CN109829117A - Method and apparatus for pushed information - Google Patents
Method and apparatus for pushed information Download PDFInfo
- Publication number
- CN109829117A CN109829117A CN201910155198.3A CN201910155198A CN109829117A CN 109829117 A CN109829117 A CN 109829117A CN 201910155198 A CN201910155198 A CN 201910155198A CN 109829117 A CN109829117 A CN 109829117A
- Authority
- CN
- China
- Prior art keywords
- voice data
- similarity
- information
- keyword
- user
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Embodiment of the disclosure discloses the method and apparatus for pushed information.One specific embodiment of this method includes: the voice data of keyword obtaining first object user, concentrating corresponding to predetermined keyword, obtains voice data collection；For the voice data that voice data is concentrated, at least one matching voice data of the corresponding keyword of the voice data is obtained；Determine that the voice data matches the similarity of voice data at least one；According to the sequence of corresponding similarity from big to small, is concentrated from voice data and choose target numbers voice data；According to the selected corresponding keyword of voice data, information to be pushed is determined, and push identified information to be pushed to the corresponding terminal device of first object user.The embodiment realizes the preference of the speech data analysis user according to user, and then can be based on the analysis results to user's pushed information.
Description
Technical field
Embodiment of the disclosure is related to field of computer technology, and in particular to the method and apparatus for pushed information.
Background technique
It is more existing to apply when to user's pushed information, usually user is analyzed according to the historical behavior data of user
Preference, thus according to user preference to user's pushed information, so that the information pushed to user is compared with the preference for meeting user.
But it is some as users for the first time log in using application in the case where, application may there is no user's history behavior number
According to.And in the case where some early period or users less using the number of application for just having begun to use application such as user, application
The user's history behavioral data having may be less.In these cases, the information of its preference how is relatively met to user's push
It is the one aspect for requiring study and thinking deeply in process of information push.
Summary of the invention
Embodiment of the disclosure proposes the method and apparatus for pushed information.
In a first aspect, embodiment of the disclosure provides a kind of method for pushed information, this method comprises: obtaining the
One target user, corresponding to predetermined keyword concentrate keyword voice data, obtain voice data collection；For voice number
According to the voice data of concentration, at least one matching voice data of the corresponding keyword of the voice data is obtained；Determine the voice
Data match the similarity of voice data at least one；According to the sequence of corresponding similarity from big to small, from voice data
It concentrates and chooses target numbers voice data；According to the selected corresponding keyword of voice data, information to be pushed is determined, with
And identified information to be pushed is pushed to the corresponding terminal device of first object user.
In some embodiments, determine that the voice data matches the similarity of voice data at least one, comprising: determine
The voice data matches the similarity of the matching voice data in voice data at least one respectively, obtains similarity collection；Root
According to obtained similarity collection, determine that the voice data matches the similarity of voice data at least one.
In some embodiments, according to obtained similarity collection, determine that the voice data matches voice number at least one
According to similarity, comprising: obtain at least one matching voice data in the corresponding weighted value of matching voice data；It determines
The weighted average for the similarity that obtained similarity is concentrated matches the phase of voice data as the voice data at least one
Like degree.
In some embodiments, at least one matching voice data determine as follows: obtain at least one second
Target user's typing, at least one corresponding keyword of matching voice data voice data is obtained as candidate speech data
To candidate speech data set, wherein the corresponding terminal device of the second target user was pushed target information, wherein target letter
Breath is according to determined by least one corresponding keyword of matching voice data；For the candidate language in candidate speech data set
Sound data obtain the user behavior data that corresponding second target user of the candidate speech data is directed to target information；In response to
It determines that user behavior data meets preset condition, chooses the candidate speech data as matching voice data.
In some embodiments, according to the selected corresponding keyword of voice data, information to be pushed is determined, comprising:
According to corresponding to the corresponding user of at least one matching voice data of the corresponding keyword of selected voice data
History pushed information, determines information to be pushed.
Second aspect, embodiment of the disclosure provide a kind of device for pushed information, which includes: to obtain list
Member, the voice data of keyword being configured to obtain first object user, concentrating corresponding to predetermined keyword, obtains voice
Data set；Determination unit is configured to the voice data concentrated for voice data, obtains the corresponding keyword of the voice data
At least one matching voice data；Determine that the voice data matches the similarity of voice data at least one；Selection unit,
It is configured to the sequence from big to small according to corresponding similarity, is concentrated from voice data and chooses target numbers voice data；
Push unit, is configured to according to the selected corresponding keyword of voice data, determines information to be pushed, and to first
The corresponding terminal device of target user pushes identified information to be pushed.
In some embodiments, determination unit is further configured to: determine the voice data respectively at least one
Similarity with the matching voice data in voice data, obtains similarity collection；According to obtained similarity collection, the voice is determined
Data match the similarity of voice data at least one.
In some embodiments, determination unit is further configured to: obtaining at least one matching voice data
With the corresponding weighted value of voice data；Determine the weighted average for the similarity that obtained similarity is concentrated as the voice
Data match the similarity of voice data at least one.
In some embodiments, at least one matching voice data determine as follows: obtain at least one second
Target user's typing, at least one corresponding keyword of matching voice data voice data is obtained as candidate speech data
To candidate speech data set, wherein the corresponding terminal device of the second target user was pushed target information, wherein target letter
Breath is according to determined by least one corresponding keyword of matching voice data；For the candidate language in candidate speech data set
Sound data obtain the user behavior data that corresponding second target user of the candidate speech data is directed to target information；In response to
It determines that user behavior data meets preset condition, chooses the candidate speech data as matching voice data.
