CN110069698A - Information-pushing method and device - Google Patents
Information-pushing method and device Download PDFInfo
- Publication number
- CN110069698A CN110069698A CN201711058940.6A CN201711058940A CN110069698A CN 110069698 A CN110069698 A CN 110069698A CN 201711058940 A CN201711058940 A CN 201711058940A CN 110069698 A CN110069698 A CN 110069698A
- Authority
- CN
- China
- Prior art keywords
- search information
- keyword
- information
- history
- lexon
- 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.)
- Granted
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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present application discloses information-pushing method and device.One specific embodiment of this method includes: the information acquisition request that receiving terminal apparatus is sent, wherein information acquisition request includes search information；Search information is matched in history keyword lexon collection group, historical search information corresponding to the history keyword lexon collection of successful match is obtained, to generate candidate search information aggregate, wherein history keyword lexon collection is corresponding with historical search information；Calculate the similarity between the candidate search information in search information and candidate search information aggregate；Based on similarity calculated, candidate search information is selected from candidate search information aggregate as target search information；Information to be pushed set obtained by scanning for using target search information is obtained, and is pushed to terminal device.This embodiment improves the accuracy of information 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 technique
Information push is also known as " Web broadcast " by certain technical standard or agreement, on the internet by pushing away
The information of user's needs is sent to reduce a technology of information overload.Information advancing technique by active push information to user,
User can be reduced the time spent in searching on network.
Existing information push mode usually pushes obtained by the search information inputted using user is scanned for wait push away
Send information aggregate.
Summary of the invention
The purpose of the embodiment of the present application is to propose 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 comprises: receiving terminal apparatus is sent out
The information acquisition request sent, wherein information acquisition request includes search information；Information will be searched in history keyword lexon collection group
Matching, obtains historical search information corresponding to the history keyword lexon collection of successful match, to generate candidate search information aggregate,
Wherein, history keyword lexon collection is corresponding with historical search information；Calculate the candidate in search information and candidate search information aggregate
Search for the similarity between information；Based on similarity calculated, candidate search letter is selected from candidate search information aggregate
Breath is used as target search information；Information to be pushed set obtained by scanning for using target search information is obtained, and is pushed to
Terminal device.
In some embodiments, search information is matched in history keyword lexon collection group, obtains the history of successful match
Historical search information corresponding to keyword subset, comprising: search information is segmented, multiple keys of search information are obtained
Lexon collection；The multiple keyword subsets for searching for information are matched in history keyword lexon collection group, obtain the history of successful match
Keyword subset；Corresponding relationship based on history keyword lexon collection and historical search information, obtains the history keyword of successful match
Historical search information corresponding to lexon collection.
In some embodiments, search information is segmented, obtains multiple keyword subsets of search information, comprising:
Search information is segmented using stammerer segmenting method, obtains the keyword set of search information；Pass through Chinese language model
Using Matching Relation of the keyword in the keyword set of search information in search information, multiple passes of search information are generated
Keyword subset.
In some embodiments, the phase between search information and the candidate search information in candidate search information aggregate is calculated
Like degree, comprising: obtain comentropy corresponding to the history keyword lexon collection of successful match, wherein history keyword lexon collection and letter
It is corresponding to cease entropy；Candidate in comentropy and candidate search information aggregate corresponding to history keyword lexon collection based on successful match
Comentropy corresponding to history keyword lexon collection corresponding to information is searched for, is calculated in search information and candidate search information aggregate
Candidate search information between similarity.
In some embodiments, comentropy corresponding to the history keyword lexon collection based on successful match and candidate search letter
Comentropy corresponding to history keyword lexon collection corresponding to the candidate search information in set is ceased, search information and candidate are calculated
Search for the similarity between the candidate search information in information aggregate, comprising: for each time in candidate search information aggregate
Choosing search information, the history keyword lexon collection and history keyword lexon collection corresponding to the candidate search information for obtaining successful match
Intersection corresponding to comentropy and successful match history keyword lexon collection and the candidate search information corresponding to history close
Comentropy corresponding to the difference set of keyword subset is calculated based on comentropy corresponding to comentropy corresponding to intersection and difference set
Search for the similarity between information and the candidate search information.
In some embodiments, the history keyword lexon collection in history keyword lexon collection group generates as follows: obtaining
Take historical search in historical time section to click set of records ends, wherein historical search click record include historical search information and
The click frequency of history click article category；Each historical search information is segmented, each historical search information is obtained
Multiple history keyword lexon collection；The click frequency for clicking article category to each history is for statistical analysis, obtains each history
Multiple history of keyword subset click the click frequency of article category；Utilize multiple history points of each history keyword lexon collection
The click frequency for hitting article category calculates comentropy corresponding to each history keyword lexon collection.
Second aspect, the embodiment of the present application provide a kind of information push-delivery apparatus, which includes: receiving unit, configuration
The information acquisition request sent for receiving terminal apparatus, wherein information acquisition request includes search information；Matching unit is matched
It sets and is matched in history keyword lexon collection group for information will to be searched for, obtained corresponding to the history keyword lexon collection of successful match
Historical search information, to generate candidate search information aggregate, wherein history keyword lexon collection is corresponding with historical search information；Meter
Unit is calculated, is configured to calculate the similarity between the candidate search information in search information and candidate search information aggregate；Choosing
Unit is taken, is configured to select candidate search information conduct from candidate search information aggregate based on similarity calculated
Target search information；Push unit is configured to information to be pushed collection obtained by acquisition is scanned for using target search information
It closes, and is pushed to terminal device.
In some embodiments, matching unit includes: participle subelement, is configured to segment search information, obtain
To multiple keyword subsets of search information；Coupling subelement is configured to going through the multiple keyword subsets for searching for information
It is matched in history keyword subset group, obtains the history keyword lexon collection of successful match；First obtains subelement, is configured to be based on
The corresponding relationship of history keyword lexon collection and historical search information is obtained and is gone through corresponding to the history keyword lexon collection of successful match
History searches for information.
In some embodiments, participle subelement includes: word segmentation module, is configured to using stammerer segmenting method to search
Information is segmented, and the keyword set of search information is obtained；Generation module is configured to Chinese language model utilization and searches
Matching Relation of the keyword in search information in the keyword set of rope information generates multiple crucial lexons of search information
Collection.
