CN109409949A - Determination method, apparatus, electronic equipment and the storage medium of user group's classification - Google Patents
Determination method, apparatus, electronic equipment and the storage medium of user group's classification Download PDFInfo
- Publication number
- CN109409949A CN109409949A CN201811208940.4A CN201811208940A CN109409949A CN 109409949 A CN109409949 A CN 109409949A CN 201811208940 A CN201811208940 A CN 201811208940A CN 109409949 A CN109409949 A CN 109409949A
- Authority
- CN
- China
- Prior art keywords
- user
- operation information
- classification
- target user
- group
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention is that embodiment provides determination method, apparatus, electronic equipment and the storage medium of a kind of user group's classification, this method comprises: obtaining the operation information of target user within a preset time;According to operation information acquisition characteristic sequence corresponding with operation information;Characteristic sequence is separately input at least one machine sort model corresponding with each user group classification, the group classification of target user is determined according to the output result of machine sort model.The technical solution of the embodiment of the present invention, which solves, determines that user belongs to the lower technical problem of which user group's accuracy according to the data that user fills in the prior art, realizing can accurately and rapidly judge which group classification user belongs to according to user's operation information, improve the technical effect of the efficiency and accuracy that judge user group's classification.
Description
Technical field
The present embodiments relate to field of computer technology more particularly to a kind of determination methods of user group classification, dress
It sets, electronic equipment and storage medium.
Background technique
With the development of science and technology, the necessity that mobile terminal has become for people's life, user can be mobile whole
See TV, browsing webpage on end, play games, see news etc., in order to meet the needs of most of user, program research staff is also opened
Begin to research and develop various application programs to meet the needs of different user.
Currently, various application programs are owned by a large amount of user, in order to better meet the demand of user, now
Most application program can actively provide a user a series of information.However, being provided a user in application program a series of
Before information, user is needed to improve data online, optionally, improved about data such as user's gender, age, hobbies, from
And the data that the program in application program is filled according to user, the interested content of user is determined, to recommend information to user.
But during user improves about personal information material, it is understood that there may be user is not very bright
Oneself true interested content, or can not think that interested content causes information solicitation inaccurate for the moment, so that passing through
The content that application program is pushed to user cannot be met the needs of users, so as to cause the technical problem that user experience is poor.
Summary of the invention
The present invention provides determination method, apparatus, electronic equipment and the storage medium of a kind of user group's classification, fast to realize
Speed, the technical effect of accurate judgement targeted user population classification.
In a first aspect, the embodiment of the invention provides a kind of determination methods of user group classification, this method comprises:
Obtain the operation information of target user within a preset time;
According to operation information acquisition characteristic sequence corresponding with the operation information;
The characteristic sequence is separately input at least one machine sort model corresponding with each user group classification
In, the group classification of the target user is determined according to the output result of the machine sort model.
Second aspect, the embodiment of the invention also provides a kind of determining device of user group classification, which includes:
Operation information module is obtained, for obtaining the operation information of target user within a preset time;
Characteristic sequence module is determined, for according to operation information acquisition feature sequence corresponding with the operation information
Column;
It determining user group's categorization module, classifying relatively for being separately input into the characteristic sequence with each user group
In at least one the machine sort model answered, the group of the target user is determined according to the output result of the machine sort model
Body classification.
The third aspect, the embodiment of the invention also provides a kind of electronic equipment, 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 processing
Device realizes the determination method of user group's classification as described in the embodiment of the present invention is any.
Fourth aspect, it is described the embodiment of the invention also provides a kind of storage medium comprising computer executable instructions
Computer executable instructions by computer processor when being executed for executing the user as described in any in the embodiment of the present invention
The determination method of group classification.
The technical solution of the embodiment of the present invention, by obtaining the operation information of target user within a preset time;According to behaviour
Make acquisition of information characteristic sequence corresponding with operation information;Characteristic sequence is separately input into opposite with each user group classification
In at least one the machine sort model answered, the group classification of target user is determined according to the output result of machine sort model,
It solves and needs user to improve personal information online in the prior art, determine that target user belongs to according to the perfect personal information of user
In which group classification, and then content is pushed to it and does not know whether oneself feels since user is during fill data
It the technical issues of interest causes user group's classifying and dividing inaccurate, and the content pushed is unsatisfactory for user demand, realizes
According to the usual operation information of target user and it is handled, that is, is remembered according to the browsing of user, click, purchase etc.
Record, determines the group classification of target user, improves the accuracy of determining targeted user population classification, and pushes away to target user
Send the technical effect of content accuracy.
Detailed description of the invention
In order to more clearly illustrate the technical scheme of the exemplary embodiment of the present invention, below to required in description embodiment
The attached drawing to be used does a simple introduction.Obviously, the attached drawing introduced is present invention a part of the embodiment to be described
Attached drawing, rather than whole attached drawings without creative efforts, may be used also for those of ordinary skill in the art
To obtain other attached drawings according to these attached drawings.
Fig. 1 is a kind of determination method flow schematic diagram of user group's classification provided by the embodiment of the present invention;
Fig. 2 is a kind of another flow diagram of determination method of user group's classification provided by the embodiment of the present invention;
Fig. 3 is a kind of determination apparatus structure schematic diagram of user group's classification provided by the embodiment of the present invention;
A kind of electronic equipment structural schematic diagram provided by the embodiment of the present invention of the position Fig. 4.
Specific embodiment
The present invention 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 the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Fig. 1 is a kind of determination method flow schematic diagram of user group's classification, the present invention provided by the embodiment of the present invention
Embodiment is applicable to determine that the group classification situation of target user, this method can be by the user groups that are configured in server
Classification determining device executes, which can be realized by way of software and/or hardware.