In some embodiments, push unit is further configured to: according to the selected corresponding key of voice data
History pushed information corresponding to the corresponding user of at least one matching voice data of word, determines information to be pushed.
The third aspect, embodiment of the disclosure provide a kind of server, 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, embodiment of the disclosure provide a kind of computer-readable medium, are stored thereon with computer program,
The method as described in implementation any in first aspect is realized when the computer program is executed by processor.
Embodiment of the disclosure provide the method and apparatus for pushed information, by acquisition first object user,
Corresponding to the voice data for the keyword that predetermined keyword is concentrated, voice data collection is obtained；The voice concentrated for voice data
Data obtain at least one matching voice data of the corresponding keyword of the voice data；Determine the voice data and at least one
The similarity of a matching voice data；According to the sequence of corresponding similarity from big to small, is concentrated from voice data and choose target
Number voice data；According to the selected corresponding keyword of voice data, information to be pushed is determined, and to first object
The corresponding terminal device of user push determined by information to be pushed, to realize according to the speech data analysis user's of user
Preference, and then can be based on the analysis results to user's pushed information.
Specifically, at least due to the voice data and Keywords matching of user's keyword corresponding for known information
The similarity of one voice data is generally higher.Therefore, it is possible to use user corresponds to the voice data and keyword of keyword
The similarity of at least one matched voice data characterizes user to the familiarity of keyword.And user is for its preference
The familiarity of information is usually higher.Therefore, it is possible to use user characterizes user to keyword to the familiarity of keyword
Preference.Based on this, the relevant information of the higher keyword of user preference degree can be chosen and push to user.
For it is some without user's history behavioral data or less user's history behavioral data in the case of, be based on by this
The information of the voice data of user pushes mode, avoids and randomly chooses pushed information in this case and user is caused to connect
Many information lost interest in or will not clicked are received, the unnecessary of the server-side of user terminal and pushed information is in turn resulted in
Flow consumption.
It, can be in conjunction with the information of this voice data based on user for having the case where algorithm of determining pushed information
Push mode is to user's pushed information.By more analyzing data, help to increase the analysis knot to the preference analysis of user
The accuracy of fruit.
On the basis of obtaining accurate user preference analysis result, choosing user may push away compared with the information of preference
It send.On the one hand it for the application of pushed information, is pushed by accurate information, adaptable user's viscosity avoided
The push of multi-user's uninterested information and caused by customer churn.It on the other hand, can be to avoid a large amount of as described in above-mentioned analysis
The push of the uninterested information of user so that user browses to its interested information faster, while saving user terminal
With the flow of the server-side of pushed information.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the disclosure is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that one embodiment of the disclosure can be applied to exemplary system architecture figure therein；
Fig. 2 is the flow chart according to one embodiment of the method for pushed information of the disclosure；
Fig. 3 is the schematic diagram of an application scenarios of the method according to an embodiment of the present disclosure for pushed information；
Fig. 4 is the flow chart according to another embodiment of the method for pushed information of the disclosure；
Fig. 5 is the structural schematic diagram according to one embodiment of the device for pushed information of the disclosure；
Fig. 6 is adapted for the structural schematic diagram for realizing the electronic equipment of embodiment of the disclosure.
Specific embodiment
The disclosure 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 feature in embodiment and embodiment in the disclosure can phase
Mutually combination.The disclosure 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 method for pushed information of the disclosure or the implementation of the device for pushed information
The exemplary architecture 100 of example.
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..
Terminal device 101,102,103 is interacted by network 104 with server 105, to receive or send message etc..Terminal
Various client applications can be installed in equipment 101,102,103.Such as the application of browser class, searching class application etc..
Terminal device 101,102,103 can be hardware, be also possible to software.When terminal device 101,102,103 is hard
When part, the various electronic equipments of interactive voice, including but not limited to smart phone, plate are can be with display screen and supported
Computer, E-book reader, pocket computer on knee and desktop computer etc..When terminal device 101,102,103 is soft
When part, it may be mounted in above-mentioned cited electronic equipment.Its may be implemented into multiple softwares or software module (such as
The multiple softwares or software module of Distributed Services are provided), single software or software module also may be implemented into.It does not do and has herein
Body limits.
Server 105 can be to provide the server of various services, for example, be installed on terminal device 101,102,103
Client application provide support back-end server.The available terminal device 101,102,103 of back-end server is corresponding
The voice data for the keyword that user concentrates for predetermined keyword, and according to voice data, determine information to be pushed.Later,
Information to be pushed can be pushed to terminal device 101,102,103.
It should be noted that the method provided by embodiment of the disclosure for pushed information is generally by server 105
It executes, correspondingly, the device for pushed information is generally positioned in server 105.
It should be noted that server 105 can be hardware, it is also possible to software.When server is hardware, Ke Yishi
The distributed server cluster of ready-made multiple server compositions, also may be implemented into individual server.When server is software,
Multiple softwares or software module (such as providing multiple softwares of Distributed Services or software module) may be implemented into, it can also
To be implemented as single software or software module.It is not specifically limited herein.
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 according to one embodiment of the method for pushed information of the disclosure
200.This for pushed information method the following steps are included:
Step 201, the voice data of keyword obtaining first object user, concentrating corresponding to predetermined keyword, obtains
To voice data collection.
It in the present embodiment, can be from for the executing subject of the method for pushed information (server 105 as shown in Figure 1)
The corresponding terminal device of first object user (terminal device 101,102,103 as shown in Figure 1) obtains above-mentioned voice data collection.