In some embodiments, computing unit includes: the second acquisition subelement, is configured to obtain the history of successful match
Comentropy corresponding to keyword subset, wherein history keyword lexon collection is corresponding with comentropy；Computation subunit is configured to
Candidate search information in comentropy and candidate search information aggregate corresponding to history keyword lexon collection based on successful match
Comentropy corresponding to corresponding history keyword lexon collection calculates search information and searches with the candidate in candidate search information aggregate
Similarity between rope information.
In some embodiments, computation subunit is further configured to: for each of candidate search information aggregate
Candidate search information, the history keyword lexon collection and history keyword lexon corresponding to the candidate search information for obtaining successful match
History corresponding to the history keyword lexon collection of comentropy corresponding to the intersection of collection and successful match and the candidate search information
Comentropy corresponding to the difference set of keyword subset, based on comentropy corresponding to comentropy corresponding to intersection and difference set, meter
Calculate the similarity between search information and the candidate search information.
In some embodiments, the history keyword lexon collection in history keyword lexon collection group generates as follows: obtaining
Take historical search in historical time section to click set of records ends, wherein historical search click record include historical search information and
The click frequency of history click article category；Each historical search information is segmented, each historical search information is obtained
Multiple history keyword lexon collection；The click frequency for clicking article category to each history is for statistical analysis, obtains each history
Multiple history of keyword subset click the click frequency of article category；Utilize multiple history points of each history keyword lexon collection
The click frequency for hitting article category calculates comentropy corresponding to each history keyword lexon collection.
The third aspect, the embodiment of the present application provide a kind of electronic equipment, which includes: one or more processing
Device；Storage device, for storing one or more programs；When one or more programs are executed by one or more processors, make
Obtain method of the one or more processors realization as described in implementation any in first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, are stored thereon with computer journey
Sequence realizes the method as described in implementation any in first aspect when the computer program is executed by processor.
Information-pushing method and device provided by the embodiments of the present application, pass through the acquisition of information that will be received from terminal device
Search information in request matches in history keyword lexon collection group, obtains corresponding to the history keyword lexon collection of successful match
Historical search information, to generate candidate search information aggregate；The time in search information and candidate search information aggregate is calculated later
Similarity between choosing search information；It is then based on similarity calculated, selects target from candidate search information aggregate
Search for information；It finally obtains and scans for obtained information to be pushed set using target search information, and be pushed to terminal
Equipment.It is scanned for, is avoided due to user's input using the similar target search information of the search information inputted with user
The problem of information push inaccuracy caused by search information is inaccurate or lack of standardization, to improve the accurate of information push
Degree.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that the embodiment of the present 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 is the flow chart according to another embodiment of the information-pushing method of the application；
Fig. 4 is the flow chart according to one embodiment of the history keyword lexon set creation method of the application；
Fig. 5 is the structural schematic diagram according to one embodiment of the information push-delivery apparatus of the application；
Fig. 6 is adapted for the structural schematic diagram for the computer system for realizing the electronic equipment of the embodiment of the present application.
Specific 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
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can be using the information-pushing method of the embodiment of the present application or the exemplary system of information push-delivery apparatus
Framework 100.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 101,102,103 and be interacted by network 104 with server 105, to receive or send out
Send message etc..Various telecommunication customer end applications, such as searching class application, net can be installed on terminal device 101,102,103
The application of page browsing device, shopping class application, instant messaging tools, mailbox client, social platform software etc..
Terminal device 101,102,103 can be with display screen and support the various electronic equipments of information browse, packet
Include but be not limited to smart phone, tablet computer, E-book reader, MP3 player (Moving Picture Experts
Group Audio Layer III, dynamic image expert's compression standard audio level 3), MP4 (Moving Picture
Experts Group Audio Layer IV, dynamic image expert's compression standard audio level 4) it is player, on knee portable
Computer and desktop computer etc..
Server 105 can provide various services, such as server 105 can connect to from terminal device 101,102,103
The data such as the information acquisition request received carry out the processing such as analyzing, and processing result (such as information to be pushed set) is fed back to
Terminal device 101,102,103.
It should be noted that information-pushing method provided by the embodiment of the present application is generally executed by server 105, accordingly
Ground, information push-delivery apparatus are generally positioned in server 105.
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
With continued reference to Fig. 2, it illustrates the processes 200 according to one embodiment of the information-pushing method of the application.It should
Information-pushing method, comprising the following steps:
Step 201, the information acquisition request that receiving terminal apparatus is sent.
In the present embodiment, the electronic equipment (such as server 105 shown in FIG. 1) of information-pushing method operation thereon
Can by wired connection mode or radio connection from terminal device (such as terminal device shown in FIG. 1 101,102,
103) information acquisition request is received.Wherein, information acquisition request may include search information.Search information can be user and be wanted
The key message of the information of acquisition is pushed to user's when user inputs search information in the input frame of searching class software
It would generally include user's information to be obtained in information.Search information can include but is not limited to single word, word combination,
Short sentence, long sentence etc..As an example, if user's information to be obtained is the encyclopaedia of " rose ", then the search of user's input
Information can be with the next item down: " rose ", " rose Rosales ", " Britain's national flower ".
It should be pointed out that above-mentioned radio connection can include but is not limited to 3G/4G connection, WiFi connection, bluetooth
Connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection and other currently known or exploitations in the future
Radio connection.
Step 202, search information is matched in history keyword lexon collection group, obtains the history keyword lexon of successful match
The corresponding historical search information of collection, to generate candidate search information aggregate.
In the present embodiment, based on information acquisition request received by step 201, electronic equipment can be by acquisition of information
Search information in request matches in pre-stored history keyword lexon collection group, obtains the history keyword lexon of successful match
Collection, and using historical search information corresponding to the history keyword lexon collection with successful match as candidate search information, to generate
Candidate search information aggregate.
In the present embodiment, electronic equipment can determine in several ways search information and history keyword lexon collection whether
Successful match.As an example, if in search information including whole history keyword words that a history keyword lexon is concentrated,
It is considered that search information and the history keyword lexon collection successful match.As another example, if including one in search information
The history keyword word for the preset number (such as 1,3) that a history keyword lexon is concentrated, it may be considered that searching for information and being somebody's turn to do
History keyword lexon collection successful match.
