each entity word and different entities word
The next relation.
Second aspect, the embodiment of the present application provide a kind of information push-delivery apparatus, which includes：Extraction unit, configuration
For the searching request in response to receiving user, extraction is for characterizing entity in the search key included from searching request
First instance word；Unit is chosen, the relation for being configured to choose from multiple second instance words between first instance word expires
The second instance word of sufficient predetermined condition as target entity word, wherein, second instance word is in the information to be pushed that obtains in advance
For characterizing the word of entity；First determination unit, is configured to determine to be used to describe target entity word from information to be pushed
The attribute word of the entity attributes characterized；Second determination unit, be configured to determine to obtain in advance closes with target entity word
With the presence or absence of the property value corresponding to attribute word in the web data of connection；Push unit, is configured to if it is determined that with treating push letter
The property value existed in associated web data corresponding to attribute word is ceased, to the terminal pushed information of user, wherein, packet
Include target entity word, attribute word and property value.
In certain embodiments, the degree of association that predetermined condition is included between first instance word and second instance word is more than default
Degree of association threshold value.
In certain embodiments, the degree of association between first instance word and second instance word with the knowledge graph pre-established
The number of nodes included by shortest path in spectrum between first instance word and second instance word is inversely proportional；And choose unit into
One step is configured to：It is chosen in multiple second instance words in the knowledge mapping pre-established between first instance word most
The second instance word of number of nodes at least included by short path is as target entity word.
In certain embodiments, the second determination unit is further configured to：Based on text analyzing model trained in advance
Determine in web data with the presence or absence of the property value corresponding to attribute word.
In certain embodiments, the second determination unit is further configured to：Using the method for data mining to webpage number
According to data mining is carried out, determined according to the result of data mining in web data with the presence or absence of the property value corresponding to attribute word.
In certain embodiments, information push-delivery apparatus further includes construction unit, and construction unit is configured to：Based on internet
Magnanimity web page text data build knowledge mapping, and knowledge mapping includes multiple entity words, the corresponding attribute of each entity word
Hyponymy between word and different entities word.
The third aspect, the embodiment of the present application provide a kind of server, which includes：One or more processors；
Storage device, for storing one or more programs, when said one or multiple programs are held by said one or multiple processors
During row so that the method for said one or the realization of multiple processors as described in any implementation in first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer-readable recording medium, are stored thereon with computer journey
Sequence, wherein, the method as described in any implementation in first aspect is realized when which is executed by processor.
Information-pushing method and device provided by the embodiments of the present application, first in the searching request by extracting user are real
Pronouns, general term for nouns, numerals and measure words, then chooses target entity word in multiple second instance words included from information to be pushed, then from treating push letter
The attribute word of entity attributes characterized for describing target entity word, then definite obtain in advance and target are determined in breath
It whether there is the corresponding property value of attribute word in the associated web data of entity word, finally if it is determined that being present in category in web data
Property the corresponding property value of word, the terminal push to user includes the information of target notional word, attribute word and property value.So as to effectively
Web data is make use of, improves the quality of the information pushed to user.
Brief description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, the application's is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 is that this application can be applied to exemplary system architecture figure therein；
Fig. 2 is the flow chart according to one embodiment of the information-pushing method of the application；
Fig. 3 a~3c are the schematic diagrames according to the application scenarios of the information-pushing method of the application；
Fig. 4 is the flow chart according to another embodiment of the information-pushing method of the application；
Fig. 5 is the structure diagram according to one embodiment of the information push-delivery apparatus of the application；
Fig. 6 is adapted for the structure diagram of the computer system of the server for realizing the embodiment of the present application.
Embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
It illustrate only easy to describe, in attached drawing and invent relevant part with related.
It should be noted that in the case where there is no conflict, the feature in embodiment and embodiment in the application can phase
Mutually combination.Describe the application in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 shows the exemplary system of the embodiment of the information-pushing method that can apply the application or information push-delivery apparatus
System framework 100.
As shown in Figure 1, system architecture 100 can include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 provide communication link medium.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be interacted with using terminal equipment 101,102,103 by network 104 with server 105, to receive or send out
Send message etc..Various client applications, such as web browser applications, purchase can be installed on terminal device 101,102,103
Species application, searching class application etc..
Terminal device 101,102,103 can have a display screen and a various electronic equipments that supported web page browses, bag
Include but be not limited to smart mobile phone, tablet computer, E-book reader, MP3 player (Moving Picture Experts
Group Audio Layer III, dynamic image expert's compression standard audio aspect 3), MP4 (Moving Picture
Experts Group Audio Layer IV, dynamic image expert's compression standard audio aspect 4) it is player, on knee portable
Computer and desktop computer etc..
Server 105 can be to provide the server of various services, such as to being shown on terminal device 101,102,103
Information provides the background server supported.Background server can dock the data such as received searching request and analyze etc.
Reason, and handling result (such as with the relevant information of searching request) is fed back into terminal device.
It should be noted that the information-pushing method that the embodiment of the present application is provided generally is performed by server 105, accordingly
Ground, information push-delivery apparatus are generally positioned in server 105.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realizing need
Will, can have any number of terminal device, network and server.
With continued reference to Fig. 2, it illustrates the flow 200 of one embodiment of the information-pushing method according to the application.Should
Information-pushing method, comprises the following steps：
Step 201, in response to receiving the searching request of user, extracted in the search key included from searching request
For characterizing the first instance word of entity.
In the present embodiment, the electronic equipment (such as server shown in Fig. 1) of information-pushing method operation thereon can
User's input is received to carry out the terminal of web page browsing using it from user by wired connection mode or radio connection
Searching request, wherein, above-mentioned searching request can be passage, keyword or one section of voice etc..
After the searching request of user is received, above-mentioned electronic equipment can analyze and process searching request to carry
Take search key.Such as cutting word is carried out to searching request, part-of-speech tagging is carried out to cutting word result, extracted further according to part-of-speech tagging
The search key that searching request is included.After search key is extracted from searching request, above-mentioned electronic equipment can
To extract the first instance word for being used for characterizing entity from search key.Usual entity is objective reality and can be mutually distinguishable
Things, can be specific people, thing, thing or abstract concept etc..Such as：Bout, desk, worker etc.