Wherein, first object user can be corresponding to the communication connection of above-mentioned executing subject, arbitrary terminal device
User.Above-mentioned executing subject can push predetermined keyword collection to the corresponding terminal device of first object user in advance, by the
The keyword that the corresponding terminal device of one target user concentrates the predetermined keyword received is shown.Later, the first mesh
Mark the voice data for each keyword that user can concentrate by terminal device typing predetermined keyword used in it.
Wherein, predetermined keyword collection can be the keyword being made of several preassigned keywords of technical staff
Collection.The selection of keyword can be determined according to actual application demand.
Step 202, the voice data concentrated for voice data, obtains at least the one of the corresponding keyword of the voice data
A matching voice data；Determine that the voice data matches the similarity of voice data at least one.
In the present embodiment, for any keyword, the corresponding matching voice data of the keyword can refer to the keyword
, the voice data for meeting preset condition.Preset condition can be arranged according to actual application demand.Matching voice data can
Directly to be specified in advance by technical staff.
As an example, some voices of the pronunciation standard and smoothness to the keyword can be chosen for any keyword
Matching voice data of the data as the keyword.Since it is considered that if user, which compares the relevant information of the keyword, feels emerging
Interest, then user naturally can pronunciation to the keyword it is familiar, can generally read the keyword more glibly.
On the contrary, if user is less interested in the relevant information of the keyword, then user may be to the keyword
It is not familiar with, can be more not familiar to the pronunciation of the keyword, or even can wrong pronunciation.
Moreover, according to different application demands, it may be considered that different features analyze voice data.For example, one
In a little situations, the user of different regions may have different accents.Therefore, voice data can also reflect corresponding user's
Location information.
Based on this, by comparing first object user to the voice data of a keyword and the matching voice number of the keyword
According to similarity, can a degree of reflection first object user to the familiarity etc. of the keyword, so as into one
It walks to whether the relevant information of the keyword is that the possible interested content of first object user is estimated.
Optionally, for any keyword, at least one corresponding voice data of the keyword can be first obtained, is somebody's turn to do
The corresponding voice data collection of keyword.The voice data conduct for meeting preset condition is chosen it is then possible to concentrate from voice data
Voice data is matched, it can also be by some voice data in technical staff's specified speech data set as matching voice data.
Wherein, at least one corresponding voice data of the keyword can be obtained from some data platforms, also can use
Some audio Software for producing generate.
Optionally, for any keyword, at least one corresponding matching voice data of the keyword can be by as follows
Step determines:
Step 1 obtains at least one second target user's typing, at least one corresponding key of matching voice data
The voice data of word obtains candidate speech data set as candidate speech data.Wherein, the corresponding terminal of the second target user is set
It is standby to be pushed target information, wherein target information can be according at least one corresponding keyword institute of matching voice data
Determining.
Wherein, the second target user can be corresponding to the communication connection of above-mentioned executing subject, arbitrary terminal device
User.And second target user be voice number that at least one corresponding keyword of matching voice data is crossed in history once typing
According to user.It can be using the history voice data of at least one corresponding keyword of matching voice data as candidate speech number
According to.
Further, the second target user can also be that receiving above-mentioned executing subject matches voice number according at least one
User is corresponded to according to the terminal device of target information determined by corresponding keyword.
As an example, for keyword " A ", the letter that can will receive above-mentioned executing subject and pushed according to keyword " A "
The voice data for the keyword " A " that the terminal device of breath is transmitted across to above-mentioned executing subject is as candidate speech data.
The corresponding candidate speech data set of each keyword can be stored in advance in above-mentioned executing subject.It later, can basis
Keyword directly searches corresponding candidate speech data set.
It should be noted that different user for ease of description, is respectively designated as the first user and second user.Ability
Field technique personnel should be appreciated that therein first and second do not constitute the particular determination to user.
Step 2 obtains the candidate speech data corresponding for the candidate speech data in candidate speech data set
Two target users are directed to the user behavior data of target information；In response to determining that user behavior data meets preset condition, choose
The candidate speech data are as matching voice data.
In this step, it can store the second target user in the corresponding database of above-mentioned executing subject for target information
User behavior data.Therefore, the second target user can be obtained from the corresponding database of above-mentioned executing subject for target
The user behavior data of information.
Wherein, preset condition can be arranged according to actual application demand.For example, preset condition can be from the second mesh
In the period of preset duration from when the corresponding terminal device of mark user receives target information, the second target user is being shown
Stay time on the page of target information is more than preset threshold.When target information includes at least two pushed informations, item is preset
The number that part can be the pushed information that the second target user clicked is greater than preset threshold.
As an example, continuing with above-mentioned keyword " A " as an example, the candidate speech data of keyword " A " have been determined
Later, it is super to the browsing duration of the information pushed according to keyword " A " that corresponding user can be chosen from candidate speech data
The candidate speech data of preset duration threshold value are crossed as matching voice data.
In other words, according to the corresponding user of history voice data of a keyword to the behavior number of the keyword relational information
According to favorable rating of the estimation user to the relevant information of the keyword.It is then possible to choose to the relevant information of the keyword
The voice data of the higher user of favorable rating helps to be promoted the user after to this as matching voice data
The voice data of keyword and the similarity for matching voice data, user after estimating is to the relevant information of the keyword
The accuracy of favorable rating.