In the present embodiment, history keyword lexon collection is corresponding with historical search information.As an example, electronic equipment can be first
First obtain multiple historical search informations in a period of time；Then for each historical search information, to the historical search information
It is segmented, to obtain multiple keywords of the historical search information；Finally multiple keys based on the historical search information
Word generates the history keyword lexon collection of the historical search information, to realize pair of history keyword subset and historical search information
It answers.Here, electronic equipment can be gathered composed by multiple keywords by the historical search information as historical search letter
The history keyword lexon collection of breath, can also set composed by the Partial key word by the historical search information searched as the history
The history keyword lexon collection of rope information, for example, those skilled in the art can multiple keywords to the historical search information into
Row analysis, therefrom selects the keyword that can be used for describing the historical search information, and by the keyword of selected taking-up institute group
At history keyword lexon collection of the set as the historical search information.
Step 203, the similarity between the candidate search information in search information and candidate search information aggregate is calculated.
In the present embodiment, it is searched based on information acquisition request received by step 201 and the obtained candidate of step 202
Rope information aggregate, electronic equipment can calculate separately in search information and candidate search information aggregate in information acquisition request
Similarity between each candidate search information.
In the present embodiment, electronic equipment can be calculated in several ways between search information and candidate search information
Similarity.
As an example, electronic equipment can calculate search information and candidate using a variety of Text similarity computing methods
Search for the similarity between information.Wherein, Text similarity computing method can include but is not limited to editing distance (Edit
Distance) algorithm, cosine similarity (cosine similarity) algorithm, Jaccard similarity algorithm etc..Editing distance,
Also known as Levenshtein distance refers between two character strings, and the minimum edit operation time needed for another is changed into as one
Number.The edit operation of license includes that a character is substituted for another character, is inserted into a character, deletes a character.One
As for, editing distance is smaller, and the similarity of two character strings is bigger.
As another example, electronic equipment can also be calculated by following steps search information and candidate search information it
Between similarity.Specifically, electronic equipment can first segment search information with candidate search information, obtain search letter
The keyword set of breath and the keyword set of candidate search information；Then by the keyword in the keyword set for searching for information
It is matched in the keyword set of candidate search information one by one, obtains the number of the keyword of successful match；Finally will matching at
The ratio of the total number of keyword in the keyword set of the number of the keyword of function and search information as search information with
Similarity between candidate search information.
Step 204, it is based on similarity calculated, candidate search information conduct is selected from candidate search information aggregate
Target search information.
In the present embodiment, be based on step 203 similarity calculated, electronic equipment can by a variety of selection modes from
Candidate search information is selected in candidate search information aggregate as target search information.
As an example, electronic equipment can successively by candidate search information aggregate each candidate search information with
Similarity between search information is compared with default similarity threshold, selects similarity from candidate search information aggregate
Greater than the candidate search information of default similarity threshold.
As another example, electronic equipment can be first, in accordance with similarity size order in candidate search information aggregate
Candidate search information be ranked up；Then preset number (such as 1,3) is selected since the big side of similarity
Candidate search information.
Step 205, information to be pushed set obtained by scanning for using target search information is obtained, and is pushed to terminal
Equipment.
In the present embodiment, based on the target search information of taking-up selected by step 204, electronic equipment can use target and search
Rope information scans in search engine or pre-stored information bank, obtains information to be pushed set, and be pushed to terminal
Equipment.Wherein, information to be pushed can have the same or similar characteristic attribute with target search information.As an example, working as mesh
When mark search information is " rose ", the information to be pushed in information to be pushed set can be the information comprising " rose ".It needs
Illustrate, the method using search information search pushed information is existing well-known technique, and details are not described herein.
Information-pushing method provided by the embodiments of the present application, by will be from the information acquisition request that terminal device receives
Search information matched in history keyword lexon collection group, obtain history corresponding to the history keyword lexon collection of successful match and search
Rope information, to generate candidate search information aggregate；The candidate search in search information and candidate search information aggregate is calculated later
Similarity between information；It is then based on similarity calculated, target search letter is selected from candidate search information aggregate
Breath；It finally obtains and scans for obtained information to be pushed set using target search information, and be pushed to terminal device.Benefit
Target search information similar with the search information inputted with user scans for, and avoids the search information due to user's input
The problem of information push inaccuracy caused by inaccurate or lack of standardization, to improve the accuracy of information push.
With further reference to Fig. 3, it illustrates the processes 300 of another embodiment of information-pushing method.Information push
The process 300 of method, comprising the following steps:
Step 301, the information acquisition request that receiving terminal apparatus is sent.
In the present embodiment, the electronic equipment (such as server 105 shown in FIG. 1) of information-pushing method operation thereon
Can by wired connection mode or radio connection from terminal device (such as terminal device shown in FIG. 1 101,102,
103) information acquisition request is received.Wherein, information acquisition request may include search information.Search information can be user and be wanted
The key message of the information of acquisition is pushed to user's when user inputs search information in the input frame of searching class software
It would generally include user's information to be obtained in information.Search information can include but is not limited to single word, word combination,
Short sentence, long sentence etc..
Step 302, search information is segmented, obtains multiple keyword subsets of search information.
In the present embodiment, based on information acquisition request received by step 301, electronic equipment can be first with more
Kind participle technique segments the search information in information acquisition request, to obtain multiple keywords of search information；Then
Multiple keywords are combined by kind of combination, to obtain multiple keyword subsets of search information.
As an example, electronic equipment can carry out the processing such as full cutting method to search information first, content point
It is cut into word；Then importance calculating is carried out (for example, by using the reverse document-frequency method (Term of word frequency-to obtained word
Frequency-Inverse Document Frequency, TF-IDF)), it is searched for based on the result that importance calculates
The keyword set of information；Any combination finally is carried out to the keyword in the keyword set of search information, to be searched for
Multiple keyword subsets of information.