As described in Figure 1, the method for the present embodiment includes:
S110, the operation information of target user within a preset time is obtained.
Wherein, target user can be the user of current operation mobile terminal, or operation mobile terminal time longest
User.When target user triggers application program, or opens client, optionally, the application journey on mobile terminal is clicked
When sequence, it is built in user group in server and classifies determining device, so that it may record user's operation information, that is, user exists
Which at time point, any content is clicked, has seen the information such as the duration of what information and browsing, target user can be existed
In client browsing record, purchaser record and thumb up record etc., that is, user triggered on the client it is any
Operation behavior stores the operation information of user into database, as operation information so as to the behaviour of quick calling target user
Make information.
It should be noted that the hobby of each user or reading habit etc., do not change usually for a long time
, but some behavioural habits, it can be can change in the short time, therefore how long the operation in is believed to target user
Breath is handled, and can be configured according to actual needs.That is, the length of preset time can be system according to business
Actual demand be configured, can also be arranged according to the investigation result of staff, be also possible at user's setting
Reason how long Nei operation information.Illustratively, if how long being carried out to its operation information by user's setting
Reason can be, trigger client on setting icon, in setting selection setting preset time, optionally, setting it is default when
Between be three months, that is to say, that the operation information in available target user three months.
Obtaining the operation information of target user within a preset time may exist at least two trigger conditions.Optionally, if
When reaching first time threshold, then the operation information of target user within a preset time is obtained;And/or it is grasped when receiving triggering
When making, then the operation information of target user within a preset time is obtained.
The first trigger condition is it is to be understood that time detection device, or record time can be set in server internal
Device or program, for recording current time, and can calculate and exist with preceding primary acquisition target user according to current time
The time difference between operating time in preset time.If time difference has reached first time threshold, server can
To obtain the operation information of target user within a preset time;It, can be with if the not up to default first time threshold of time difference
Any operation is not executed.Wherein, the preceding primary operation information of target user within a preset time that obtains is it is to be understood that obtaining
Take target user within a preset time in the historical juncture of operation information, with the current time difference the smallest moment.That is,
No matter whether user opens the application program of mobile terminal, or whether executes any operation on Application Program Interface, as long as
Time difference has reached first time threshold, then the user group's classification determining device being built in server, so that it may obtain
The operation information of target user within a preset time.Second of trigger condition is it is to be understood that detecting target user's triggering
When the application program, server can obtain the operation information of target user within a preset time from database.Namely
It says, as long as user triggers client, so that it may obtain operation information of the target user in three months.
It is of course also possible to which above two embodiment is combined together, that is to say, that once meet above two triggering
Any one in condition, server can transfer the operation information of target user within a preset time from database.
S120, according to operation information acquisition characteristic sequence corresponding with operation information.
It is to be understood that behavior details corresponding with operation information can be extracted according to the operation information of target user.
Illustratively, it is obtained in target user A tri- months from database, operation information in the application, i.e., browsing is each
The browsing time of a channel either clicks the information such as number of video or webpage in a certain respect.Certainly, user is in preset time
Interior possibility has browsed the information of many channels, can extract user A respectively in the behavior details of different channel, that is, in difference
The characteristic sequence of channel.Illustratively, in the data information of GameChannel in available user A tri- months, accordingly
The feature of proposition can be, click the number of game class article, read the total duration of game class article, game class article thumbs up
The comment number and the hop count of game class article etc. of number, game class article;It can also be with counting user A in novel frequency
The result of the operation information in road, corresponding feature extraction can be, user A novel is added on bookshelf number, read
The quantity of novel, the type for reading novel etc..It should be noted that if user A triggers the application program, the application program
From the background, i.e. server, so that it may record all operationss information of the user A in the application program.It should be noted that can also be with
Corresponding feature is directly extracted from the operation information of target user.
In order to quickly obtain characteristic sequence corresponding with operation information from operation information, it can obtain and operate
Before the corresponding characteristic sequence of information, preparatory training characteristics generate model.Optionally, the operation letter of at least one user is obtained
Breath, and using operation information as first sample data, feature is obtained using the training of deep neural network algorithm and generates model;Its
In, feature generates model and is used to the operation information of target user being converted to characteristic sequence corresponding with operation information.
Wherein, the quantity of at least one user can be one, two or multiple etc..Since the training of model is base
It is completed in big data, i.e., model has versatility, and the sample data generallyd use is multiple, that is, the quantity of user can be with
Be it is multiple, optionally, obtain the operation information of 1000 users, can be using the operation information of 1000 users as first sample
Data.
After obtaining first sample data, place can be trained to first sample data using at least one algorithm
Reason, optionally, is trained first sample data using deep neural network algorithm, is also not limited to depth nerve net certainly
Network algorithm is trained rear available feature to 1000 sample datas and generates model.
If the operation information of target user is input to feature generation model, so that it may obtain corresponding with operation information
Characteristic sequence.
S130, characteristic sequence is separately input at least one machine sort model corresponding with each user group classification
In, the group classification of target user is determined according to the output result of machine sort model.
It based on the above technical solution, can also will be in order to determine which group classification target user belongs to
The corresponding characteristic sequence of target user's operation information is separately input into machine mould corresponding with each user group classification
In.It should be noted that staff can classify obtained characteristic sequence, then it is separately input into and each user group
Body is classified in corresponding machine mould.
It is to be understood that training at least one machine sort model in advance, each machine sort model can be used for sentencing
Whether disconnected user is corresponding with current machine model user group classification, and trained machine sort model quantity can be in advance
It is one, two or multiple etc..Each machine mould can according to the operation information of target user within a preset time come
Judge whether the user is user group's classification corresponding with machine mould title.