For each keyword that predetermined keyword is concentrated, at least one corresponding matching voice number can be preset
According to.Matching voice data can store in the local of above-mentioned executing subject, or is stored in above-mentioned executing subject and corresponds to
Database in.At this point it is possible to obtain matching voice data from the local of above-mentioned executing subject or its corresponding database.When
So, the corresponding matching voice data of keyword can also be obtained from third party's data platform.
For any voice data, the similarity of at least one corresponding matching voice data of the voice data can be with
Different calculations is chosen according to application scenarios.
It is alternatively possible to first determine that the voice data matches the matching voice data in voice data at least one respectively
Similarity, obtain similarity collection.Then it can be concentrated from obtained similarity and choose maximum value as the voice data and its
The similarity of at least one corresponding matching voice data, the average value for the similarity that the similarity that can also be determined is concentrated
The similarity of at least one the matching voice data corresponding as the voice data.
Optionally, after obtaining similarity collection, each at least one matching voice data can also first be obtained
With the corresponding weighted value of voice data.Then it determines that the weighted average for the similarity that obtained similarity is concentrated is used as to be somebody's turn to do
The similarity of at least one corresponding matching voice data of voice data.Wherein, each matching voice data respectively corresponds
Weighted value can be preassigned by technical staff, can also according to it is each matching voice data objective attribute target attribute (such as environment is made an uproar
Sound) attribute value determine.
Wherein, the similarity of any two voice data can be counted using the voice similarity algorithm of some open sources
It calculates.For example, using the similarity for determining two voice data based on the voice similarity mode algorithm of deep learning.
Step 203, the sequence according to corresponding similarity from big to small is concentrated from voice data and chooses target numbers language
Sound data.
In the present embodiment, target numbers can be preset by technical staff, can also be determined according to preset condition.Example
Such as, preset condition may include 30 percent that target numbers are equal to the total number for the voice data that voice data collection includes
Deng.
Step 204, according to the selected corresponding keyword of voice data, information to be pushed is determined, and to the first mesh
It marks the corresponding terminal device of user and pushes identified information to be pushed.
It in the present embodiment, can be flexibly to determine using in a manner of a variety of different wait push away after keyword has been determined
It delivers letters breath.For example, corresponding pushed information can be preset for each keyword.At this point it is possible to which it is corresponding to directly acquire keyword
Pushed information as information to be pushed.
In another example can be retrieved in target database based on keyword, according to actual demand from search result
Middle selection information to be pushed.It for example, can be using access time newest search result as information to be pushed.Wherein, target
Database can be preassigned database, can also refer to the database for meeting certain condition.
With continued reference to the signal that Fig. 3, Fig. 3 are according to the application scenarios of the method for pushed information of the present embodiment
Figure 30 0.In the application scenarios of Fig. 3,301 first login terminal device of terminal device, 301 institute used in it is utilized in user
When one client application of installation, which can show that predetermined keyword is concentrated to user by terminal device 301
Keyword.As shown in the figure, there are three keywords, respectively " Cosplay " (Costume Play, role playing),
" Python " (a kind of computer programming language), " rosy clouds Lip river ".
Later, user can pass through the voice data of 301 three keywords of typing of terminal device.As shown in the figure,
" Cosplay " corresponds to voice data 302, " Python " corresponding voice data 303, " rosy clouds Lip river " corresponding voice data 304.Then,
Voice data 302, voice data 303, voice data 304 can be sent to by the client application installed on terminal device 301
Above-mentioned executing subject.
Then, above-mentioned executing subject can obtain at least one corresponding matching voice number of three voice data respectively
According to, and determine three voice data respectively with it is corresponding at least one matching voice data similarity.
Specifically, with voice data 304 as an example, can first be obtained from the corresponding database 305 of above-mentioned executing subject
304 corresponding two matching voice data 306 of voice data.It is then possible to calculate matched two of voice data 304
Similarity 307 with voice data 306.
Similarly, the similarity 308 of at least one matched matching voice data of voice data 302 is calculated, and
Calculate the similarity 309 of at least one matched matching voice data of voice data 303.
Later, three obtained similarity can be ranked up, selects maximum according to the sequence of similarity from big to small
Value is similarity 308.It is used as it is then possible to choose information relevant to similarity 308 corresponding keyword " Python " wait push away
It delivers letters breath 309, and information to be pushed 309 is pushed into terminal device 301.
In this application scenarios, keyword " Cosplay " is the relevant word of Quadratic Finite Element.Keyword " Python " is to compile
The relevant word of journey.Keyword " rosy clouds Lip river " is the relevant word of e-sports.According to user to the pronunciation of this three keywords
The similarity for matching voice data corresponding with these three keywords, familiar or happiness of the analysis user to these three keywords
Good degree.
Using this application scene as example, user is to the voice data 303 of keyword " Python " and the matching of the keyword
The similarity of voice data is maximum, it is therefore contemplated that user is interested in programming relevant information.Based on this, Ke Yixiang
User, which pushes, programs relevant information.
And user is to the matching corresponding with the two keywords of the voice data of keyword " Cosplay " and " rosy clouds Lip river "
The similarity of voice data is lower, it is believed that user does not know Quadratic Finite Element and the relevant information of e-sports.Based on this,
It can choose a small amount of push or do not push Quadratic Finite Element and the relevant information of e-sports.
The method provided by the above embodiment of the disclosure is by receiving and analyzing voice data and pass of the user to keyword
The similarity of at least one matching voice data corresponding to keyword, to estimate user to the interested of the relevant information of keyword
Degree.Based on this, select the relevant information of the more interested keyword of user as pushed information, so as to avoid to user
Many information that it is lost interest in or will not click are received, in turn result in the server-side of user terminal and pushed information need not
The flow consumption wanted.