As an example, electronic equipment can segment search information first with stammerer segmenting method, with
To the keyword set of search information；Then the keyword in the keyword set of search information is utilized by Chinese language model
Matching Relation in search information, to generate multiple keyword subsets of search information.Wherein, stammerer segmenting method supports three
Kind participle mode: accurate model, searches engine-model at syntype.Accurate model, it is intended to sentence most accurately be cut, be suitble to
Text analyzing；Syntype can all be scanned all in sentence at the word of word, and speed is very fast, but cannot solve
Certainly ambiguity；Search engine mode to long word cutting again, improves recall rate, suitable for search on the basis of accurate model
Engine participle.Chinese language model (Chinese Language Model, CLM), and it is referred to as N-Gram, it is that big vocabulary connects
Common a kind of language model in continuous speech recognition.Chinese language model utilizes the collocation information in context between adjacent word,
It needs the phonetic continuously without space, stroke, or representing alphabetical or stroke number can when being converted into Chinese character string (i.e. sentence)
To calculate the sentence with the maximum frequency, to realize the automatic conversion for arriving Chinese character.The model is based on such a it is assumed that the
The appearance of N number of word is only related to the word of front N-1, and all uncorrelated to other any words, and the frequency of whole sentence is exactly that each word goes out
The product of the existing frequency.These frequencys can be obtained by directly counting the number of N number of word while appearance from corpus.As showing
Example, for search information " roller washing machine how much ", electronic equipment is first with stammerer segmenting method to " roller washing machine is more
Few money " is segmented, to obtain the keyword set of search information: " roller, washing machine, how much "；Then pass through Chinese
Language model utilizes Matching Relation in " roller washing machine how much ", generates 6 keyword subsets of search information: " roller ",
" washing machine ", " how much ", " roller, washing machine ", " washing machine, how much " and " roller, washing machine, how much ".
Step 303, the multiple keyword subsets for searching for information are matched in history keyword lexon collection group, obtain matching at
The history keyword lexon collection of function.
In the present embodiment, multiple keyword subsets based on the obtained search information of step 302, electronic equipment can be with
The multiple keyword subsets for searching for information are successively matched in history keyword lexon collection group, to obtain the history of successful match
Keyword subset.Wherein, if a keyword subset of search information and a history keyword in history keyword lexon collection group
Lexon collection is identical, it may be considered that the history keyword lexon collection is the history keyword lexon collection of successful match.
Step 304, the corresponding relationship based on history keyword lexon collection and historical search information, obtains the history of successful match
Historical search information corresponding to keyword subset.
In the present embodiment, the history keyword lexon collection based on successful match acquired in step 303, electronic equipment can be with
According to the corresponding relationship of history keyword subset and historical search information, obtain corresponding to the history keyword lexon collection of successful match
Historical search information.Wherein, a history keyword lexon collection can correspond at least one historical search information, a historical search
Information can equally correspond at least one history keyword lexon collection.
Step 305, comentropy corresponding to the history keyword lexon collection of successful match is obtained.
In the present embodiment, the history keyword lexon collection based on successful match acquired in step 304, electronic equipment can be with
Obtain comentropy corresponding to the history keyword lexon collection of successful match.
In the present embodiment, history keyword lexon collection is corresponding with comentropy.As an example, a history keyword lexon collection can
With at least one corresponding historical search information, firstly, electronic equipment is available using corresponding to the history keyword lexon collection
At least one historical search information scans for obtained pushed information set；Then, those skilled in the art can be to institute
Obtained each pushed information in pushed information set is analyzed, and is based on the analysis results each pushed information set-point
Hit probability；Finally, electronic equipment can use the click probability calculation of each pushed information in the pushed information set history
The comentropy of keyword subset.
Optionally, electronic equipment can use the comentropy H that following formula calculates history keyword lexon collection:
Wherein, n is the number of the pushed information in pushed information set, and p is the click probability of pushed information, piIt is i-th
The click probability of a pushed information.
Step 306, comentropy and candidate search information aggregate corresponding to the history keyword lexon collection based on successful match
In candidate search information corresponding to comentropy corresponding to history keyword lexon collection, calculate search information and candidate search believed
The similarity between candidate search information in breath set.
In the present embodiment, electronic equipment can use comentropy corresponding to the history keyword lexon collection of successful match and
Comentropy corresponding to history keyword lexon collection corresponding to candidate search information in candidate search information aggregate calculates search
The similarity between candidate search information in information and candidate search information aggregate.Here, electronic equipment can use and walk
Rapid 405 identical mode calculates comentropy corresponding to history keyword lexon collection corresponding to candidate search information, here no longer
It repeats.
In some optional implementations of the present embodiment, for each candidate search in candidate search information aggregate
Information, the history keyword lexon collection and history corresponding to the candidate search information that electronic equipment can obtain successful match first
The history keyword lexon collection of comentropy corresponding to the intersection of keyword subset and successful match and the candidate search information institute are right
Comentropy corresponding to the difference set for the history keyword lexon collection answered；It is then based on corresponding to comentropy corresponding to intersection and difference set
Comentropy, calculate search information and the candidate search information between similarity.Wherein, intersection may include successful match
History keyword lexon corresponding to history keyword lexon collection and the candidate search information concentrates identical history keyword word, and difference set can
With include the history keyword lexon collection of successful match concentrate from history keyword lexon corresponding to the candidate search information it is different
History keyword word.
Optionally, electronic equipment can be calculated similar between search information and the candidate search information by following formula
Spend S:
S=(1-0.25*H+)-(1-0.25*H-)2+sig mod Sn；
Wherein, H+For comentropy corresponding to intersection, H-For comentropy corresponding to difference set, SnFor in intersection not in history
The length of history keyword word in keyword subset group and with the not history keyword word in history keyword lexon collection group in difference set
Length sum its difference.
In some optional implementations of the present embodiment, for each candidate search in candidate search information aggregate
Information, the history keyword lexon collection and history corresponding to the candidate search information that electronic equipment can obtain successful match first
Comentropy corresponding to the intersection of keyword subset；It is then based on comentropy corresponding to intersection, calculates search information and the time
Similarity between choosing search information.Wherein, comentropy corresponding to intersection is bigger, search information and the candidate search information it
Between similarity it is bigger.
In some optional implementations of the present embodiment, for each candidate search in candidate search information aggregate
Information, the history keyword lexon collection and history corresponding to the candidate search information that electronic equipment can obtain successful match first
Comentropy corresponding to the difference set of keyword subset；It is then based on comentropy corresponding to difference set, calculates search information and the time
Similarity between choosing search information.Wherein, comentropy corresponding to difference set is smaller, search information and the candidate search information it
Between similarity it is bigger.
Step 307, it is based on similarity calculated, candidate search information conduct is selected from candidate search information aggregate
Target search information.
In the present embodiment, it is based on step 306 similarity calculated, electronic equipment can be from candidate search information aggregate
In select candidate search information as target search information.
Step 308, information to be pushed set obtained by scanning for using target search information is obtained, and is pushed to terminal
Equipment.
In the present embodiment, based on the target search information of taking-up selected by step 307, electronic equipment can use target and search
Rope information scans in search engine or pre-stored information bank, obtains information to be pushed set, and be pushed to terminal
Equipment.Wherein, information to be pushed can have the same or similar characteristic attribute with target search information.