To be an entity.Above-mentioned electronic equipment be able to will be used to characterize above-mentioned specific people, thing, thing or abstract from search key
The word of concept is extracted as first instance word.
In application scenes, above-mentioned electronic equipment can be by each search key and the knowledge mapping pre-established
Each entity word matched, when any one entity word in a search key and knowledge mapping matches, then
It can be extracted the search key as first instance word.
Step 202, the relation chosen from multiple second instance words between first instance word meets the of predetermined condition
Two entity words are as target entity word.Wherein, second instance word is to be used to characterize entity in the information to be pushed obtained in advance
Word.
Above-mentioned electronic equipment (such as server shown in Fig. 1) can obtain information to be pushed in advance by all means.
Such as above-mentioned information to be pushed is received at the owner of information to be pushed；Or above-mentioned electronic equipment by web crawlers from mutual
Networking crawls above-mentioned information to be pushed.Above-mentioned electronic equipment can be waited to push using various analysis means to what is obtained in advance in advance
Information is analyzed therefrom to extract multiple second instance words.Such as wait to push away from above-mentioned according to the entity word corpus pre-established
Deliver letters and extract multiple second instance words in breath；Alternatively, above-mentioned information to be pushed is input to entity word trained in advance identifies mould
Type from above-mentioned information to be pushed to extract multiple second instance words；It is or each according to included by information to be pushed
The semantic feature of word extracts multiple second instance words from above-mentioned information to be pushed.Herein, second instance word is on characterizing
State and be used for the word for characterizing entity in information to be pushed.
In the present embodiment, based on the first instance word obtained in step 201, above-mentioned electronic equipment (such as shown in Fig. 1
Server) relation that can be chosen from above-mentioned multiple second instances between above-mentioned first instance word meets the of predetermined condition
Two notional words are carried as target entity word.The quantity of target entity word can be at least one.
In the present embodiment, above-mentioned predetermined condition can be that first instance word is identical with second instance word；Alternatively, the
The semanteme of one entity word and second instance word it is semantic same or like etc..
It should be noted that the above-mentioned various methods that entity word is extracted from information to be pushed are widely studied at present and should
Known technology, details are not described herein.
Step 203, the category of entity attributes characterized for describing target entity word is determined from information to be pushed
Property word.
In the present embodiment, the electronic equipment (such as server shown in Fig. 1) of information-pushing method operation thereon can
After obtaining target entity word in step 202, it can determine to be used to describe target entity word institute from information to be pushed
The attribute word of the entity attributes of characterization.
In general, an entity can have at least one attribute.As an example, a people can have gender, age,
Go through, wife, son, the attribute such as daughter；One object can have attributes such as quality, volume, states of matter, color etc.；One city
There can be the attributes such as area, population, the country one belongs to, geographical location.
Above-mentioned electronic equipment can pre-establish entity word-attribute word relation list.In entity word-attribute word relation row
In table, the entity word for characterizing an entity, can list the attribute word for characterizing the entity attributes.A usual entity can
With including multiple attributes, equally, each entity word in entity word-attribute word relation list, can correspond to multiple attributes
Word.Alternatively, above-mentioned electronic equipment can access the entity word-attribute word relation list pre-established.
Above-mentioned electronic equipment can be according to the above-mentioned entity word-attribute word relation list pre-established from information to be pushed
In determine the attribute word of entity attributes that is characterized for describing above-mentioned target entity word.
In application scenes, above-mentioned information to be pushed can be input to attribute trained in advance by above-mentioned electronic equipment
The attribute word of the entity attributes characterized for describing above-mentioned target entity word is extracted in extraction model.Such as it can utilize
Largely it is labelled with entity word and the text data of attribute word is trained to above-mentioned attributes extraction above-mentioned attributes extraction model
The output valve of model tends to actual value.
Step 204, it is right to whether there is attribute word institute in the web data with target entity word association for determining to obtain in advance
The property value answered.
In the present embodiment, above-mentioned electronic equipment can obtain in advance closes respectively with each keyword in information to be pushed
The web data of connection.After target entity word is obtained in step 202, above-mentioned electronic equipment can from it is above-mentioned it is obtaining in advance with
Extraction and the web data of target entity word association in the web data that each keyword in information to be pushed is respectively associated.
After determining the attribute word of entity attributes that is characterized for describing target entity word in step 203, on
Stating electronic equipment can determine in the above-mentioned and web data of target entity word association with the presence or absence of corresponding to above-mentioned attribute word
Property value.
Typically for each entity, each of which attribute can correspond at least one property value.Such as：The wife of AA
It is BB, " BB " is the property value of the attribute " wife " of entity " AA " here；The capital of China is Beijing, and " Beijing " is entity here
The property value of the attribute " capital " of " China ".The color of this desk is yellow, and " yellow " is the category of entity " desk " here
The property value of property " color ".
In the present embodiment, above-mentioned electronic equipment can carry out semanteme to above-mentioned with the web data of target entity word association
Analyze to determine in above-mentioned web data with the presence or absence of the property value corresponding to above-mentioned attribute word.
Step 205, however, it is determined that there is the property value corresponding to attribute word in web data, letter is pushed to the terminal of user
Breath.
In the present embodiment, when determine with exist in the web data of target entity word association with attribute word corresponding to category
Property value after, above-mentioned electronic equipment can be pushed to the terminal of user include above-mentioned target entity word, describe target entity word institute
The information of property value corresponding to the attribute word and attribute word of the entity attributes of characterization.So, last to user
In the information pushed, not only include target entity word and attribute word in former information to be pushed, above-mentioned electronics can also be included
The attribute corresponding with the attribute word of above-mentioned target entity word that equipment is excavated from the web data of target entity word association
Value, can improve the quality of the information of user's push, be conducive to the innovation of the pattern to user terminal pushed information.
It is worth noting that, however, it is determined that when being not present in web data with property value corresponding to attribute word, above-mentioned electronics
Equipment can directly push above-mentioned information to be pushed to user terminal.
With continued reference to Fig. 3 a~3c, Fig. 3 a~3c are the signals according to the application scenarios of the information-pushing method of the present embodiment
Figure.
In the application scenarios, as shown in Figure 3a, initiating search in the search engine that user is shown by terminal device please
Seek " CC automobiles " 301.Afterwards, server can backstage extraction first instance word " CC automobiles " from searching request.Further according to pre-
Second instance word " DD vapour is extracted in the information to be pushed related with CC automobiles " DD automobiles have more rational wheelbase " 302 first obtained
Car "；It is then determined that whether DD automobiles meet predetermined condition with CC automobiles.If second instance word " DD automobiles " and first instance word
" CC automobiles " meets predetermined condition, " DD automobiles " can be used as target entity word.Then, can be from information to be pushed " DD vapour
Car has more rational wheelbase " attribute " wheelbase " of extraction description " DD automobiles " in 302；Then, above-mentioned electronic equipment with target
" its wheelbase of DD automobiles is the category that attribute " wheelbase " is determined in 2330mm " in entity word " DD automobiles " associated web data 303
Property value is " 2330mm ".Finally, as shown in Figure 3c to the terminal pushed information 304 of user：" DD vehicle wheel bases 2330 ".Work as user
After clicking above-mentioned pushed information, web content data as shown in Figure 3b will be showed.
The method that above-described embodiment of the application provides from the web data of target entity word association by excavating number
According to come improve to user push information, so as to improve the quality of pushed information.
In some optional implementations of the present embodiment, above-mentioned second instance word and first instance word and between met
Preset condition for example can be between first instance word the degree of association be more than default degree of association threshold value.First instance word and second
The degree of association between entity word can be calculated by the calculation of relationship degree method between existing word, not repeated herein.When
When the degree of association between one second instance word and first instance word is more than default degree of association threshold value, above-mentioned electronic equipment by this
Two entity words are as target entity word.
In some optional implementations of the present embodiment, above-mentioned electronic equipment can use data mining method pair with
The web data of above-mentioned target entity word association carries out data mining.Specifically, multiple known attributes and attribute can be based on
Relation schema between value is above-mentioned with being excavated in the web data of target entity word association and the property value corresponding to attribute word.
And determined according to the result of data mining in the content-data of the webpage with the presence or absence of the property value corresponding to attribute word.
Please continue to refer to Fig. 4, it illustrates the flow 400 of another embodiment of information-pushing method.The information pushes
The flow 400 of method, comprises the following steps：
Step 401, in response to receiving the searching request of user, extracted in the search key included from searching request
For characterizing the first instance word of entity.
In the present embodiment, the electronic equipment (such as server shown in Fig. 1) of information-pushing method operation thereon can
With the search key included first by various analyzing and processing means extraction searching request；Then from above-mentioned search key
Middle extraction is used for the first instance word for characterizing entity.Above-mentioned electronic equipment will be used to characterizing from search key specific people,
The word of thing, thing or abstract concept is extracted as first instance word.
Step 402, it is chosen at from multiple second instance words in the knowledge mapping pre-established between first instance word
Shortest path included by the minimum second instance word of number of nodes be as target entity word, wherein second instance word
It is used for the word for characterizing entity in the information to be pushed obtained in advance.
In the present embodiment, above-mentioned electronic equipment can pre-establish knowledge mapping, or above-mentioned electronic equipment can visit
Ask the knowledge mapping pre-established.The above-mentioned knowledge mapping pre-established can include rudimentary knowledge collection of illustrative plates and vertical class knowledge graph
Spectrum.Above-mentioned rudimentary knowledge collection of illustrative plates can include entity word (or concept) etc. of multiple fields, and above-mentioned vertical class knowledge mapping can be with
For the knowledge mapping of specific field, such as automotive field knowledge mapping, hotel's domain knowledge collection of illustrative plates, house property domain knowledge collection of illustrative plates
Deng.
In some optional implementations of the present embodiment, above-mentioned electronic equipment can according to from internet by various
The web page text data for the magnanimity that method obtains build above-mentioned knowledge mapping.Such as carried out in magnanimity web page text data at analysis
Reason extracts multiple entity words (notional word), characterizes the attribute word of entity attributes.It will be carried from the web page text data of magnanimity
The multiple entity words obtained are integrated, and eliminate contradiction word and ambiguity word.According to the entity word finally obtained and each reality
Correlation between the corresponding attribute word of pronouns, general term for nouns, numerals and measure words and each entity word builds knowledge mapping.Here each entity word it is mutual
Relation includes the hyponymy between different entities word.
Above-mentioned electronic equipment can extract multiple the second realities for being used to characterize entity from the information to be pushed obtained in advance
Pronouns, general term for nouns, numerals and measure words.Above-mentioned electronic equipment can extract more according to the rule-based and entity extraction method of dictionary from above-mentioned information to be pushed
A second instance word for being used to characterize entity, or the entity extraction method based on statistical machine learning is in above-mentioned information to be pushed
The multiple second instance words for being used to characterize entity of middle extraction.It is above-mentioned rule-based with the entity extraction method of dictionary and based on statistics
The entity extraction method of machine learning is widely studied at present and application known technology, and details are not described herein.
Above-mentioned electronic equipment can determine above-mentioned first instance word and each the according to the above-mentioned knowledge mapping pre-established
Shortest path between two entity words.If there is no path between first instance word and a second instance word, exclude this second
Entity word.If the second instance word is further determined that there are multiple paths between first instance word and a second instance word
With the shortest path between first instance word.In general, in knowledge mapping, if an entity word can be arrived by predefined paths
Up to another entity word, which can include multiple nodes (two endpoints for including path).Can be by included
The quantity of node determine the length in path.In the present embodiment, can be by between second instance word and first instance word
The number of nodes in path determine the shortest path between second instance word and first instance word.
In general, in knowledge mapping, the degree of association between two entity words can consider between two entity words most
Number of nodes included by short path is inversely proportional.That is, the degree of association between first instance word and second instance word can be with
Think that the quantity of the node included by the shortest path between first instance word and second instance word is inversely proportional.Further,
Above-mentioned electronic equipment can be by a minimum second instance of the number of nodes included by the shortest path between first instance word
Word is as target entity word.
Step 403, the category of entity attributes characterized for describing target entity word is determined from information to be pushed
Property word.
In the present embodiment, the electronic equipment (such as server shown in Fig. 1) of information-pushing method operation thereon can
After obtaining target entity word in step 402, it can determine to be used to describe by various analyses from information to be pushed
The attribute word for the entity attributes that target entity word is characterized.
In application scenes, above-mentioned electronic equipment can be according to the knowledge mapping pre-established from the knowledge mapping
Find each attribute word of corresponding target entity word.It can include multiple entity words, each entity word in above-mentioned knowledge mapping
Hyponymy between corresponding attribute and different entities word.Above-mentioned electronic equipment can be from above-mentioned knowledge mapping
It is middle to search the word identical with above-mentioned target entity word, then the attribute corresponding with target entity word is found in knowledge mapping
Word.Then by each word in above-mentioned information to be pushed with finding attribute word corresponding with target entity word in knowledge mapping
The attribute word of the entity attributes so as to determine to be characterized for describing target entity word from information to be pushed is compared.
Step 404, based on text analyzing model trained in advance determine with the mark associated web data of entity word whether
There are the property value corresponding to attribute word.
In the present embodiment, above-mentioned electronic equipment can obtain in advance closes respectively with each keyword in information to be pushed
The web data of connection.After target entity word is obtained in step 202, above-mentioned electronic equipment can from it is above-mentioned it is obtaining in advance with
Extraction and the web data of target entity word association in the web data that each keyword in information to be pushed is respectively associated.
In advance trained text analyzing model can be set in above-mentioned electronic equipment, by the content-data of above-mentioned webpage and
The corresponding attribute word of the obtained target entity word of step 403 is input to above-mentioned text analyzing model to determine above-mentioned web data
In with the presence or absence of property value corresponding to attribute word.When in above-mentioned web data there are during the property value corresponding to attribute word,
The above-mentioned property value with corresponding to attribute word of above-mentioned text analyzing model output.When there is no belong in the content-data of above-mentioned webpage
During property value corresponding to property word, then prompt message is exported.
Above-mentioned electronic equipment can in advance using largely with the addition of the text data of mark to above-mentioned text analyzing model into
Row training.Above-mentioned mark can include the property value corresponding to entity word, attribute word and attribute word.By above-mentioned text analyzing
The training of model causes the output valve convergence mark value of above-mentioned text analyzing model.
Step 405, however, it is determined that there is the property value corresponding to attribute word in web data, letter is pushed to the terminal of user
Breath.
In the present embodiment, when determine with exist in the web data of target entity word association with attribute word corresponding to category
Property value after, above-mentioned electronic equipment can be pushed to the terminal of user include above-mentioned target entity word, describe target entity word institute
The information of property value corresponding to the attribute word and attribute word of the entity attributes of characterization.
Figure 4, it is seen that compared with the corresponding embodiments of Fig. 2, the flow of the information-pushing method in the present embodiment
It is in 400 that the number of nodes included by the shortest path between first instance word in the knowledge mapping pre-established is minimum
A second instance word as target entity word, so as to rapidly determine target entity word from information to be pushed.
In addition, the flow 400 of information-pushing method in the present embodiment also based on text analyzing model from target entity word association
Determined in web data for above-mentioned target entity word is described attribute word corresponding to property value, above-mentioned electronics can be reduced
Equipment searches the complexity of the property value corresponding to attribute word in above-mentioned web data, so as to be conducive to push to user terminal
The information of better quality.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, this application provides a kind of push of information to fill
The one embodiment put, the device embodiment is corresponding with the embodiment of the method shown in Fig. 2, which specifically can be applied to respectively
In kind electronic equipment.
As shown in figure 5, the information push-delivery apparatus 500 of the present embodiment includes：Extraction unit 501, choose unit 502, first
Determination unit 503, the second determination unit 504 and push unit 505.Wherein, extraction unit 501, are configured in response to receiving
To the searching request of user, first instance word of the extraction for characterizing entity in the search key included from searching request；
Unit 502 is chosen, the relation for being configured to choose from multiple second instance words between first instance word meets predetermined condition
Second instance word as target entity word, wherein, second instance word is to be used to characterize reality in the information to be pushed that obtains in advance
The word of body；First determination unit 503, is configured to determine what is characterized for describing target entity word from information to be pushed
The attribute word of entity attributes；Second determination unit 504, is configured to determine the net with target entity word association obtained in advance
With the presence or absence of the property value corresponding to attribute word in page data；Push unit 505, is configured to if it is determined that being closed with information to be pushed
There is the property value corresponding to attribute word in the web data of connection, to the terminal pushed information of user, wherein, information includes mesh
Mark entity word, attribute word and property value.
In the present embodiment, the extraction unit 501 of information push-delivery apparatus 500, selection unit 502, the first determination unit
503rd, the second determination unit 504 and the specific processing of push unit 505 and its caused technique effect can be right with reference to figure 2 respectively
The related description of step 201 in embodiment, step 202, step 203, step 204 and step 205 is answered, details are not described herein.
In some optional implementations of the present embodiment, above-mentioned second instance word and first instance word and between expire
The preset condition of foot for example can be for first instance word between the degree of association be more than and preset degree of association threshold value.First instance word and
The degree of association between two entity words can be calculated by the calculation of relationship degree method between existing word, not repeated herein.
In some optional implementations of the present embodiment, the degree of association between first instance word and second instance word with
The number of nodes included by shortest path in the knowledge mapping pre-established between first instance word and second instance word into
Inverse ratio.Unit 502 is chosen further to be configured to：Be chosen in multiple second instance words in the knowledge mapping pre-established with
The second instance word of the number of nodes included by shortest path at least between first instance word is as target entity word.
In some optional implementations of the present embodiment, the second determination unit 504 is further configured according to such as lower section
Method is determined in web data with the presence or absence of the property value corresponding to attribute word：Net is determined based on text analyzing model trained in advance
With the presence or absence of the property value corresponding to attribute word in page data.
In some optional implementations of the present embodiment, the second determination unit 504 is further configured according to such as lower section
Method is determined in web data with the presence or absence of the property value corresponding to attribute word：Web data is carried out using the method for data mining
Data mining, determines in web data with the presence or absence of the property value corresponding to attribute word according to the result of data mining.
In some optional implementations of the present embodiment, above- mentioned information pusher 500 further includes construction unit (figure
Not shown in), construction unit is further configured to：Knowledge mapping, knowledge are built based on internet mass web page text data
Collection of illustrative plates includes the hyponymy between multiple entity words, the corresponding attribute word of each entity word and different entities word.
Below with reference to Fig. 6, it illustrates suitable for for realizing the computer system 600 of the server of the embodiment of the present application
Structure diagram.Server shown in Fig. 6 is only an example, should not be to the function and use scope band of the embodiment of the present application
Carry out any restrictions.
As shown in fig. 6, computer system 600 includes central processing unit (CPU, Central Processing Unit)
601, its can according to the program being stored in read-only storage (ROM, Read Only Memory) 602 or from storage part
606 programs being loaded into random access storage device (RAM, Random Access Memory) 603 and perform it is various appropriate
Action and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data.CPU 601、ROM
602 and RAM 603 is connected with each other by bus 604.Input/output (I/O, Input/Output) interface 605 is also connected to
Bus 604.
I/O interfaces 605 are connected to lower component：Storage part 606 including hard disk etc.；And including such as LAN (locals
Net, Local Area Network) card, modem etc. network interface card communications portion 607.Communications portion 607 passes through
Communication process is performed by the network of such as internet.Driver 608 is also according to needing to be connected to I/O interfaces 605.Detachable media
609, such as disk, CD, magneto-optic disk, semiconductor memory etc., as needed be installed on driver 608 on, in order to from
The computer program read thereon is mounted into storage part 606 as needed.
Especially, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product, it includes being carried on computer-readable medium
On computer program, the computer program include be used for execution flow chart shown in method program code.In such reality
Apply in example, which can be downloaded and installed by communications portion 607 from network, and/or from detachable media
609 are mounted.When the computer program is performed by central processing unit (CPU) 601, perform what is limited in the present processes
Above-mentioned function.It should be noted that computer-readable medium described herein can be computer-readable signal media or
Computer-readable recording medium either the two any combination.Computer-readable recording medium for example can be --- but
Be not limited to --- electricity, magnetic, optical, electromagnetic, system, device or the device of infrared ray or semiconductor, or it is any more than combination.
The more specifically example of computer-readable recording medium can include but is not limited to：Electrical connection with one or more conducting wires,
Portable computer diskette, hard disk, random access storage device (RAM), read-only storage (ROM), erasable type may be programmed read-only deposit
Reservoir (EPROM or flash memory), optical fiber, portable compact disc read-only storage (CD-ROM), light storage device, magnetic memory
Part or above-mentioned any appropriate combination.In this application, computer-readable recording medium can any be included or store
The tangible medium of program, the program can be commanded the either device use or in connection of execution system, device.And
In the application, computer-readable signal media can include believing in a base band or as the data that a carrier wave part is propagated
Number, wherein carrying computer-readable program code.The data-signal of this propagation can take various forms, including but not
It is limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer
Any computer-readable medium beyond readable storage medium storing program for executing, the computer-readable medium can send, propagate or transmit use
In by instruction execution system, device either device use or program in connection.Included on computer-readable medium
Program code any appropriate medium can be used to transmit, include but not limited to：Wirelessly, electric wire, optical cable, RF etc., Huo Zheshang
Any appropriate combination stated.
Flow chart and block diagram in attached drawing, it is illustrated that according to the system of the various embodiments of the application, method and computer journey
Architectural framework in the cards, function and the operation of sequence product.At this point, each square frame in flow chart or block diagram can generation
The part of one module of table, program segment or code, the part of the module, program segment or code include one or more use
In the executable instruction of logic function as defined in realization.It should also be noted that marked at some as in the realization replaced in square frame
The function of note can also be with different from the order marked in attached drawing generation.For example, two square frames succeedingly represented are actually
It can perform substantially in parallel, they can also be performed in the opposite order sometimes, this is depending on involved function.Also to note
Meaning, the combination of each square frame and block diagram in block diagram and/or flow chart and/or the square frame in flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit can also be set within a processor, for example, can be described as：A kind of processor bag
Include extraction unit, choose unit, the first determination unit, the second determination unit and push unit.Wherein, the title of these units exists
The restriction to the unit in itself is not formed in the case of certain, for example, extraction unit is also described as " from searching request institute
Comprising search key in extraction be used for mark levies in kind body first instance word unit ".
As on the other hand, present invention also provides a kind of computer-readable medium, which can be
Included in device described in above-described embodiment；Can also be individualism, and without be incorporated the device in.Above-mentioned calculating
Machine computer-readable recording medium carries one or more program, when said one or multiple programs are performed by the device so that should
Device：Searching request in response to receiving user, in the search key included from searching request extraction be used to characterize reality
The first instance word of body；The relation chosen from multiple second instance words between first instance word meets the second of predetermined condition
Entity word as target entity word, wherein, second instance word is the word for being used to characterize entity in the information to be pushed that obtains in advance；
The attribute word of entity attributes characterized for describing target entity word is determined from information to be pushed；Determine to obtain in advance
The web data with target entity word association in the presence or absence of the property value corresponding to attribute word；If it is determined that deposited in web data
Property value corresponding to attribute word, to the terminal pushed information of user, wherein, information includes target entity word, attribute word
And property value.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.People in the art
Member should be appreciated that invention scope involved in the application, however it is not limited to the technology that the particular combination of above-mentioned technical characteristic forms
Scheme, while should also cover in the case where not departing from foregoing invention design, carried out by above-mentioned technical characteristic or its equivalent feature
The other technical solutions for being combined and being formed.Such as features described above has similar work(with (but not limited to) disclosed herein
The technical solution that the technical characteristic of energy is replaced mutually and formed.
Claims (14)
1. a kind of information-pushing method, including：
Searching request in response to receiving user, asks extraction in included search key to be used to characterize from described search
The first instance word of entity；
The second instance word that the relation between the first instance word meets predetermined condition is chosen from multiple second instance words
As target entity word, wherein, the second instance word is the word for being used to characterize entity in the information to be pushed obtained in advance；
The attribute word of entity attributes characterized for describing the target entity word is determined from the information to be pushed；
With the presence or absence of corresponding to the attribute word in the web data with the target entity word association for determining to obtain in advance
Property value；
If it is determined that there is the property value corresponding to the attribute word in the web data, letter is pushed to the terminal of the user
Breath, wherein, described information includes the target entity word, the attribute word and the property value.
2. according to the method described in claim 1, wherein, the predetermined condition is included between first instance word and second instance word
The degree of association be more than default degree of association threshold value.
3. according to the method described in claim 2, wherein, the degree of association between the first instance word and second instance word with
The number of nodes included by shortest path in the knowledge mapping pre-established between first instance word and second instance word is into anti-
Than；And
The relation chosen from multiple second instance words between the first instance word meets the second reality of predetermined condition
Pronouns, general term for nouns, numerals and measure words as target entity word, including：
The shortest path institute being chosen in multiple second instance words in the knowledge mapping pre-established between first instance word
Including the minimum second instance word of number of nodes as target entity word.
4. according to the method described in claim 1, wherein, the net with the target entity word association for determining to obtain in advance
With the presence or absence of the property value corresponding to the attribute word in page data, including：
Determined based on text analyzing model trained in advance in the web data with the presence or absence of the category corresponding to the attribute word
Property value.
5. according to the method described in claim 1, wherein, the net with the target entity word association for determining to obtain in advance
With the presence or absence of the property value corresponding to the attribute word in page data, including：
Data mining is carried out to the web data using the method for data mining, the net is determined according to the result of data mining
With the presence or absence of the property value corresponding to the attribute word in page data.
6. according to the method described in claim 3, wherein, the method further includes：
The knowledge mapping is built based on internet mass web page text data, and the knowledge mapping includes multiple entity words, each
Hyponymy between the corresponding attribute word of a entity word and different entities word.
7. a kind of information push-delivery apparatus, including：
Extraction unit, is configured to the searching request in response to receiving user, asks included search to be closed from described search
Extraction is used for the first instance word for characterizing entity in keyword；
Unit is chosen, the relation for being configured to choose from multiple second instance words between the first instance word meets predetermined
The second instance word of condition as target entity word, wherein, the second instance word is to be used in the information to be pushed that obtains in advance
In the word of characterization entity；
First determination unit, is configured to determine to be characterized for describing the target entity word from the information to be pushed
Entity attributes attribute word；
Whether the second determination unit, be configured to deposit in the definite web data with the target entity word association obtained in advance
In the property value corresponding to the attribute value attribute word corresponding to the attribute word；
Push unit, is configured to if it is determined that there is the property value corresponding to the attribute word in the web data, to institute
The terminal pushed information of user is stated, wherein, described information includes the target entity word, the attribute word and the attribute
Value.
8. device according to claim 7, wherein, the predetermined condition is included between first instance word and second instance word
The degree of association be more than default degree of association threshold value.
9. device according to claim 8, wherein, the degree of association between the first instance word and second instance word with
The number of nodes included by shortest path in the knowledge mapping pre-established between first instance word and second instance word is into anti-
Than；And
The selection unit is further configured to：
The shortest path institute being chosen in multiple second instance words in the knowledge mapping pre-established between first instance word
Including the minimum second instance word of number of nodes as target entity word.
10. device according to claim 7, wherein, second determination unit is further configured to：
Determined based on text analyzing model trained in advance in the web data with the presence or absence of the category corresponding to the attribute word
Property value.
11. device according to claim 7, wherein, second determination unit is further configured to：
Data mining is carried out to the web data using the method for data mining, the net is determined according to the result of data mining
With the presence or absence of the property value corresponding to the attribute word in page data.
12. device according to claim 9, wherein, described device further includes construction unit, and the construction unit configuration is used
In：
The knowledge mapping is built based on internet mass web page text data, and the knowledge mapping includes multiple entity words, each
Hyponymy between the corresponding attribute word of a entity word and different entities word.
13. a kind of server, including：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processors are real
The now method as described in any in claim 1-6.
14. a kind of computer-readable recording medium, is stored thereon with computer program, wherein, when which is executed by processor
Realize the method as described in any in claim 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711319980.1A CN107944025A (en) | 2017-12-12 | 2017-12-12 | Information-pushing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711319980.1A CN107944025A (en) | 2017-12-12 | 2017-12-12 | Information-pushing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107944025A true CN107944025A (en) | 2018-04-20 |
Family
ID=61942852
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711319980.1A Pending CN107944025A (en) | 2017-12-12 | 2017-12-12 | Information-pushing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107944025A (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108829858A (en) * | 2018-06-22 | 2018-11-16 | 北京京东金融科技控股有限公司 | Data query method, apparatus and computer readable storage medium |
| CN109241291A (en) * | 2018-07-18 | 2019-01-18 | 华南师范大学 | Knowledge mapping optimal path inquiry system and method based on deeply study |
| CN109255036A (en) * | 2018-08-31 | 2019-01-22 | 北京字节跳动网络技术有限公司 | Method and apparatus for output information |
| CN109255037A (en) * | 2018-08-31 | 2019-01-22 | 北京字节跳动网络技术有限公司 | Method and apparatus for output information |
| CN109284342A (en) * | 2018-11-22 | 2019-01-29 | 北京百度网讯科技有限公司 | Method and apparatus for output information |
| CN109783651A (en) * | 2019-01-29 | 2019-05-21 | 北京百度网讯科技有限公司 | Extract method, apparatus, electronic equipment and the storage medium of entity relevant information |
| CN110363610A (en) * | 2019-05-24 | 2019-10-22 | 平安科技（深圳）有限公司 | The determination method and device of the attribute of target product, electronic equipment |
| CN110750627A (en) * | 2018-07-19 | 2020-02-04 | 上海谦问万答吧云计算科技有限公司 | Material retrieval method and device, electronic equipment and storage medium |
| CN111259659A (en) * | 2020-01-14 | 2020-06-09 | 北京百度网讯科技有限公司 | Information processing method and device |
| CN111341308A (en) * | 2020-02-12 | 2020-06-26 | 百度在线网络技术（北京）有限公司 | Method and apparatus for outputting information |
| CN111460269A (en) * | 2019-01-18 | 2020-07-28 | 北京字节跳动网络技术有限公司 | Information pushing method and device |
| CN111625680A (en) * | 2020-05-15 | 2020-09-04 | 青岛聚看云科技有限公司 | Method and device for determining search result |
| CN111695073A (en) * | 2020-05-18 | 2020-09-22 | 北京字节跳动网络技术有限公司 | Information pushing method and device and electronic equipment |
| CN111736738A (en) * | 2020-06-30 | 2020-10-02 | 广州小鹏车联网科技有限公司 | Control object query method and device of vehicle-mounted system |
| WO2020206910A1 (en) * | 2019-04-12 | 2020-10-15 | 平安科技（深圳）有限公司 | Product information pushing method, apparatus, computer device, and storage medium |
| CN111800493A (en) * | 2020-06-29 | 2020-10-20 | 百度在线网络技术（北京）有限公司 | Information content pushing method and device, electronic equipment and storage medium |
| CN112507715A (en) * | 2020-11-30 | 2021-03-16 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for determining incidence relation between entities |
| WO2021129515A1 (en) * | 2019-12-23 | 2021-07-01 | 中兴通讯股份有限公司 | Knowledge graph query method, electronic device, and storage medium |
| CN113111647A (en) * | 2021-04-06 | 2021-07-13 | 北京字跳网络技术有限公司 | Information processing method and device, terminal and storage medium |
| CN113242308A (en) * | 2021-05-21 | 2021-08-10 | 杭州米络星科技(集团)有限公司 | Information pushing method, device, equipment and storage medium |
| CN113515700A (en) * | 2021-07-01 | 2021-10-19 | 深圳追一科技有限公司 | Information pushing method and device, electronic equipment and storage medium |
| WO2023160500A1 (en) * | 2022-02-28 | 2023-08-31 | 北京字节跳动网络技术有限公司 | Encyclopedia information display method and apparatus, device and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609444A (en) * | 2010-11-08 | 2012-07-25 | 微软公司 | Presenting actions and providers associated with entities |
| CN102737039A (en) * | 2011-04-07 | 2012-10-17 | 北京百度网讯科技有限公司 | Index building method, searching method and searching result sorting method and corresponding device |
| CN103425714A (en) * | 2012-05-25 | 2013-12-04 | 北京搜狗信息服务有限公司 | Query method and system |
| CN103631948A (en) * | 2013-12-11 | 2014-03-12 | 北京京东尚科信息技术有限公司 | Identifying method of named entities |
| CN103760991A (en) * | 2014-01-13 | 2014-04-30 | 北京搜狗科技发展有限公司 | Physical input method and physical input device |
| CN103914566A (en) * | 2014-04-22 | 2014-07-09 | 百度在线网络技术（北京）有限公司 | Search result display method and search result display device |
-
2017
- 2017-12-12 CN CN201711319980.1A patent/CN107944025A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609444A (en) * | 2010-11-08 | 2012-07-25 | 微软公司 | Presenting actions and providers associated with entities |
| CN102737039A (en) * | 2011-04-07 | 2012-10-17 | 北京百度网讯科技有限公司 | Index building method, searching method and searching result sorting method and corresponding device |
| CN103425714A (en) * | 2012-05-25 | 2013-12-04 | 北京搜狗信息服务有限公司 | Query method and system |
| CN103631948A (en) * | 2013-12-11 | 2014-03-12 | 北京京东尚科信息技术有限公司 | Identifying method of named entities |
| CN103760991A (en) * | 2014-01-13 | 2014-04-30 | 北京搜狗科技发展有限公司 | Physical input method and physical input device |
| CN103914566A (en) * | 2014-04-22 | 2014-07-09 | 百度在线网络技术（北京）有限公司 | Search result display method and search result display device |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108829858B (en) * | 2018-06-22 | 2021-09-17 | 京东数字科技控股有限公司 | Data query method and device and computer readable storage medium |
| CN108829858A (en) * | 2018-06-22 | 2018-11-16 | 北京京东金融科技控股有限公司 | Data query method, apparatus and computer readable storage medium |
| CN109241291A (en) * | 2018-07-18 | 2019-01-18 | 华南师范大学 | Knowledge mapping optimal path inquiry system and method based on deeply study |
| CN109241291B (en) * | 2018-07-18 | 2022-02-15 | 华南师范大学 | Knowledge graph optimal path query system and method based on deep reinforcement learning |
| CN110750627A (en) * | 2018-07-19 | 2020-02-04 | 上海谦问万答吧云计算科技有限公司 | Material retrieval method and device, electronic equipment and storage medium |
| WO2020042377A1 (en) * | 2018-08-31 | 2020-03-05 | 北京字节跳动网络技术有限公司 | Method and apparatus for outputting information |
| CN109255036A (en) * | 2018-08-31 | 2019-01-22 | 北京字节跳动网络技术有限公司 | Method and apparatus for output information |
| CN109255037A (en) * | 2018-08-31 | 2019-01-22 | 北京字节跳动网络技术有限公司 | Method and apparatus for output information |
| CN109284342A (en) * | 2018-11-22 | 2019-01-29 | 北京百度网讯科技有限公司 | Method and apparatus for output information |
| CN111460269B (en) * | 2019-01-18 | 2023-09-01 | 北京字节跳动网络技术有限公司 | Information pushing method and device |
| CN111460269A (en) * | 2019-01-18 | 2020-07-28 | 北京字节跳动网络技术有限公司 | Information pushing method and device |
| CN109783651A (en) * | 2019-01-29 | 2019-05-21 | 北京百度网讯科技有限公司 | Extract method, apparatus, electronic equipment and the storage medium of entity relevant information |
| WO2020206910A1 (en) * | 2019-04-12 | 2020-10-15 | 平安科技（深圳）有限公司 | Product information pushing method, apparatus, computer device, and storage medium |
| CN110363610B (en) * | 2019-05-24 | 2023-04-18 | 平安科技（深圳）有限公司 | Method and device for determining attributes of target product and electronic equipment |
| CN110363610A (en) * | 2019-05-24 | 2019-10-22 | 平安科技（深圳）有限公司 | The determination method and device of the attribute of target product, electronic equipment |
| WO2021129515A1 (en) * | 2019-12-23 | 2021-07-01 | 中兴通讯股份有限公司 | Knowledge graph query method, electronic device, and storage medium |
| CN111259659A (en) * | 2020-01-14 | 2020-06-09 | 北京百度网讯科技有限公司 | Information processing method and device |
| CN111341308A (en) * | 2020-02-12 | 2020-06-26 | 百度在线网络技术（北京）有限公司 | Method and apparatus for outputting information |
| CN111341308B (en) * | 2020-02-12 | 2023-07-21 | 百度在线网络技术（北京）有限公司 | Method and device for outputting information |
| CN111625680A (en) * | 2020-05-15 | 2020-09-04 | 青岛聚看云科技有限公司 | Method and device for determining search result |
| CN111625680B (en) * | 2020-05-15 | 2023-08-25 | 青岛聚看云科技有限公司 | Method and device for determining search results |
| CN111695073A (en) * | 2020-05-18 | 2020-09-22 | 北京字节跳动网络技术有限公司 | Information pushing method and device and electronic equipment |
| CN111800493A (en) * | 2020-06-29 | 2020-10-20 | 百度在线网络技术（北京）有限公司 | Information content pushing method and device, electronic equipment and storage medium |
| CN111736738A (en) * | 2020-06-30 | 2020-10-02 | 广州小鹏车联网科技有限公司 | Control object query method and device of vehicle-mounted system |
| WO2022001682A1 (en) * | 2020-06-30 | 2022-01-06 | 广州橙行智动汽车科技有限公司 | Control object query method and apparatus for vehicle-mounted system |
| CN112507715A (en) * | 2020-11-30 | 2021-03-16 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for determining incidence relation between entities |
| CN112507715B (en) * | 2020-11-30 | 2024-01-16 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for determining association relation between entities |
| CN113111647A (en) * | 2021-04-06 | 2021-07-13 | 北京字跳网络技术有限公司 | Information processing method and device, terminal and storage medium |
| CN113242308A (en) * | 2021-05-21 | 2021-08-10 | 杭州米络星科技(集团)有限公司 | Information pushing method, device, equipment and storage medium |
| CN113515700A (en) * | 2021-07-01 | 2021-10-19 | 深圳追一科技有限公司 | Information pushing method and device, electronic equipment and storage medium |
| CN113515700B (en) * | 2021-07-01 | 2024-02-20 | 深圳追一科技有限公司 | Information pushing method and device, electronic equipment and storage medium |
| WO2023160500A1 (en) * | 2022-02-28 | 2023-08-31 | 北京字节跳动网络技术有限公司 | Encyclopedia information display method and apparatus, device and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107944025A (en) | Information-pushing method and device | |
| US11669579B2 (en) | Method and apparatus for providing search results | |
| US20190095537A1 (en) | Method and apparatus for expanding query | |
| CN107908789A (en) | Method and apparatus for generating information | |
| CN103502983B (en) | Memoizing Web-browsing computation with DOM-based isomorphism | |
| CN108062354A (en) | Information recommendation method, system, storage medium, electronic equipment and vehicle | |
| CN107832468B (en) | Demand recognition methods and device | |
| CN107679039A (en) | The method and apparatus being intended to for determining sentence | |
| CN106383875B (en) | Man-machine interaction method and device based on artificial intelligence | |
| CN107220386A (en) | Information-pushing method and device | |
| EP3893125A1 (en) | Method and apparatus for searching video segment, device, medium and computer program product | |
| CN111522927B (en) | Entity query method and device based on knowledge graph | |
| CN105426508B (en) | Webpage generating method and device | |
| WO2014126657A1 (en) | Latent semantic analysis for application in a question answer system | |
| CN108520470A (en) | Method and apparatus for generating customer attribute information | |
| CN108572990A (en) | Information-pushing method and device | |
| CN106326091A (en) | Browser webpage compatibility detection method and system | |
| US20170308620A1 (en) | Making graph pattern queries bounded in big graphs | |
| CN107943877A (en) | The generation method and device of content of multimedia to be played | |
| CN106407361A (en) | Method and device for pushing information based on artificial intelligence | |
| CN107958078A (en) | Information generating method and device | |
| CN107742128A (en) | Method and apparatus for output information | |
| CN109033282A (en) | A kind of Web page text extracting method and device based on extraction template | |
| CN107977678A (en) | Method and apparatus for output information | |
| CN110019519A (en) | Data processing method, device, storage medium and electronic device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180420 |
|
| RJ01 | Rejection of invention patent application after publication |