With further reference to Fig. 4, it illustrates the processes 400 of another embodiment of the method for pushed information.The use
In the process 400 of the method for pushed information, comprising the following steps:
Step 401, the voice data of keyword obtaining first object user, concentrating corresponding to predetermined keyword, obtains
To voice data collection.
Step 402, the voice data concentrated for voice data, obtains at least the one of the corresponding keyword of the voice data
A matching voice data；Determine that the voice data matches the similarity of voice data at least one.
Step 403, the sequence according to corresponding similarity from big to small is concentrated from voice data and chooses target numbers language
Sound data.
The specific implementation procedure of above-mentioned steps 401,402 and 403 can refer to step 201 in Fig. 2 corresponding embodiment,
202 and 203 related description, details are not described herein.
Step 404, right respectively according at least one matching voice data of the selected corresponding keyword of voice data
History pushed information corresponding to the user answered, determines information to be pushed, and to the corresponding terminal device of first object user
Information to be pushed determined by pushing.
In the present embodiment, after concentrating selection voice data from voice data, above-mentioned executing subject can be from selection
The corresponding user of voice data history pushed information in choose pushed information as information to be pushed.For example, can choose
The higher some pushed informations of clicking rate are as information to be pushed.It is of course also possible to search related to above-mentioned history pushed information
Information as information to be pushed.
In other words, based on analyze active user may keyword to the voice data of selection it is interested after, can
To choose these users from the history pushed information of the interested other users of the keyword equally to the voice data of selection
Interested pushed information is pushed to active user.
It is alternatively possible to be determined according to above-mentioned history pushed information wait push using existing various collaborative filterings
Information is pushed to the corresponding terminal device of first object user.
Figure 4, it is seen that the method for pushed information compared with the corresponding embodiment of Fig. 2, in the present embodiment
Process 400 select it is corresponding matching voice data and target user the biggish keyword of voice data similarity after,
It can determine that information to be pushed pushes to mesh further according to the history pushed information of the corresponding user of these matching voice data
Mark the corresponding terminal device of user.As a result, further such that the information to be pushed determined meets the hobby of target user as far as possible,
Increase the information of push and the matching degree of user preference.And in the relevant information of keyword selected to user's push
On the basis of, increase the coverage for the information that can be pushed.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, present disclose provides for pushed information
One embodiment of device, the Installation practice is corresponding with embodiment of the method shown in Fig. 2, which specifically can be applied to
In various electronic equipments.
As shown in figure 5, the device 500 provided in this embodiment for pushed information includes acquiring unit 501, determination unit
502, selection unit 503 and push unit 504.Wherein, acquiring unit 501 is configured to obtain first object user, corresponding
In the voice data for the keyword that predetermined keyword is concentrated, voice data collection is obtained；Determination unit 502 is configured to for voice
Voice data in data set obtains at least one matching voice data of the corresponding keyword of the voice data；Determine the language
Sound data match the similarity of voice data at least one；Selection unit 503 is configured to according to corresponding similarity from big
To small sequence, is concentrated from voice data and choose target numbers voice data；Push unit 504 is configured to according to selected by
The corresponding keyword of the voice data taken determines information to be pushed, and pushes to the corresponding terminal device of first object user
Identified information to be pushed.
In the present embodiment, in the device of pushed information 500: acquiring unit 501, determination unit 502, selection unit
503 and push unit 504 specific processing and its brought technical effect can be respectively with reference to the step in Fig. 2 corresponding embodiment
201, the related description of step 202, step 203 and step 204, details are not described herein.
In some optional implementations of the present embodiment, above-mentioned determination unit 502 is further configured to: determining should
Voice data matches the similarity of the matching voice data in voice data at least one respectively, obtains similarity collection；According to
Obtained similarity collection determines that the voice data matches the similarity of voice data at least one.
In some optional implementations of the present embodiment, above-mentioned determination unit 502 is further configured to: being obtained extremely
The corresponding weighted value of matching voice data in few matching voice data；It is similar to determine that obtained similarity is concentrated
The weighted average of degree matches the similarity of voice data as the voice data at least one.
In some optional implementations of the present embodiment, at least one matching voice data is true as follows
It is fixed: to obtain at least one second target user's typing, at least one corresponding keyword of matching voice data voice data
As candidate speech data, candidate speech data set is obtained, wherein the corresponding terminal device of the second target user, which is pushed, looks over so as to check
Mark information, wherein target information is according to determined by least one corresponding keyword of matching voice data；For candidate language
Candidate speech data in sound data set obtain the use that corresponding second target user of the candidate speech data is directed to target information
Family behavioral data；In response to determining that user behavior data meets preset condition, the candidate speech data are chosen as matching voice
Data.
In some optional implementations of the present embodiment, above-mentioned push unit 504 is further configured to: according to institute
History corresponding to the corresponding user of at least one matching voice data of the corresponding keyword of the voice data of selection pushes away
It delivers letters breath, determines information to be pushed.
The device provided by the above embodiment of the disclosure, by acquiring unit obtain first object user, correspond to it is pre-
If the voice data of the keyword in keyword set obtains voice data collection；The voice that determination unit concentrates voice data
Data obtain at least one matching voice data of the corresponding keyword of the voice data；Determine the voice data and at least one
The similarity of a matching voice data；Sequence of the selection unit according to corresponding similarity from big to small is concentrated from voice data
Choose target numbers voice data；Push unit determines letter to be pushed according to the selected corresponding keyword of voice data
Breath, and identified information to be pushed is pushed to the corresponding terminal device of first object user, to realize according to user couple
The voice data of keyword with corresponding to keyword at least one match the similarity of voice data and analyze the preference of user,
And then it can avoid based on the analysis results to user's pushed information and push many its to user and lose interest in or will not click
Information in turn results in the unnecessary flow consumption of the server-side of user terminal and pushed information.