From figure 3, it can be seen that compared with the corresponding embodiment of Fig. 2, the process of the information-pushing method in the present embodiment
300 highlight the step of choosing target push information.The scheme of the present embodiment description is right using history keyword lexon collection institute as a result,
The comentropy answered calculates the similarity between search information and candidate search information, thus improve calculated similarity
Accuracy facilitates the accuracy for further increasing information push.
With further reference to Fig. 4, it illustrates the processes 400 of one embodiment of history keyword lexon set creation method.It should
The process 400 of history keyword lexon set creation method, comprising the following steps:
Step 401, set of records ends is clicked in the historical search obtained in historical time section.
In the present embodiment, the electronic equipment of history keyword lexon set creation method operation thereon is (such as shown in FIG. 1
Server 105) historical search in available historical time section (such as previous moon, previous season, the first half) clicks
Set of records ends.Wherein, historical search click record can be user and scanned for using search information and click pushed information
Afterwards caused by record, historical search click set of records ends in historical search click record may include historical search information and
The click frequency of history click article category.Wherein, the category of article can be three-level category.By taking household appliances article as an example, three
Grade category can include but is not limited to refrigerator class, washing machine class, air-conditioning class, television class etc..
Step 402, each historical search information is segmented, obtains multiple history keywords of each historical search information
Lexon collection.
In the present embodiment, the historical search information in record is clicked for every historical search, electronic equipment can be first
The historical search information is segmented using a variety of participle techniques, to obtain multiple history keywords that the history searches prime information
Word；Then multiple history keyword words are combined in the way of multiple combinations, are gone through with obtaining the multiple of the historical search information
History keyword subset.
As an example, electronic equipment can carry out the processing such as full cutting method to historical search information first, in
Appearance is divided into word；Then importance calculating (for example, by using the reverse document-frequency method of word frequency -) is carried out to obtained word, be based on
The result that importance calculates obtains the history keyword set of words of historical search information；Finally to the history of the historical search information
History keyword word in keyword set carries out any combination, to obtain multiple history keyword lexons of the historical search information
Collection.
As an example, electronic equipment can segment historical search information first with stammerer segmenting method,
To obtain the history keyword set of words of historical search information；Then the history of historical search information is utilized by Chinese language model
Matching Relation of the history keyword word in historical search information in keyword set, is gone through with generating the multiple of historical search information
History keyword subset.
Step 403, for statistical analysis to the click frequency of each history click article category, obtain each history keyword
Multiple history of lexon collection click the click frequency of article category.
In the present embodiment, the click frequency that electronic equipment can click article category to each history carries out statistical
Analysis, so that the multiple history for obtaining each history keyword lexon collection click the click frequency of article category.As an example, if one
History keyword lexon collection corresponds to multiple historical searches and clicks record, then counting this multiple historical search clicks the history in recording
(for example, clicking article category for identical history, being clicked the conduct of the sum of frequency should for the click frequency of click article category
History clicks the click frequency of article category, and the history that default click frequency threshold value is less than for clicking the frequency clicks article product
Class deletes the click frequency that the history clicks article category), the history as the history keyword lexon collection clicks article category
Click the frequency.
Step 404, it is calculated using the click frequency that multiple history of each history keyword lexon collection click article category each
Comentropy corresponding to a history keyword lexon collection.
In the present embodiment, each history keyword lexon collection concentrated for each history keyword lexon, electronic equipment can
The history keyword lexon collection institute is calculated with the click frequency for clicking article category using multiple history of the history keyword lexon collection
Corresponding comentropy.
Optionally, electronic equipment can use the comentropy H that following formula calculates history keyword lexon collection:
Wherein, m is the number that multiple history click article category, and q is the click probability that history clicks article category, that is, is gone through
The click frequency that history clicks article category clicks the ratio of total click frequency of article category, q with m historyjFor j-th of history
The click probability of article category is clicked, i.e., j-th of history clicks the click frequency of article category and m history clicks article category
Total click frequency ratio.
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 set, the Installation practice is corresponding with 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 may include: receiving unit 501, matching unit 502,
Computing unit 503, selection unit 504 and push unit 505.Wherein, receiving unit 501 are configured to receiving terminal apparatus hair
The information acquisition request sent, wherein information acquisition request includes search information；Matching unit 502 is configured to that information will be searched for
It is matched in history keyword lexon collection group, obtains historical search information corresponding to the history keyword lexon collection of successful match, with
Generate candidate search information aggregate, wherein history keyword lexon collection is corresponding with historical search information；Computing unit 503, configuration are used
The similarity between candidate search information in calculating search information and candidate search information aggregate；Selection unit 504, configuration
For being based on similarity calculated, candidate search information is selected from candidate search information aggregate and is believed as target search
Breath；Push unit 505 is configured to information to be pushed set obtained by acquisition is scanned for using target search information, and pushes away
Give terminal device.
In the present embodiment, in information push-delivery apparatus 500: receiving unit 501, matching unit 502, computing unit 503, choosing
The specific processing and its brought technical effect for taking unit 504 and push unit 505 can be respectively with reference in Fig. 2 corresponding embodiments
Step 201, step 202, step 203, the related description of step 204 and step 205, details are not described herein.
In some optional implementations of the present embodiment, matching unit 502 may include: participle subelement (in figure
It is not shown), it is configured to segment search information, obtains multiple keyword subsets of search information；Coupling subelement (figure
In be not shown), be configured to match the multiple keyword subsets for searching for information in history keyword lexon collection group, obtain matching
Successful history keyword lexon collection；First obtain subelement (not shown), be configured to based on history keyword lexon collection with
The corresponding relationship of historical search information obtains historical search information corresponding to the history keyword lexon collection of successful match.
In some optional implementations of the present embodiment, participle subelement may include: that word segmentation module (is not shown in figure
Out), it is configured to segment search information using stammerer segmenting method, obtains the keyword set of search information；It generates
Module (not shown) is configured to Chinese language model and is existed using the keyword in the keyword set of search information
The Matching Relation in information is searched for, multiple keyword subsets of search information are generated.
In some optional implementations of the present embodiment, computing unit 503 may include: the second acquisition subelement
(not shown) is configured to obtain comentropy corresponding to the history keyword lexon collection of successful match, wherein history keyword
Lexon collection is corresponding with comentropy；Computation subunit (not shown) is configured to the history keyword lexon based on successful match
History keyword lexon collection institute corresponding to candidate search information in collection corresponding comentropy and candidate search information aggregate is right
The comentropy answered calculates the similarity between the candidate search information in search information and candidate search information aggregate.