Illustratively, there are five the quantity of machine sort model, the model of different user group classification is characterized, can be distinguished
It is the machine mould of novel fan, the machine mould of star fan, the machine mould of game enthusiasts, music class fan
Machine mould and dancing class fan machine mould.Will characteristic sequence corresponding with user's A operation information, respectively it is defeated
Enter into five machine sort models, machine mould can be handled each characteristic sequence, can be sentenced according to the result of output
Determine which kind of user group's classification user A is.
Specifically, will characteristic sequence corresponding with target user's operation information, be separately input into each machine sort mould
In type, can determine whether the group classification of target user is identical as the title of current machine disaggregated model.
Wherein, machine sort model can be two disaggregated models, be also possible to similarity model, but be not limited to above-mentioned
Two kinds of models, as long as can judge the group classification of target user, the specific model embodiment of the present invention is not construed as limiting.
Optionally, when the machine mould used is two disaggregated model, that is to say, that by characteristic sequence be separately input into respectively
User group classifies in corresponding two disaggregated model, if the result of two disaggregated models output is consistent with the first default result,
Then determine that the group classification of target user is identical as the title of the first two disaggregated model is worked as.
It should be noted that two disaggregated models of different names have it is multiple, optionally, music-lover two classification moulds
Type, two disaggregated models of dancing class fan etc. can be with before determining the group classification of target user according to two disaggregated models
Two disaggregated model corresponding with different groups classification is trained in advance.The output result of two disaggregated models can be 1 or -1,
When the result of output is 1, then the group classification of target user is identical as the title of two disaggregated models;If output result be-
1, then it represents that the group classification of target user is different from the title of two disaggregated models.Illustratively, by characteristic sequence, it is input to sound
In two disaggregated models of happy fan, if the output result of two disaggregated models is 1, indicate that the group classification of target user belongs to sound
Happy fan group;If the result of two disaggregated models output is -1, then it represents that target user is unmusical fan group, can be with
It by the characteristic sequence of target user, then is input in two disaggregated models of other group classifications, and then according to two disaggregated models
Output is as a result, determine which user group's classification target user belongs to.
Optionally, machine mould can also be similarity model.When machine mould is similarity model, can be, it will
Characteristic sequence is separately input into similarity model corresponding with each user group classification, if the output result of similarity model exists
Within preset threshold range, it is determined that the group classification of target user and the title of similarity model are identical.
Wherein, similarity model is it is to be understood that judge the phase between the characteristic sequence and the characteristic sequence of storage of input
Like angle value.Therefore, it before the characteristic sequence of target user is input to similarity model, can first store in the group classification
The characteristic sequence of certain customers can be according to defeated when the characteristic sequence of target user to be input in each group classification model
Similarity value between the characteristic sequence of the characteristic sequence and storage that enter determines whether target user is the group classification.If
Similarity value is within preset threshold range, and optionally, preset threshold is more than or equal to 85 percent.That is work as phase
When being more than or equal to 85 percent like angle value, so that it may determine that target user is identical as the title of current similarity model.
Illustratively, will characteristic sequence corresponding with target user's operation information, be input to the similar of music-lover
It spends in model, when the value of similarity model output is more than or equal to 0.85, then can be determined that the group classification of target user is sound
Happy fan determines that target user is not music-lover if the similarity value of output is lower than 0.85, can be by feature sequence
Column are input in other similarity models the group classification for determining target user again.
The technical solution of the embodiment of the present invention, by obtaining the operation information of target user within a preset time;According to behaviour
Make acquisition of information characteristic sequence corresponding with operation information;Characteristic sequence is separately input into opposite with each user group classification
In at least one the machine sort model answered, the group classification of target user is determined according to the output result of machine sort model,
It solves and needs user to improve personal information online in the prior art, determine that target user belongs to according to the perfect personal information of user
In which group classification, and then content is pushed to it and does not know whether oneself feels since user is during fill data
It the technical issues of interest causes user group's classifying and dividing inaccurate, and the content pushed is unsatisfactory for user demand, realizes
According to the usual operation information of target user and it is handled, that is, is remembered according to the browsing of user, click, purchase etc.
Record, determines the group classification of target user, improves the accuracy of determining targeted user population classification, and pushes away to target user
Send the technical effect of content accuracy.
During the operation information to target user is analyzed and processed, the group of target user can be not only determined
Classification, can also determine that target user is interested in a certain partial content in some channel.When target user triggers client
When each channel on end, then channel content can be pushed to target user according to the group classification of target user.Fig. 2 is the present invention
A kind of another flow diagram of determination method of user group's classification provided by embodiment, as described in Figure 2, the embodiment of the present invention
Method include:
S210, the operation information of target user within a preset time is obtained.
Illustratively, when target user triggers the client on mobile terminal, that is to say, that target user opens this
After application program, user group's sorter can record the operation information of target user on the client, optionally,
The operation information of target user is recorded, and by operation information storage into local data base.When to target user's operation information not
When the time of processing reaches first time threshold, optionally, one month, then target use can be transferred from local data base
Operation information in family three months, in the application program.
Wherein, which channel may include: user in the operation information being deployed into clicks in which time, reads
Content in terms of which and the time etc. in one aspect read in content.
S220, according to operation information acquisition characteristic sequence corresponding with operation information.
After obtaining the operation information of target user, server can be screened the operation information of target user.
Wherein, screening, which can be, carries out denoising etc. to the operation information got, certainly, can also not have to sieve operation information
Choosing, staff can be configured according to actual needs, be not limited thereto.
Operation information can be input to preparatory trained spy by characteristic sequence corresponding with operation information in order to obtain
Sign generates in model, obtains characteristic sequence corresponding with operation information.Wherein, characteristic sequence can indicate that target user is seeing
It sees the time of some channel, or to information such as the like times of content in a certain respect.
S230, characteristic sequence is input at least one machine sort model corresponding with each user group classification,
The group classification of target user is determined according to the output result of machine sort model.
It is to be understood that before characteristic sequence is input to machine sort model, in order to ensure determining user group point
The accuracy of class result can first obtain the data operation information of at least 500 users in each group classification, and to 500 use
The data operation information at family is trained, and disaggregated model corresponding with each user group classification is obtained, this is because respectively
A model is all based on what big data training obtained, therefore when sample data is more, mistake of the model that training obtains in application
Result is more accurate in journey.
After obtaining machine sort model, can will characteristic sequence corresponding with target user's operation information, respectively
Be input in each machine mould, can according to output result whether consistent or input results pre- with default result
If determining the group classification of target user within threshold range, specific judgment criteria and mode can be found in embodiment
One.
Optionally, the group classification of target user is determined according to the output result of machine sort model, comprising: determine target
Group classification of the user at least two periods, and group classification type in different time periods is different.
It should be noted that the group classification of user is combined in preset time, all operationss information of user is determined
, indicate that overall user belongs to the group classification.On this basis in order to more be apparent from the demand of user,
The operation information of user can be divided according to the time period, be divided at least one period, and then determine user in difference
The user group of period classifies, and understands user in the interested content of different time sections, thus accurately when different
Between section to user push relevant content.User in different time periods classification at this time, and it is true according to user's all operationss information
Determine user's classification not contradict.
Wherein, user group's classification can be classified by least one sub-group and be constituted.Optionally, user group is classified as small
Say user group, then the classification of corresponding sub-group can be the classification for liking different type novel, optionally, sub-group classification
For fantasy class novel fan, Metropolitan novel fan etc..
During determining targeted user population classification, it is assorted can to determine that target user likes seeing period in which
The content of sample pushes different contents to user, in turn then the period that can trigger different channel according to user is different
It meets the needs of different users.Therefore the operation information of user can be divided according to the time period, obtains at least one time
The operation information of target user in section.The operation information of target user is divided according to the time period to be advantageous in that, using journey
Sequence is generally mounted on mobile terminal, using the possible more than one of the user of mobile terminal, then different user may be liked
Joyous content is not also identical, and the time point of operation is not also identical, and optionally, the content that the elderly and young man like is not quite similar,
In this way according to the operation information at least one period, it will be appreciated which type of content liked in different time sections user,
To targetedly push related content, and then meet the diversified demand of user.
Illustratively, mobile terminal is plate, can be with more than one, Ta Menke using the user of plate in three months
To log in identical account, the operation information got at this time can be the operation information of different user composition, if one of them
User is generally mainly the program of dancing class to 4 points in 8 points to ten two points novels for seeing fantasy class of the morning, two o'clock in afternoon, evening
Another upper main user is using pad, and the content seen also is mainly the novel of fantasy class, is determined according to whole operation informations
User is novel class user group classification.It, can be by user's in order to which the group classification of user in different periods is determined clearly
Operation information is temporally divided into three periods, 8 points to ten three points of the morning, ten three points to ten nine points of afternoon, at ten nine points at night
To 24 points, through processing determine user at eight to ten three points be novel user group classification, ten three points to ten nine points be
Dancing class user group classification, ten nine points to 24 points be novel user group.That is, user can in different time sections
Group classification can be different.
Certainly, after the group classification for determining different time sections user, relevant information can be pushed to user.Example
Property, when user triggers client between 8 points to ten two points of the morning, the information of novel can be pushed to user, if user
Trigger the information of novel, then can information depending on the user's operation, push the interested novel sub-group of user point to user
Class;If user in the afternoon 3 points or so triggering clients when, can be according to user's 3 points or so of historical viewings data in the afternoon
Relevant content is pushed to user.That is, the period that the technical solution of the embodiment of the present invention can be triggered in conjunction with user,
Obtain user during this period of time, about the historical viewings data of this respect, determine the group classification of target user, and according to
The period of each channel pushes relevant content to target user and mentions to meet the needs of users in family triggering application program
The technical effect of high user experience.
S240, when target user trigger client on each channel when, according to the group classification of target user to target use
Family pushes the content of each channel.
Wherein, many channels can also be shown on the main display surface face of client, be corresponding with difference in each channel
The content of aspect.Optionally, each channel includes star's channel, channel of making laughs, music channel, mother and baby's channel, dancing channel, animation
One or more of channel, GameChannel, movie channel, tourism channel, luxury goods channel or novel channel.It needs
Bright, each channel in client can be above-mentioned one or more, be also not limited to certainly above-mentioned cited
Channel.Illustratively, it is corresponding with different types of novel in novel channel, optionally, fantasy class novel, Metropolitan novel, speech
Feelings class novel etc..
When user opens client, if wanting to see the information about in a certain respect, user can click wherein some frequency
The content that can push each channel after opening channel to target user according to the group classification of user is clicked in road at this time.Example
Property, if user wants to see novel, novel channel can be clicked, can show different types of novel after opening.
It should be noted that can also be determined during determining the group classification of target user is novel fan
Target user often browsed the novel of which seed type, the browsing duration of each type novel and in which period
It sees the novel of which type, highest can be set by the priority for browsing the longest novel types of duration, in display interface
In preferentially show.Illustratively, for target user in 3 months, the time of browsing fantasy novel is 70 hours, literatures
30 hours of novel, 20 hours of science fiction class novel etc., then user click novel channel after, can in the display interface to
The novel types that user recommends successively can be fantasy class novel, literature novel, science fiction class novel, and fantasy class novel
It is most to push quantity.
It should be noted that triggering other channels for user, the content and mode pushed on display interface is touched with user
The mode shown when sending out novel channel can be identical with mode, and the particular content only shown is different, and this is no longer going to repeat them.
The technical solution of the embodiment of the present invention, by obtaining the operation information of target user within a preset time;According to behaviour
Make acquisition of information characteristic sequence corresponding with operation information;Characteristic sequence is separately input into opposite with each user group classification
In at least one the machine sort model answered, the group classification of target user is determined according to the output result of machine sort model,
It solves and needs user to improve personal information online in the prior art, determine that target user belongs to according to the perfect personal information of user
In which group classification, and then content is pushed to it and does not know whether oneself feels since user is during fill data
It the technical issues of interest causes user group's classifying and dividing inaccurate, and the content pushed is unsatisfactory for user demand, realizes
According to the usual operation information of target user and it is handled, that is, is remembered according to the browsing of user, click, purchase etc.
Record, determines the group classification of target user, improves the accuracy of determining targeted user population classification, and pushes away to target user
Send the technical effect of content accuracy.
Fig. 3 is a kind of determination apparatus structure schematic diagram of user group's classification provided in an embodiment of the present invention, which can
It is configured in server.Wherein, which includes: to obtain operation information module 310, determine characteristic sequence module 320, determine and use
Family group classification module 330.Wherein, operation information module 310 is obtained, for obtaining the operation of target user within a preset time
Information;Characteristic sequence module 320 is determined, for according to operation information acquisition feature sequence corresponding with the operation information
Column;Determine user group's categorization module 330, it is corresponding with each user group classification for being separately input into the characteristic sequence
At least one machine sort model in, the group of the target user is determined according to the output result of the machine sort model
Classification.
The technical solution of the embodiment of the present invention, by obtaining the operation information of target user within a preset time;According to behaviour
Make acquisition of information characteristic sequence corresponding with operation information;Characteristic sequence is separately input into opposite with each user group classification
In at least one the machine sort model answered, the group classification of target user is determined according to the output result of machine sort model,
It solves and needs user to improve personal information online in the prior art, determine that target user belongs to according to the perfect personal information of user
In which group classification, and then content is pushed to it and does not know whether oneself feels since user is during fill data
It the technical issues of interest causes user group's classifying and dividing inaccurate, and the content pushed is unsatisfactory for user demand, realizes
According to the usual operation information of target user and it is handled, that is, is remembered according to the browsing of user, click, purchase etc.
Record, determines the group classification of target user, improves the accuracy of determining targeted user population classification, and pushes away to target user
Send the technical effect of content accuracy.
Based on the above technical solution, the acquisition operation information module 310, also particularly useful for: if reaching first
When time threshold, then the operation information of target user within a preset time is obtained;And/or
When receiving trigger action, then the operation information of target user within a preset time is obtained.
On the basis of above-mentioned each technical solution, determination user group categorization module 330 in described device is also specific to use
In being separately input into the characteristic sequence in two disaggregated model corresponding with each user group classification, if the two classification mould
The output result of type is consistent with the first default result, it is determined that the group classification of the target user and presently described two classification
The title of model is identical.
On the basis of above-mentioned each technical solution, determination user group categorization module 330 in described device is also specific to use
In being separately input into the characteristic sequence in similarity model corresponding with each user group classification, if the similarity model
Output result within preset threshold range, it is determined that the group classification of the target user and presently described similarity model
Title it is identical.
On the basis of above-mentioned each technical solution, determination characteristic sequence module 320 in described device, also particularly useful for will
The operation information is input to the feature that training generates in advance and generates in model, obtains feature corresponding with the operation information
Sequence.
On the basis of above-mentioned each technical solution, it includes: to obtain at least one that training, which generates the step of feature generates model,
The operation information of user, and using the operation information as first sample data, it is obtained using the training of deep neural network algorithm
Feature generates model;Wherein, the feature generates model for being converted to and the behaviour operation information of the target user
Make the corresponding characteristic sequence of information.
On the basis of above-mentioned each technical solution, determining user group's categorization module also particularly useful for: determine described in
Group classification of the target user at least two periods, and group classification type in different time periods is different.
On the basis of above-mentioned each technical solution, described device further includes pushing module, for touching as the target user
When sending out each channel in client, then the channel is pushed to the target user according to the group classification of the target user
Content.
On the basis of above-mentioned each technical solution, each channel includes star's channel, channel of making laughs, music channel, mother
In baby's channel, dancing channel, animation channel, GameChannel, movie channel, tourism channel, luxury goods channel or novel channel
One or more.
The determining device of the classification of user group provided by the embodiment of the present invention can be performed any embodiment of that present invention and be mentioned
The determination method of user group's classification of confession, has the corresponding functional module of execution method and beneficial effect.
It is worth noting that, each unit included by above-mentioned apparatus and module are only divided according to function logic
, but be not limited to the above division, as long as corresponding functions can be realized;In addition, the specific name of each functional unit
Title is also only for convenience of distinguishing each other, and is not intended to restrict the invention the protection scope of embodiment.
Fig. 4 is the structural schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention.Fig. 4, which is shown, to be suitable for being used to realizing
The block diagram of the example electronic device 400 of embodiment of the embodiment of the present invention.It is real it illustrates being suitable for being used to below with reference to Fig. 4
The structural schematic diagram of the electronic equipment (such as terminal device or server) 400 of the existing embodiment of the present disclosure.In the embodiment of the present disclosure
Terminal device can include but is not limited to such as mobile phone, laptop, digit broadcasting receiver, PDA (individual digital
Assistant), PAD (tablet computer), PMP (portable media player), car-mounted terminal (such as vehicle mounted guidance terminal) etc.
The fixed terminal of mobile terminal and such as number TV, desktop computer etc..Electronic equipment shown in Fig. 4 is only one and shows
Example, should not function to the embodiment of the present disclosure and use scope bring any restrictions.
As shown in figure 4, electronic equipment 400 may include processing unit (such as central processing unit, graphics processor etc.)
401, random access can be loaded into according to the program being stored in read-only memory (ROM) 402 or from storage device 408
Program in memory (RAM) 403 and execute various movements appropriate and processing.In RAM 403, it is also stored with electronic equipment
Various programs and data needed for 400 operations.Processing unit 401, ROM 402 and RAM 403 pass through the phase each other of bus 404
Even.Input/output (I/O) interface 405 is also connected to bus 404.
In general, following device can connect to I/O interface 405: including such as touch screen, touch tablet, keyboard, mouse, taking the photograph
As the input unit 406 of head, microphone, accelerometer, gyroscope etc.;Including such as liquid crystal display (LCD), loudspeaker, vibration
The output device 407 of dynamic device etc.;Storage device 408 including such as tape, hard disk etc.;And communication device 409.Communication device
409, which can permit electronic equipment 400, is wirelessly or non-wirelessly communicated with other equipment to exchange data.Although Fig. 4 shows tool
There is the electronic equipment 400 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.
Particularly, disclosed embodiment, the process described above with reference to flow chart may be implemented as counting according to the present invention
Calculation machine software program.For example, embodiment disclosed by the invention includes a kind of computer program product comprising be carried on computer
Computer program on readable medium, the computer program include the program code for method shown in execution flow chart.?
In such embodiment, which can be downloaded and installed from network by communication device 409, or from storage
Device 408 is mounted, or is mounted from ROM402.When the computer program is executed by processing unit 401, the present invention is executed
The above-mentioned function of being limited in the method for open embodiment.
It should be noted that the present invention disclose above-mentioned computer-readable medium can be computer-readable signal media or
Person's 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 group
It closes.The more specific example of computer readable storage medium can include but is not limited to: have being electrically connected for one or more conducting wires
Connect, portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed it is read-only
Memory (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 the present disclosure, computer readable storage medium can be it is any include or
The tangible medium of program is stored, which can be commanded execution system, device or device use or in connection.
And in the present disclosure, computer-readable signal media may include in a base band or as carrier wave a part propagate number
It is believed that number, wherein carrying computer-readable program code.The data-signal of this propagation can take various forms, including
But it is not limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be calculating
Any computer-readable medium other than machine readable storage medium storing program for executing, which can send, propagate or
Transmission is for by the use of instruction execution system, device or device or program in connection.Computer-readable medium
On include program code 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 multiple programs are by the electricity
When sub- equipment executes, so that the electronic equipment: obtaining the operation information of target user within a preset time;Believed according to the operation
Breath obtains characteristic sequence corresponding with the operation information;The characteristic sequence is separately input into and is classified with each user group
In at least one corresponding machine sort model, the target user is determined according to the output result of the machine sort model
Group classification.
It can be write with one or more programming languages or combinations thereof for executing operation disclosed by the invention
Computer program code, 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
It includes local area network (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as benefit
It is connected with ISP by internet).
Flow chart and block diagram in attached drawing illustrate the system, method and calculating that various embodiments are disclosed according to the present invention
The architecture, function and operation in the cards of machine program product.In this regard, each box in flowchart or block diagram can
To represent a part of a module, program segment or code, a part of the module, program segment or code includes one or more
A executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, in box
The function of being marked can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are real
It can be basically executed in parallel on border, they can also be executed in the opposite order sometimes, and this depends on the function involved.?
It should be noted that the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart, it can be with
It is realized with the dedicated hardware based system for executing defined functions or operations, or specialized hardware and computer can be used
The combination of instruction is realized.
Being described in module involved by of the invention disclose in embodiment can be realized by way of software, can also be led to
The mode of hardware is crossed to realize.Wherein, the title of module does not constitute the restriction to the unit itself, example under certain conditions
Such as, it obtains operation information module and is also described as " obtaining operation information module in preset time ";Determine characteristic sequence mould
Block can also be described as " characteristic sequence acquisition module " etc..
Above description is only preferred embodiment disclosed by the invention and the explanation to institute's application technology principle.This field skill
Art personnel should be appreciated that the present invention disclose involved in the open scope, however it is not limited to the specific combination of above-mentioned technical characteristic and
At technical solution, while should also cover in the case where not departing from design disclosed above, by above-mentioned technical characteristic or its be equal
Feature carries out any combination and other technical solutions for being formed.Such as features described above be disclosed in publication with the present invention it is (but unlimited
In) technical characteristic with similar functions is replaced mutually and the technical solution that is formed.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (12)
1. a kind of determination method of user group's classification characterized by comprising
Obtain the operation information of target user within a preset time;
According to operation information acquisition characteristic sequence corresponding with the operation information;
The characteristic sequence is separately input at least one machine sort model corresponding with each user group classification, root
The group classification of the target user is determined according to the output result of the machine sort model.
2. the method according to claim 1, wherein described obtain the operation letter of target user within a preset time
Breath, comprising:
If reach first time threshold, the operation information of target user within a preset time is obtained;And/or
When receiving trigger action, then the operation information of target user within a preset time is obtained.
3. the method according to claim 1, wherein described be separately input into the characteristic sequence and each user
In at least one corresponding machine sort model of group classification, according to the determination of the output result of the machine sort model
The group classification of target user, comprising:
The characteristic sequence is separately input into two disaggregated model corresponding with each user group classification, if two classification
The output result of model is consistent with the first default result, it is determined that the group classification of the target user and presently described two points
The title of class model is identical.
4. the method according to claim 1, wherein described be separately input into the characteristic sequence and each user
In at least one corresponding machine sort model of group classification, according to the determination of the output result of the machine sort model
The group classification of target user, comprising:
The characteristic sequence is separately input into similarity model corresponding with each user group classification, if the similarity mould
The output result of type is within preset threshold range, it is determined that the group classification of the target user and presently described similarity mould
The title of type is identical.
5. the method according to claim 1, wherein described according to operation information acquisition and the operation information phase
Corresponding characteristic sequence includes:
The operation information is input to the feature that training generates in advance to generate in model, is obtained corresponding with the operation information
Characteristic sequence.
6. according to the method described in claim 5, it is characterized in that, training includes: the step of generating feature generation model
The operation information of at least one user is obtained, and using the operation information as first sample data, using depth nerve
Network algorithm training obtains feature and generates model;
Wherein, it is opposite with the operation information for being converted to the operation information of the target user to generate model for the feature
The characteristic sequence answered.
7. the method according to claim 1, wherein the output result according to the machine sort model is true
The group classification of the fixed target user, comprising:
The target user is determined in the group classification of at least two periods, and group classification type in different time periods is not
Together.
8. the method according to claim 1, wherein further include:
When the target user triggers each channel in client, then according to the group classification of the target user to the mesh
Mark user pushes the content of the channel.
9. according to the method described in claim 8, it is characterized in that, each channel includes star's channel, channel of making laughs, music
Channel, mother and baby's channel, dancing channel, animation channel, GameChannel, movie channel, tourism channel, luxury goods channel or novel
One or more of channel.
10. a kind of determining device of user group's classification characterized by comprising
Operation information module is obtained, for obtaining the operation information of target user within a preset time;
Characteristic sequence module is determined, for according to operation information acquisition characteristic sequence corresponding with the operation information;
Determine user group's categorization module, it is corresponding with each user group classification for being separately input into the characteristic sequence
In at least one machine sort model, the group point of the target user is determined according to the output result of the machine sort model
Class.
11. 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
The now determination method of user group's classification as described in any in claim 1-9.
12. a kind of storage medium comprising computer executable instructions, the computer executable instructions are by computer disposal
For executing the determination method of user group's classification as described in any in claim 1-9 when device executes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811208940.4A CN109409949A (en) | 2018-10-17 | 2018-10-17 | Determination method, apparatus, electronic equipment and the storage medium of user group's classification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811208940.4A CN109409949A (en) | 2018-10-17 | 2018-10-17 | Determination method, apparatus, electronic equipment and the storage medium of user group's classification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109409949A true CN109409949A (en) | 2019-03-01 |
Family
ID=65468309
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811208940.4A Pending CN109409949A (en) | 2018-10-17 | 2018-10-17 | Determination method, apparatus, electronic equipment and the storage medium of user group's classification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109409949A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109902681A (en) * | 2019-03-04 | 2019-06-18 | 苏州达家迎信息技术有限公司 | User group's relationship determines method, apparatus, equipment and storage medium |
CN110390605A (en) * | 2019-07-25 | 2019-10-29 | 新奥(中国)燃气投资有限公司 | A kind of modification scheme method for pushing and device |
CN110598769A (en) * | 2019-08-30 | 2019-12-20 | 京东数字科技控股有限公司 | User group discovery method, device, equipment and computer readable storage medium |
CN111078742A (en) * | 2019-12-09 | 2020-04-28 | 秒针信息技术有限公司 | User classification model training method, user classification method and device |
CN111415191A (en) * | 2020-02-19 | 2020-07-14 | 珠海格力电器股份有限公司 | User classification method and device, electronic equipment and storage medium |
CN112132345A (en) * | 2020-09-23 | 2020-12-25 | 深圳创新奇智科技有限公司 | Method and device for predicting user information of electric power company, electronic equipment and storage medium |
CN112559826A (en) * | 2019-09-25 | 2021-03-26 | 北京国双科技有限公司 | User group dividing method and device, storage medium and electronic equipment |
CN112801685A (en) * | 2020-09-10 | 2021-05-14 | 腾讯科技(深圳)有限公司 | Information pushing method and device, computer equipment and storage medium |
CN113935789A (en) * | 2021-12-20 | 2022-01-14 | 广州半城云信息科技有限公司 | User-defined crowd division method and system |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104598601A (en) * | 2015-01-27 | 2015-05-06 | 北京齐尔布莱特科技有限公司 | Method, device and calculating equipment for classifying users and content |
CN106446078A (en) * | 2016-09-08 | 2017-02-22 | 乐视控股(北京)有限公司 | Information recommendation method and recommendation apparatus |
CN106792210A (en) * | 2016-12-07 | 2017-05-31 | Tcl集团股份有限公司 | The sorting technique and system of a kind of TV user |
CN107357874A (en) * | 2017-07-04 | 2017-11-17 | 北京京东尚科信息技术有限公司 | User classification method and device, electronic equipment, storage medium |
CN107563429A (en) * | 2017-07-27 | 2018-01-09 | 国家计算机网络与信息安全管理中心 | A kind of sorting technique and device of network user colony |
US20180013846A1 (en) * | 2015-09-29 | 2018-01-11 | Tencent Technology (Shenzhen) Company Limited | Event information push method, event information push apparatus, and storage medium |
CN107818344A (en) * | 2017-10-31 | 2018-03-20 | 上海壹账通金融科技有限公司 | The method and system that user behavior is classified and predicted |
CN108268511A (en) * | 2016-12-30 | 2018-07-10 | 上海互联网软件集团有限公司 | Network user classification method based on big data |
CN108399418A (en) * | 2018-01-23 | 2018-08-14 | 北京奇艺世纪科技有限公司 | A kind of user classification method and device |
-
2018
- 2018-10-17 CN CN201811208940.4A patent/CN109409949A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104598601A (en) * | 2015-01-27 | 2015-05-06 | 北京齐尔布莱特科技有限公司 | Method, device and calculating equipment for classifying users and content |
US20180013846A1 (en) * | 2015-09-29 | 2018-01-11 | Tencent Technology (Shenzhen) Company Limited | Event information push method, event information push apparatus, and storage medium |
CN106446078A (en) * | 2016-09-08 | 2017-02-22 | 乐视控股(北京)有限公司 | Information recommendation method and recommendation apparatus |
CN106792210A (en) * | 2016-12-07 | 2017-05-31 | Tcl集团股份有限公司 | The sorting technique and system of a kind of TV user |
CN108268511A (en) * | 2016-12-30 | 2018-07-10 | 上海互联网软件集团有限公司 | Network user classification method based on big data |
CN107357874A (en) * | 2017-07-04 | 2017-11-17 | 北京京东尚科信息技术有限公司 | User classification method and device, electronic equipment, storage medium |
CN107563429A (en) * | 2017-07-27 | 2018-01-09 | 国家计算机网络与信息安全管理中心 | A kind of sorting technique and device of network user colony |
CN107818344A (en) * | 2017-10-31 | 2018-03-20 | 上海壹账通金融科技有限公司 | The method and system that user behavior is classified and predicted |
CN108399418A (en) * | 2018-01-23 | 2018-08-14 | 北京奇艺世纪科技有限公司 | A kind of user classification method and device |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109902681A (en) * | 2019-03-04 | 2019-06-18 | 苏州达家迎信息技术有限公司 | User group's relationship determines method, apparatus, equipment and storage medium |
CN110390605A (en) * | 2019-07-25 | 2019-10-29 | 新奥(中国)燃气投资有限公司 | A kind of modification scheme method for pushing and device |
CN110598769A (en) * | 2019-08-30 | 2019-12-20 | 京东数字科技控股有限公司 | User group discovery method, device, equipment and computer readable storage medium |
CN110598769B (en) * | 2019-08-30 | 2022-06-07 | 京东科技控股股份有限公司 | User group discovery method, device, equipment and computer readable storage medium |
CN112559826A (en) * | 2019-09-25 | 2021-03-26 | 北京国双科技有限公司 | User group dividing method and device, storage medium and electronic equipment |
CN111078742A (en) * | 2019-12-09 | 2020-04-28 | 秒针信息技术有限公司 | User classification model training method, user classification method and device |
CN111415191A (en) * | 2020-02-19 | 2020-07-14 | 珠海格力电器股份有限公司 | User classification method and device, electronic equipment and storage medium |
CN111415191B (en) * | 2020-02-19 | 2024-02-13 | 珠海格力电器股份有限公司 | User classification method, device, electronic equipment and storage medium |
CN112801685A (en) * | 2020-09-10 | 2021-05-14 | 腾讯科技(深圳)有限公司 | Information pushing method and device, computer equipment and storage medium |
CN112801685B (en) * | 2020-09-10 | 2024-06-18 | 腾讯科技(深圳)有限公司 | Information pushing method, device, computer equipment and storage medium |
CN112132345A (en) * | 2020-09-23 | 2020-12-25 | 深圳创新奇智科技有限公司 | Method and device for predicting user information of electric power company, electronic equipment and storage medium |
CN113935789A (en) * | 2021-12-20 | 2022-01-14 | 广州半城云信息科技有限公司 | User-defined crowd division method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109409949A (en) | Determination method, apparatus, electronic equipment and the storage medium of user group's classification | |
CN106464758B (en) | It initiates to communicate using subscriber signal | |
CN106462623B (en) | The song recommendations used based on content item | |
US20160063874A1 (en) | Emotionally intelligent systems | |
CN106030569A (en) | Techniques for reformulating search queries | |
CN107209905A (en) | Corresponding de-themed categorization for personalization and task completion services | |
CN110475155A (en) | Live video temperature state identification method, device, equipment and readable medium | |
CA2950421A1 (en) | Systems, methods and apparatus for generating music recommendations | |
KR20110066168A (en) | System and method for playlist generation based on similarity data | |
CN103455538B (en) | Information processing unit, information processing method and program | |
US10956470B2 (en) | Facet-based query refinement based on multiple query interpretations | |
US20200160385A1 (en) | Delivering advertisements based on user sentiment and learned behavior | |
CN111259192A (en) | Audio recommendation method and device | |
CN111143697A (en) | Content recommendation method and related device | |
CN103295148A (en) | Digital consumer data model and customer analytic record | |
US20120311140A1 (en) | Method of processing web access information and server implementing same | |
CN107666435A (en) | A kind of method and device for shielding message | |
CN110276006A (en) | Methods of exhibiting, device, electronic equipment and the computer readable storage medium of painted eggshell | |
CN110363604A (en) | Page generation method and device | |
CN114238618A (en) | Information pushing method, electronic equipment and storage medium | |
CN106354867A (en) | Multimedia resource recommendation method and device | |
CN109064283B (en) | Commodity recommendation method and device and computer-readable storage medium | |
CN110674404A (en) | Link information generation method, device, system, storage medium and electronic equipment | |
Yang et al. | Quantitative study of music listening behavior in a smartphone context | |
CN109783740A (en) | Pay close attention to the sort method and device of the page |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190301 |