Below with reference to Fig. 6, it illustrates the electronic equipment that is suitable for being used to realize embodiment of the disclosure, (example is as shown in figure 1
Server) 600 structural schematic diagram.Server shown in Fig. 6 is only an example, should not be to the function of embodiment of the disclosure
Any restrictions can be brought with use scope.
As shown in fig. 6, electronic equipment 600 may include processing unit (such as central processing unit, graphics processor etc.)
601, random access can be loaded into according to the program being stored in read-only memory (ROM) 602 or from storage device 608
Program in memory (RAM) 603 and execute various movements appropriate and processing.In RAM 603, it is also stored with electronic equipment
Various programs and data needed for 600 operations.Processing unit 601, ROM 602 and RAM603 are connected with each other by bus 604.
Input/output (I/O) interface 605 is also connected to bus 604.
In general, following device can connect to I/O interface 605: including such as touch screen, touch tablet, keyboard, mouse, taking the photograph
As the input unit 606 of head, microphone, accelerometer, gyroscope etc.；Including such as liquid crystal display (LCD), loudspeaker, vibration
The output device 607 of dynamic device etc.；Storage device 608 including such as tape, hard disk etc.；And communication device 609.Communication device
609, which can permit electronic equipment 600, is wirelessly or non-wirelessly communicated with other equipment to exchange data.Although Fig. 6 shows tool
There is the electronic equipment 600 of various devices, it should be understood that being not required for implementing or having all devices shown.It can be with
Alternatively implement or have more or fewer devices.Each box shown in Fig. 6 can represent a device, can also root
According to needing to represent multiple devices.
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 communication device 609, or from storage device 608
It is mounted, or is mounted from ROM 602.When the computer program is executed by processing unit 601, the implementation of the disclosure is executed
The above-mentioned function of being limited in the method for example.
It should be noted that computer-readable medium described in embodiment of the disclosure can be computer-readable signal
Medium or computer readable storage medium either the two any combination.Computer readable storage medium for example can be with
System, device or the device of --- but being not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or it is any more than
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 are programmable
Read-only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic are deposited
Memory device or above-mentioned any appropriate combination.In embodiment of the disclosure, computer readable storage medium, which can be, appoints
What include or the tangible medium of storage program that the program can be commanded execution system, device or device use or and its
It is used in combination.And in embodiment of the disclosure, computer-readable signal media may include in a base band or as carrier wave
The data-signal that a part is propagated, wherein carrying computer-readable program code.The data-signal of this propagation can be adopted
With diversified forms, including but not limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal is situated between
Matter can also be any computer-readable medium other than computer readable storage medium, which can be with
It sends, propagate or transmits for by the use of instruction execution system, device or device or program in connection.Meter
The program code for including on calculation machine readable medium can transmit with any suitable medium, including but not limited to: electric wire, optical cable,
RF (radio frequency) etc. or above-mentioned any appropriate combination.
Above-mentioned computer-readable medium can be included in above-mentioned electronic equipment；It is also possible to individualism, and not
It is fitted into the electronic equipment.Above-mentioned computer-readable medium carries one or more program, when said one or more
When a program is by the execution, so that the electronic equipment: reception first object user typing, corresponding to predetermined keyword concentration
The voice data of keyword obtains voice data collection；For the voice data that voice data is concentrated, it is corresponding to obtain the voice data
Keyword at least one matching voice data；Determine that the voice data matches the similarity of voice data at least one；
According to the sequence of corresponding similarity from big to small, is concentrated from voice data and choose target numbers voice data；According to selected
The corresponding keyword of the voice data taken determines information to be pushed, and pushes to the corresponding terminal device of first object user
Identified information to be pushed.
The behaviour for executing embodiment of the disclosure can be write with one or more programming languages or combinations thereof
The computer program code of work, above procedure design language include object oriented program language-such as Java,
Smalltalk, C++ further include conventional procedural programming language-such as " C " language or similar program design language
Speech.Program code can be executed fully on the user computer, partly be executed on the user computer, as an independence
Software package execute, part on the user computer part execute on the remote computer or completely in remote computer or
It is executed on server.In situations involving remote computers, remote computer can pass through the network of any kind --- packet
Include local area network (LAN) or wide area network (WAN) --- it is connected to subscriber computer, or, it may be connected to outer computer (such as
It is connected using ISP by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the disclosure, 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 embodiment of the disclosure can be realized by way of software, can also be passed through
The mode of hardware is realized.Described unit also can be set in the processor, for example, can be described as: a kind of processor,
Including receiving unit, determination unit, selection unit and push unit.Wherein, the title of these units is not under certain conditions
Constitute restriction to the unit itself, for example, receiving unit be also described as " receive first object user typing, it is right
The voice data for the keyword that should be concentrated in predetermined keyword, obtains the unit of voice data collection ".
Above description is only the preferred embodiment of the disclosure and the explanation to institute's application technology principle.Those skilled in the art
Member it should be appreciated that embodiment of the disclosure involved in invention scope, however it is not limited to the specific combination of above-mentioned technical characteristic and
At technical solution, while should also cover do not depart from foregoing invention design in the case where, by above-mentioned technical characteristic or its be equal
Feature carries out any combination and other technical solutions for being formed.Such as disclosed in features described above and embodiment of the disclosure (but
It is not limited to) technical characteristic with similar functions is replaced mutually and the technical solution that is formed.