In some optional implementations of the present embodiment, computation subunit can be further configured to: for waiting
Each candidate search information in choosing search information aggregate, the history keyword lexon collection and the candidate search for obtaining successful match are believed
The history keyword lexon collection and the time of comentropy corresponding to the intersection of the corresponding history keyword lexon collection of breath and successful match
Comentropy corresponding to the difference set of history keyword lexon collection corresponding to choosing search information, based on comentropy corresponding to intersection and
Comentropy corresponding to difference set calculates the similarity between search information and the candidate search information.
In some optional implementations of the present embodiment, the history keyword lexon collection in history keyword lexon collection group can
To generate as follows: set of records ends is clicked in the historical search obtained in historical time section, wherein note is clicked in historical search
Record includes the click frequency that historical search information and history click article category；Each historical search information is segmented, is obtained
To multiple history keyword lexon collection of each historical search information；The click frequency for clicking article category to each history is united
Meter analysis, the multiple history for obtaining each history keyword lexon collection click the click frequency of article category；It is closed using each history
The click frequency that multiple history of keyword subset click article category calculates comentropy corresponding to each history keyword lexon collection.
Below with reference to Fig. 6, it illustrates the computer systems 600 for the electronic equipment for being suitable for being used to realize the embodiment of the present application
Structural schematic diagram.Electronic equipment shown in Fig. 6 is only an example, function to the embodiment of the present application and should not use model
Shroud carrys out any restrictions.
As shown in fig. 6, computer system 600 includes central processing unit (CPU) 601, it can be read-only according to being stored in
Program in memory (ROM) 602 or be loaded into the program in random access storage device (RAM) 603 from storage section 608 and
Execute various movements appropriate 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 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to always
Line 604.
I/O interface 605 is connected to lower component: the importation 606 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 608 including hard disk etc.；
And the communications portion 609 of the network interface card including LAN card, modem etc..Communications portion 609 via such as because
The network of spy's net executes communication process.Driver 610 is also connected to I/O interface 605 as needed.Detachable media 611, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 610, in order to read from thereon
Computer program be mounted into storage section 608 as needed.
Particularly, 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 comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 609, and/or from detachable media
611 are mounted.When the computer program is executed by central processing unit (CPU) 601, limited in execution 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 storage medium either the two any combination.Computer readable storage medium for example can be --- but
Be not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.
The more specific example of computer readable storage medium can include but is not limited to: have one or more conducting wires electrical connection,
Portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only deposit
Reservoir (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory
Part or above-mentioned any appropriate combination.In this application, computer readable storage medium, which can be, any include or stores
The tangible medium of program, the program can be commanded execution system, device or device use or in connection.And
In the application, computer-readable signal media may include in a base band or the data as the propagation of carrier wave a part are believed
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 other than readable storage medium storing program for executing, the computer-readable medium can send, propagate or transmit use
In by the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc., Huo Zheshang
Any appropriate combination stated.
The calculating of the operation for executing the application can be write with one or more programming languages or combinations thereof
Machine program code, described program design language include object oriented program language-such as Java, Smalltalk, C+
+, further include conventional procedural programming language-such as " C " language or similar programming language.Program code can
Fully to execute, partly execute on the user computer on the user computer, be executed as an independent software package,
Part executes on the remote computer or executes on a remote computer or server completely on the user computer for part.
In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network (LAN)
Or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize Internet service
Provider is connected by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or 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 also can be set in the processor, for example, can be described as: a kind of processor packet
Include receiving unit, matching unit, computing unit, selection unit and push unit.Wherein, the title of these units is in certain situation
Under do not constitute restriction to the unit itself, for example, receiving unit is also described as the " letter that receiving terminal apparatus is sent
Cease the unit of acquisition request ".
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in electronic equipment described in above-described embodiment；It is also possible to individualism, and without in the supplying electronic equipment.
Above-mentioned computer-readable medium carries one or more program, when said one or multiple programs are held by the electronic equipment
When row, so that the electronic equipment: the information acquisition request that receiving terminal apparatus is sent, wherein information acquisition request includes search
Information；Search information is matched in history keyword lexon collection group, is obtained corresponding to the history keyword lexon collection of successful match
Historical search information, to generate candidate search information aggregate, wherein history keyword lexon collection is corresponding with historical search information；Meter
Calculate the similarity between the candidate search information in search information and candidate search information aggregate；Based on similarity calculated,
Candidate search information is selected from candidate search information aggregate as target search information；Obtain using target search information into
Information to be pushed set obtained by row is searched for, and it is pushed to terminal device.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (14)
1. a kind of information-pushing method, which is characterized in that the described method includes:
The information acquisition request that receiving terminal apparatus is sent, wherein the information acquisition request includes search information；
Described search information is matched in history keyword lexon collection group, is obtained corresponding to the history keyword lexon collection of successful match
Historical search information, to generate candidate search information aggregate, wherein history keyword lexon collection is corresponding with historical search information；
Calculate the similarity between the candidate search information in described search information and the candidate search information aggregate；
Based on similarity calculated, candidate search information is selected from the candidate search information aggregate as target search
Information；
Information to be pushed set obtained by scanning for using the target search information is obtained, and is pushed to the terminal and sets
It is standby.
2. the method according to claim 1, wherein it is described by described search information in history keyword lexon collection group
Middle matching obtains historical search information corresponding to the history keyword lexon collection of successful match, comprising:
Described search information is segmented, multiple keyword subsets of described search information are obtained；
Multiple keyword subsets of described search information are matched in history keyword lexon collection group, obtain the history of successful match
Keyword subset；
Corresponding relationship based on history keyword lexon collection and historical search information obtains the history keyword lexon of the successful match
The corresponding historical search information of collection.
3. according to the method described in claim 2, obtaining described it is characterized in that, described segment described search information
Search for multiple keyword subsets of information, comprising:
Described search information is segmented using stammerer segmenting method, obtains the keyword set of described search information；
Utilize the keyword in the keyword set of described search information in described search information by Chinese language model
Matching Relation generates multiple keyword subsets of described search information.
4. the method according to claim 1, wherein the calculating described search information and the candidate search are believed
The similarity between candidate search information in breath set, comprising:
Obtain comentropy corresponding to the history keyword lexon collection of the successful match, wherein history keyword lexon collection and information
Entropy is corresponding；
In comentropy and the candidate search information aggregate corresponding to history keyword lexon collection based on the successful match
Comentropy corresponding to history keyword lexon collection corresponding to candidate search information calculates described search information and searches with the candidate
The similarity between candidate search information in rope information aggregate.
5. according to the method described in claim 4, it is characterized in that, the history keyword lexon collection based on the successful match
History keyword lexon collection institute corresponding to candidate search information in corresponding comentropy and the candidate search information aggregate
Corresponding comentropy calculates similar between described search information and the candidate search information in the candidate search information aggregate
Degree, comprising:
For each candidate search information in the candidate search information aggregate, the history keyword word of the successful match is obtained
Comentropy and the successful match corresponding to the intersection of history keyword lexon collection corresponding to subset and the candidate search information
History keyword lexon collection and the candidate search information corresponding to history keyword lexon collection difference set corresponding to comentropy, base
Comentropy corresponding to the comentropy corresponding to the intersection and the difference set calculates described search information and the candidate search
Similarity between information.
6. method described in one of -5 according to claim 1, which is characterized in that the history in the history keyword lexon collection group is closed
Keyword subset generates as follows:
Set of records ends is clicked in the historical search obtained in historical time section, wherein it includes historical search that record is clicked in historical search
Information and history click the click frequency of article category；
Each historical search information is segmented, multiple history keyword lexon collection of each historical search information are obtained；
The click frequency for clicking article category to each history is for statistical analysis, obtains the multiple of each history keyword lexon collection
The click frequency of history click article category；
Each history keyword word is calculated using the click frequency that multiple history of each history keyword lexon collection click article category
Comentropy corresponding to subset.
7. a kind of information push-delivery apparatus, which is characterized in that described device includes:
Receiving unit is configured to the information acquisition request of receiving terminal apparatus transmission, wherein the information acquisition request includes
Search for information；
Matching unit is configured to match described search information in history keyword lexon collection group, obtains going through for successful match
Historical search information corresponding to history keyword subset, to generate candidate search information aggregate, wherein history keyword lexon collection with
Historical search information is corresponding；
Computing unit, be configured to calculate candidate search information in described search information and the candidate search information aggregate it
Between similarity；
Selection unit is configured to be selected candidate based on similarity calculated from the candidate search information aggregate and searched
Rope information is as target search information；
Push unit is configured to information to be pushed set obtained by acquisition is scanned for using the target search information, and
It is pushed to the terminal device.
8. device according to claim 7, which is characterized in that the matching unit includes:
Subelement is segmented, is configured to segment described search information, obtains multiple crucial lexons of described search information
Collection；
Coupling subelement, is configured to multiple keyword subsets of described search information in history keyword lexon collection group
Match, obtains the history keyword lexon collection of successful match；
First obtains subelement, is configured to the corresponding relationship based on history keyword lexon collection and historical search information, obtains institute
State historical search information corresponding to the history keyword lexon collection of successful match.
9. device according to claim 8, which is characterized in that the participle subelement includes:
Word segmentation module is configured to segment described search information using stammerer segmenting method, obtains described search information
Keyword set；
Generation module is configured to Chinese language model and is existed using the keyword in the keyword set of described search information
Matching Relation in described search information generates multiple keyword subsets of described search information.
10. device according to claim 7, which is characterized in that the computing unit includes:
Second obtains subelement, is configured to obtain comentropy corresponding to the history keyword lexon collection of the successful match,
In, history keyword lexon collection is corresponding with comentropy；
Computation subunit is configured to comentropy and the time corresponding to the history keyword lexon collection based on the successful match
Comentropy corresponding to history keyword lexon collection corresponding to the candidate search information in information aggregate is searched in choosing, is searched described in calculating
The similarity between candidate search information in rope information and the candidate search information aggregate.
11. device according to claim 10, which is characterized in that the computation subunit is further configured to:
For each candidate search information in the candidate search information aggregate, the history keyword word of the successful match is obtained
Comentropy and the successful match corresponding to the intersection of history keyword lexon collection corresponding to subset and the candidate search information
History keyword lexon collection and the candidate search information corresponding to history keyword lexon collection difference set corresponding to comentropy, base
Comentropy corresponding to the comentropy corresponding to the intersection and the difference set calculates described search information and the candidate search
Similarity between information.
12. the device according to one of claim 7-11, which is characterized in that the history in the history keyword lexon collection group
Keyword subset generates as follows:
Set of records ends is clicked in the historical search obtained in historical time section, wherein it includes historical search that record is clicked in historical search
Information and history click the click frequency of article category；
Each historical search information is segmented, multiple history keyword lexon collection of each historical search information are obtained；
The click frequency for clicking article category to each history is for statistical analysis, obtains the multiple of each history keyword lexon collection
The click frequency of history click article category；
Each history keyword word is calculated using the click frequency that multiple history of each history keyword lexon collection click article category
Comentropy corresponding to subset.
13. a kind of electronic equipment, which is characterized in that the electronic equipment includes:
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as method as claimed in any one of claims 1 to 6.
14. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
Such as method as claimed in any one of claims 1 to 6 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711058940.6A CN110069698B (en) | 2017-11-01 | 2017-11-01 | Information pushing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711058940.6A CN110069698B (en) | 2017-11-01 | 2017-11-01 | Information pushing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110069698A true CN110069698A (en) | 2019-07-30 |
| CN110069698B CN110069698B (en) | 2021-09-03 |
Family
ID=67364546
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711058940.6A Active CN110069698B (en) | 2017-11-01 | 2017-11-01 | Information pushing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110069698B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242724A (en) * | 2020-01-06 | 2020-06-05 | 北京字节跳动网络技术有限公司 | Object pushing method and device |
| CN111597311A (en) * | 2020-01-14 | 2020-08-28 | 北京百度网讯科技有限公司 | Method and apparatus for outputting information |
| CN111597413A (en) * | 2020-05-14 | 2020-08-28 | 上海携程商务有限公司 | Information pushing method, system, equipment and storage medium |
| CN113051392A (en) * | 2021-04-30 | 2021-06-29 | 中国银行股份有限公司 | Knowledge pushing method and device |
| CN113139115A (en) * | 2020-01-19 | 2021-07-20 | 北京沃东天骏信息技术有限公司 | Information recommendation method, search method, device, client, medium and equipment |
| CN113377976A (en) * | 2021-08-16 | 2021-09-10 | 北京达佳互联信息技术有限公司 | Resource searching method and device, computer equipment and storage medium |
| CN113763103A (en) * | 2021-01-19 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Method and device for determining collocation relationship of articles, electronic equipment and storage medium |
| CN113763081A (en) * | 2020-08-26 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Article recall method and device |
| CN114222000A (en) * | 2021-12-13 | 2022-03-22 | 中国平安财产保险股份有限公司 | Information pushing method and device, computer equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799589A (en) * | 2011-05-25 | 2012-11-28 | 阿里巴巴集团控股有限公司 | Information pushing method and device |
| CN103631803A (en) * | 2012-08-23 | 2014-03-12 | 百度国际科技（深圳）有限公司 | Method, device and server for advertisement orientation based on input behaviors |
| CN105808685A (en) * | 2016-03-02 | 2016-07-27 | 腾讯科技（深圳）有限公司 | Promotion information pushing method and device |
| CN106897317A (en) * | 2015-12-21 | 2017-06-27 | 北京奇虎科技有限公司 | Based on the method and apparatus that keyword scans for recommending |
| CN107169077A (en) * | 2017-05-10 | 2017-09-15 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN107172151A (en) * | 2017-05-18 | 2017-09-15 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN107220386A (en) * | 2017-06-29 | 2017-09-29 | 北京百度网讯科技有限公司 | Information-pushing method and device |
| CN107256267A (en) * | 2017-06-19 | 2017-10-17 | 北京百度网讯科技有限公司 | Querying method and device |
| US20170308583A1 (en) * | 2016-04-20 | 2017-10-26 | Facebook, Inc. | Suggested Queries Based on Interaction History on Online Social Networks |
-
2017
- 2017-11-01 CN CN201711058940.6A patent/CN110069698B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799589A (en) * | 2011-05-25 | 2012-11-28 | 阿里巴巴集团控股有限公司 | Information pushing method and device |
| CN103631803A (en) * | 2012-08-23 | 2014-03-12 | 百度国际科技（深圳）有限公司 | Method, device and server for advertisement orientation based on input behaviors |
| CN106897317A (en) * | 2015-12-21 | 2017-06-27 | 北京奇虎科技有限公司 | Based on the method and apparatus that keyword scans for recommending |
| CN105808685A (en) * | 2016-03-02 | 2016-07-27 | 腾讯科技（深圳）有限公司 | Promotion information pushing method and device |
| US20170308583A1 (en) * | 2016-04-20 | 2017-10-26 | Facebook, Inc. | Suggested Queries Based on Interaction History on Online Social Networks |
| CN107169077A (en) * | 2017-05-10 | 2017-09-15 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN107172151A (en) * | 2017-05-18 | 2017-09-15 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN107256267A (en) * | 2017-06-19 | 2017-10-17 | 北京百度网讯科技有限公司 | Querying method and device |
| CN107220386A (en) * | 2017-06-29 | 2017-09-29 | 北京百度网讯科技有限公司 | Information-pushing method and device |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242724A (en) * | 2020-01-06 | 2020-06-05 | 北京字节跳动网络技术有限公司 | Object pushing method and device |
| CN111597311A (en) * | 2020-01-14 | 2020-08-28 | 北京百度网讯科技有限公司 | Method and apparatus for outputting information |
| CN111597311B (en) * | 2020-01-14 | 2023-04-25 | 北京百度网讯科技有限公司 | Method and device for outputting information |
| CN113139115A (en) * | 2020-01-19 | 2021-07-20 | 北京沃东天骏信息技术有限公司 | Information recommendation method, search method, device, client, medium and equipment |
| CN111597413A (en) * | 2020-05-14 | 2020-08-28 | 上海携程商务有限公司 | Information pushing method, system, equipment and storage medium |
| CN113763081A (en) * | 2020-08-26 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Article recall method and device |
| CN113763103A (en) * | 2021-01-19 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Method and device for determining collocation relationship of articles, electronic equipment and storage medium |
| CN113051392A (en) * | 2021-04-30 | 2021-06-29 | 中国银行股份有限公司 | Knowledge pushing method and device |
| CN113377976A (en) * | 2021-08-16 | 2021-09-10 | 北京达佳互联信息技术有限公司 | Resource searching method and device, computer equipment and storage medium |
| CN114222000A (en) * | 2021-12-13 | 2022-03-22 | 中国平安财产保险股份有限公司 | Information pushing method and device, computer equipment and storage medium |
| CN114222000B (en) * | 2021-12-13 | 2024-02-02 | 中国平安财产保险股份有限公司 | Information pushing method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110069698B (en) | 2021-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110069698A (en) | Information-pushing method and device | |
| US10795939B2 (en) | Query method and apparatus | |
| CN108804532B (en) | Query intention mining method and device and query intention identification method and device | |
| CN107609152B (en) | Method and apparatus for expanding query expressions | |
| WO2018149115A1 (en) | Method and apparatus for providing search results | |
| CN109460513A (en) | Method and apparatus for generating clicking rate prediction model | |
| CN107105031A (en) | Information-pushing method and device | |
| CN107729336A (en) | Data processing method, equipment and system | |
| CN109918555B (en) | Method, apparatus, device and medium for providing search suggestions | |
| CN108256070A (en) | For generating the method and apparatus of information | |
| CN108540508B (en) | Method, device and equipment for pushing information | |
| CN108628830A (en) | A kind of method and apparatus of semantics recognition | |
| CN113806588B (en) | Method and device for searching video | |
| US20220122124A1 (en) | Method of recommending content, electronic device, and computer-readable storage medium | |
| CN103309869A (en) | Method and system for recommending display keyword of data object | |
| CN109933217A (en) | Method and apparatus for pushing sentence | |
| CN110737824B (en) | Content query method and device | |
| CN106681598A (en) | Information input method and device | |
| CN109190123A (en) | Method and apparatus for output information | |
| CN109902152B (en) | Method and apparatus for retrieving information | |
| CN110737820B (en) | Method and apparatus for generating event information | |
| CN105488027B (en) | The method for pushing and device of keyword | |
| CN109213916A (en) | Method and apparatus for generating information | |
| CN112100216A (en) | Creative keyword processing method and device | |
| CN112417996A (en) | Information processing method and device for industrial drawing, electronic equipment and storage medium |
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 |