Claims (12)
1. a kind of method for pushed information, comprising:
The voice data of keyword obtaining first object user, concentrating corresponding to predetermined keyword, obtains voice data collection；
For the voice data that the voice data is concentrated, at least one matching language of the corresponding keyword of the voice data is obtained
Sound data；Determine the voice data with it is described at least one match the similarity of voice data；
According to the sequence of corresponding similarity from big to small, is concentrated from the voice data and choose target numbers voice data；
According to the selected corresponding keyword of voice data, information to be pushed is determined, and to the first object user couple
The terminal device answered pushes identified information to be pushed.
2. according to the method described in claim 1, wherein, the determination voice data with it is described at least one match voice number
According to similarity, comprising:
Determine the voice data respectively with it is described at least one match in voice data matching voice data similarity, obtain
Similarity collection；
According to obtained similarity collection, determine the voice data with it is described at least one match the similarity of voice data.
3. according to the method described in claim 2, wherein, the similarity collection that the basis obtains determines the voice data and institute
State the similarity of at least one matching voice data, comprising:
Obtain the corresponding weighted value of matching voice data at least one described matching voice data；
Determine the weighted average of the similarity that obtained similarity is concentrated as the voice data with it is described at least one match
The similarity of voice data.
4. according to the method described in claim 1, wherein, at least one described matching voice data determines as follows:
Obtain at least one second target user's typing, at least one corresponding keyword of matching voice data voice
Data obtain candidate speech data set as candidate speech data, wherein the corresponding terminal device of the second target user is pushed
Cross target information, wherein the target information is determined according at least one described corresponding keyword of matching voice data
's；
For the candidate speech data in the candidate speech data set, obtains corresponding second target of the candidate speech data and use
Family is directed to the user behavior data of the target information；Meet preset condition in response to the determination user behavior data, chooses
The candidate speech data are as matching voice data.
5. method described in one of -4 according to claim 1, wherein the corresponding key of the voice data according to selected by
Word determines information to be pushed, comprising:
According at least one matching voice data of the selected corresponding keyword of voice data, corresponding user institute is right
The history pushed information answered, determines the information to be pushed.
6. a kind of device for pushed information, comprising:
Acquiring unit, the voice number of keyword being configured to obtain first object user, being concentrated corresponding to predetermined keyword
According to obtaining voice data collection；
Determination unit is configured to the voice data concentrated for the voice data, obtains the corresponding key of the voice data
At least one matching voice data of word；Determine the voice data with it is described at least one match the similarity of voice data；
Selection unit is configured to the sequence from big to small according to corresponding similarity, concentrates from the voice data and chooses mesh
Mark number voice data；
Push unit is configured to determine information to be pushed, Yi Jixiang according to the selected corresponding keyword of voice data
The corresponding terminal device of the first object user push determined by information to be pushed.
7. device according to claim 6, wherein the determination unit is further configured to:
Determine the voice data respectively with it is described at least one match in voice data matching voice data similarity, obtain
Similarity collection；
According to obtained similarity collection, determine the voice data with it is described at least one match the similarity of voice data.
8. device according to claim 7, wherein the determination unit is further configured to:
Obtain the corresponding weighted value of matching voice data at least one described matching voice data；
Determine the weighted average of the similarity that obtained similarity is concentrated as the voice data with it is described at least one match
The similarity of voice data.
9. device according to claim 6, wherein at least one described matching voice data determines as follows:
Obtain at least one second target user's typing, at least one corresponding keyword of matching voice data voice
Data obtain candidate speech data set as candidate speech data, wherein the corresponding terminal device of the second target user is pushed
Cross target information, wherein the target information is determined according at least one described corresponding keyword of matching voice data
's；
For the candidate speech data in the candidate speech data set, obtains corresponding second target of the candidate speech data and use
Family is directed to the user behavior data of the target information；Meet preset condition in response to the determination user behavior data, chooses
The candidate speech data are as matching voice data.
10. the device according to one of claim 6-9, wherein the push unit is further configured to:
According at least one matching voice data of the selected corresponding keyword of voice data, corresponding user institute is right
The history pushed information answered, determines the information to be pushed.
11. a kind of server, comprising:
One or more processors；
Storage device is stored thereon with 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 5.
12. a kind of computer-readable medium, is stored thereon with computer program, wherein the realization when program is executed by processor
Such as method as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910155198.3A CN109829117B (en) | 2019-02-27 | 2019-02-27 | Method and device for pushing information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910155198.3A CN109829117B (en) | 2019-02-27 | 2019-02-27 | Method and device for pushing information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109829117A true CN109829117A (en) | 2019-05-31 |
| CN109829117B CN109829117B (en) | 2021-04-27 |
Family
ID=66865071
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910155198.3A Active CN109829117B (en) | 2019-02-27 | 2019-02-27 | Method and device for pushing information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109829117B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111883131A (en) * | 2020-08-20 | 2020-11-03 | 腾讯科技（深圳）有限公司 | Voice data processing method and device |
| CN112347310A (en) * | 2020-11-05 | 2021-02-09 | 中国平安人寿保险股份有限公司 | Event processing information query method and device, computer equipment and storage medium |
| CN116932919A (en) * | 2023-09-15 | 2023-10-24 | 中关村科学城城市大脑股份有限公司 | Information pushing method, device, electronic equipment and computer readable medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104717519A (en) * | 2015-04-02 | 2015-06-17 | 兴天通讯技术（天津）有限公司 | Intelligent-television-based interactive advertisement recommending method and system |
| CN105243143A (en) * | 2015-10-14 | 2016-01-13 | 湖南大学 | Recommendation method and system based on instant voice content detection |
| US20160240196A1 (en) * | 2015-02-16 | 2016-08-18 | Alpine Electronics, Inc. | Electronic Device, Information Terminal System, and Method of Starting Sound Recognition Function |
| CN106850539A (en) * | 2016-12-07 | 2017-06-13 | 广东小天才科技有限公司 | Verification information acquisition method and device |
| US20170215011A1 (en) * | 2016-01-22 | 2017-07-27 | Personics Holdings, LLC. | System and method for efficiency among devices |
| CN107451131A (en) * | 2016-05-30 | 2017-12-08 | 贵阳朗玛信息技术股份有限公司 | A kind of audio recognition method and device |
| CN109033162A (en) * | 2018-06-19 | 2018-12-18 | 深圳市元征科技股份有限公司 | A kind of data processing method, server and computer-readable medium |
-
2019
- 2019-02-27 CN CN201910155198.3A patent/CN109829117B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160240196A1 (en) * | 2015-02-16 | 2016-08-18 | Alpine Electronics, Inc. | Electronic Device, Information Terminal System, and Method of Starting Sound Recognition Function |
| CN104717519A (en) * | 2015-04-02 | 2015-06-17 | 兴天通讯技术（天津）有限公司 | Intelligent-television-based interactive advertisement recommending method and system |
| CN105243143A (en) * | 2015-10-14 | 2016-01-13 | 湖南大学 | Recommendation method and system based on instant voice content detection |
| US20170215011A1 (en) * | 2016-01-22 | 2017-07-27 | Personics Holdings, LLC. | System and method for efficiency among devices |
| CN107451131A (en) * | 2016-05-30 | 2017-12-08 | 贵阳朗玛信息技术股份有限公司 | A kind of audio recognition method and device |
| CN106850539A (en) * | 2016-12-07 | 2017-06-13 | 广东小天才科技有限公司 | Verification information acquisition method and device |
| CN109033162A (en) * | 2018-06-19 | 2018-12-18 | 深圳市元征科技股份有限公司 | A kind of data processing method, server and computer-readable medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111883131A (en) * | 2020-08-20 | 2020-11-03 | 腾讯科技（深圳）有限公司 | Voice data processing method and device |
| CN111883131B (en) * | 2020-08-20 | 2023-10-27 | 腾讯科技（深圳）有限公司 | Voice data processing method and device |
| CN112347310A (en) * | 2020-11-05 | 2021-02-09 | 中国平安人寿保险股份有限公司 | Event processing information query method and device, computer equipment and storage medium |
| CN112347310B (en) * | 2020-11-05 | 2023-08-15 | 中国平安人寿保险股份有限公司 | Query method, device, computer equipment and storage medium of event processing information |
| CN116932919A (en) * | 2023-09-15 | 2023-10-24 | 中关村科学城城市大脑股份有限公司 | Information pushing method, device, electronic equipment and computer readable medium |
| CN116932919B (en) * | 2023-09-15 | 2023-11-24 | 中关村科学城城市大脑股份有限公司 | Information pushing method, device, electronic equipment and computer readable medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109829117B (en) | 2021-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109460514B (en) | Method and device for pushing information | |
| CN109460513B (en) | Method and apparatus for generating click rate prediction model | |
| JP6882463B2 (en) | Computer-based selection of synthetic speech for agents | |
| EP2612261B1 (en) | Internet search related methods and apparatus | |
| US20180082184A1 (en) | Context-aware chatbot system and method | |
| CN110555714A (en) | method and apparatus for outputting information | |
| CN109947919A (en) | Method and apparatus for generating text matches model | |
| CN108121800A (en) | Information generating method and device based on artificial intelligence | |
| CN110909145B (en) | Training method and device for multi-task model | |
| CN111738010B (en) | Method and device for generating semantic matching model | |
| CN106354856B (en) | Artificial intelligence-based deep neural network enhanced search method and device | |
| CN110059172B (en) | Method and device for recommending answers based on natural language understanding | |
| CN106407381B (en) | A kind of method and apparatus of the pushed information based on artificial intelligence | |
| CN109829117A (en) | Method and apparatus for pushed information | |
| CN109858045A (en) | Machine translation method and device | |
| CN109829164A (en) | Method and apparatus for generating text | |
| CN114841142A (en) | Text generation method and device, electronic equipment and storage medium | |
| CN112182255A (en) | Method and apparatus for storing media files and for retrieving media files | |
| CN109190123A (en) | Method and apparatus for output information | |
| CN114625923A (en) | Training method of video retrieval model, video retrieval method, device and equipment | |
| CN115841366A (en) | Article recommendation model training method and device, electronic equipment and storage medium | |
| US9984160B2 (en) | Determining a query answer selection | |
| CN110083677A (en) | Searching method, device, equipment and the storage medium of contact person | |
| CN110245357A (en) | Principal recognition methods and device | |
| CN110245334A (en) | Method and apparatus for output information |
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 | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing. Patentee after: Tiktok vision (Beijing) Co.,Ltd. Address before: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing. Patentee before: BEIJING BYTEDANCE NETWORK TECHNOLOGY Co.,Ltd. Address after: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing. Patentee after: Douyin Vision Co.,Ltd. Address before: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing. Patentee before: Tiktok vision (Beijing) Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |