CN110087104A - Device, method, electronic equipment and the computer readable storage medium of information push - Google Patents
Device, method, electronic equipment and the computer readable storage medium of information push Download PDFInfo
- Publication number
- CN110087104A CN110087104A CN201910353015.9A CN201910353015A CN110087104A CN 110087104 A CN110087104 A CN 110087104A CN 201910353015 A CN201910353015 A CN 201910353015A CN 110087104 A CN110087104 A CN 110087104A
- Authority
- CN
- China
- Prior art keywords
- equipment
- intelligent television
- television equipment
- audient
- crowd
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/252—Processing of multiple end-users' preferences to derive collaborative data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application provides device, method, electronic equipment and the computer readable storage mediums of a kind of push of information, this method comprises: obtaining the device identification of intelligent television equipment to be identified；For the intelligent television equipment generating device behavior characteristic information to be identified；The device identification of the intelligent television equipment to be identified and the equipment behavior characteristic information are input to pre-set equipment audient crowd prediction model, obtain the corresponding audient crowd's attributive character information of the intelligent television equipment to be identified；Obtained audient crowd's attributive character information is sent to information processing end.
Description
Technical field
This application involves data analysis technique fields, device, method, electronics in particular to a kind of push of information
Equipment and computer readable storage medium.
Background technique
With the development of information science technology, smart television is popularized comprehensively, is investigated and is shown according to related data, at this stage
DTV (Digital Television, DTV) equipment ownership is about 2.27 hundred million, and Internet television equipment is possessed
Amount about 1.5 hundred million, the ownership of internet television equipment is about 1.49 hundred million, throwing of the advertising resource in intelligent television equipment
Money and budget are also more and more, reasonable in order to improve distribution when advertising resource is allocated when carrying out advertising resource dispensing
Degree, determines that audient crowd's attributive character information of intelligent television equipment is then particularly important.
The collection method of the corresponding audient crowd's attributive character information of advertisement exposure in intelligent television equipment, usually in advance
First selected part intelligent television equipment, according to the selected corresponding audient crowd of part intelligent television equipment, according to a certain percentage
All intelligent television equipments of statistics are spreaded to, so that the corresponding audient crowd of all intelligent television equipments is obtained, still, in order to
Reduce cost, generally only select a small amount of intelligent television equipment, the intelligent television equipment obtained when carrying out and spreading to calculating by
The accuracy of everybody's group's attributive character information is relatively low.
Summary of the invention
In view of this, a kind of device, method, electronic equipment and the computer for being designed to provide information push of the application
Readable storage medium storing program for executing, to improve the accuracy of audient crowd's attributive character information of obtained intelligent television equipment.
In a first aspect, the embodiment of the present application provides a kind of device of information push, which includes:
Module is obtained, for obtaining the device identification of intelligent television equipment to be identified；
Generation module, for being the intelligent television equipment generating device behavior characteristic information to be identified；
Prediction module, the device identification of the intelligent television equipment to be identified for obtaining the acquisition module and institute
The equipment behavior characteristic information for stating generation module generation is input to pre-set equipment audient crowd prediction model, obtains
The corresponding audient crowd's attributive character information of the intelligent television equipment to be identified；
Pushing module, audient crowd's attributive character information for obtaining the prediction module are sent to information processing
End.
Optionally, device further include: training module, the training module are used for:
Construct training sample database, the training sample database include sample intelligent television equipment device identification and corresponding people
Sample audient crowd's attributive character information of work mark；
Using the device identification of the sample intelligent television equipment and corresponding equipment behavior characteristic information as the equipment
The input feature vector of audient crowd's prediction model, using corresponding sample audient crowd attributive character information as the equipment by everybody
The output feature of group's prediction model, training obtain the equipment audient crowd prediction model.
Optionally, the training module is specifically used for:
The device identification of the sample intelligent television equipment and corresponding equipment behavior characteristic information are input to and are initially set
By everybody's group's prediction model, forecast sample audient crowd's attributive character information is obtained；
It compares the forecast sample audient crowd attributive character information and manually marks the sample audient crowd attribute spy
Reference breath obtains comparing error；
According to the smallest principle of the comparison error is made, the model of the original equipment audient crowd prediction model is joined
Number is adjusted, equipment audient crowd's prediction model after being adjusted.
Optionally, device further include: update module, the update module are used for:
Utilize the device identification and corresponding audient crowd's attributive character information update of the intelligent television equipment to be identified
Intelligent television equipment storage table.
Optionally, the device further include: enquiry module and determining module,
The acquisition module is also used to:
Equipment audient's inquiry request of user terminal is obtained, carries intelligent television equipment to be checked in the inquiry request
Device identification；
The enquiry module, in the intelligent television equipment storage table, inquiry to be obtained with the acquisition module
The consistent intelligent television equipment of device identification of the intelligent television equipment to be checked；
The determining module, if inquiring the equipment mark with the intelligent television equipment to be checked for the enquiry module
Know consistent intelligent television equipment, then based on the corresponding audient crowd's attributive character information of intelligent television equipment inquired, really
Fixed audient's number corresponding with the request time of the equipment audient inquiry request.
Second aspect, the embodiment of the present application provide a kind of method of information push, this method comprises:
Obtain the device identification of intelligent television equipment to be identified；
For the intelligent television equipment generating device behavior characteristic information to be identified；
The device identification of the intelligent television equipment to be identified and the equipment behavior characteristic information are input to and are set in advance
The equipment audient crowd's prediction model set obtains the corresponding audient crowd's attributive character letter of the intelligent television equipment to be identified
Breath；
Obtained audient crowd's attributive character information is sent to information processing end.
Optionally, it after the audient crowd's attributive character information for obtaining the intelligent television equipment to be identified, also wraps
It includes:
Utilize the device identification and corresponding audient crowd's attributive character information update of the intelligent television equipment to be identified
Intelligent television equipment storage table.
Optionally, after updating the intelligent television equipment storage table, further includes:
Equipment audient's inquiry request of user terminal is received, carries intelligent television equipment to be checked in the inquiry request
Device identification；
In the intelligent television equipment storage table, inquire consistent with the device identification of the intelligent television equipment to be checked
Intelligent television equipment；
If inquiring the consistent intelligent television equipment of device identification with the intelligent television equipment to be checked, it is based on looking into
The corresponding audient crowd's attributive character information of the intelligent television equipment ask, the determining request with the equipment audient inquiry request
Time corresponding audient's number.
The third aspect, the embodiment of the present application provide a kind of electronic equipment, comprising: processor, storage medium and bus, institute
State storage medium and be stored with the executable machine readable instructions of the processor, when electronic equipment operation, the processor with
By bus communication between the storage medium, the processor executes the machine readable instructions, to execute such as above-mentioned side
The step of method.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, the computer-readable storage
It is stored with computer program on medium, executes when the computer program is run by processor such as the step of above-mentioned method.
The device of information push provided by the embodiments of the present application, is getting for obtaining intelligent television equipment to be identified
Device identification and for after intelligent television equipment generating device behavior characteristic information to be identified, by setting for intelligent television equipment to be identified
Standby mark and equipment behavior characteristic information are input to pre-set equipment audient crowd prediction model, and prediction obtains intelligence to be identified
The corresponding audient crowd's attributive character information of energy television equipment, in this way, the audient crowd's attributive character information improved
Accuracy, the audient crowd's attributive character information also improved apply accuracy.
To enable the above objects, features, and advantages of the application to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the application, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is a kind of the first structural schematic diagram of the device of information push provided by the embodiments of the present application；
Fig. 2 is a kind of second of structural schematic diagram of the device of information push provided by the embodiments of the present application；
Fig. 3 is a kind of the third structural schematic diagram of the device of information push provided by the embodiments of the present application；
Fig. 4 is a kind of flow diagram of the method for information push provided by the embodiments of the present application；
Fig. 5 is a kind of structural schematic diagram of computer equipment 500 provided by the embodiments of the present application.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
Middle attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
It is some embodiments of the present application, instead of all the embodiments.The application being usually described and illustrated herein in the accompanying drawings is real
The component for applying example can be arranged and be designed with a variety of different configurations.Therefore, below to the application's provided in the accompanying drawings
The detailed description of embodiment is not intended to limit claimed scope of the present application, but is merely representative of the selected reality of the application
Apply example.Based on embodiments herein, those skilled in the art institute obtained without making creative work
There are other embodiments, shall fall in the protection scope of this application.
When counting the corresponding audient's number of advertisement exposure in intelligent television equipment, usually preselect part intelligence
Television equipment in advance manually demarcates selected intelligent television equipment, is existed with the intelligent television equipment for determining selected in advance
The corresponding commercial audience crowd attributive character of different time sections (age of such as audient crowd, gender, viewing number), is obtaining
After audient's number in the corresponding crowd's attributive character of selected intelligent television equipment, the number of selected intelligent television equipment is calculated
Ratio between amount and the quantity of full dose intelligent television equipment, based on ratio audient corresponding with selected intelligent television equipment
Number calculates audient's number of full dose intelligent television equipment.For example, the number of selected intelligent television equipment is 1000, entirely
The number for measuring intelligent television equipment is 10000, there is 100 equipment, 7 points of viewing at night in selected intelligent television equipment
Number is 4 people, then it is 4000 people that the number of 7 points of viewings, which is 4*100*10, at night in full dose intelligent television equipment, it is, entirely
Measure intelligent television equipment at night 7 points audient's number be 4000.
Although the audient's number of available full dose TV at some time point through the above way, when prior choosing
When the number of fixed intelligent television equipment is fewer, it is, the number and full dose smart television of selected intelligent television equipment
When ratio between the number of equipment is very big, a possibility that full dose intelligent television equipment corresponding audient's number viewing program, is got over
It is more, it is not necessarily identical as the behavior of user in selected intelligent television equipment, therefore, spreading to full dose intelligent television equipment
The accuracy of audient crowd's attributive character can be relatively low.
For ease of description, herein by the equipment behavior characteristic information for being directed to intelligent television equipment is determined, to determine intelligence
Audient crowd's attributive character information of energy television equipment, in order to carry out resource dispensing in intelligent television equipment.The application needle
To intelligent television equipment field, after the device identification for getting intelligent television equipment to be identified, the intelligence electricity to be identified is determined
It is depending on the equipment behavior characteristic information of equipment, the device identification of equipment to be identified and corresponding equipment behavior attributive character information is defeated
Enter into pre-set equipment audient crowd prediction model, prediction obtains the corresponding audient crowd of intelligent television equipment to be identified
Attributive character information, in this way, the accuracy of the audient crowd's attributive character information improved, while also improving and applying
To audient crowd's attributive character information carry out resource dispensing in intelligent television equipment when dispensing accuracy.The application is implemented
Example will be described in detail based on the thought.
The embodiment of the present application provides a kind of device of information push, as shown in Figure 1, the device is set applied to smart television
Standby monitor supervision platform, the device include:
Module 11 is obtained, for obtaining the device identification of intelligent television equipment to be identified；
Generation module 12, for being the intelligent television equipment generating device behavior characteristic information to be identified；
Prediction module 13, the device identification of the intelligent television equipment to be identified for obtaining the acquisition module 11
Pre-set equipment audient crowd, which is input to, with the equipment behavior characteristic information that the generation module 12 generates predicts mould
Type obtains the corresponding audient crowd's attributive character information of the intelligent television equipment to be identified；
Pushing module 14, audient crowd's attributive character information for obtaining the prediction module are sent to information processing
End.
Intelligent television equipment to be identified can be but not limited to digital television devices, Interactive Internet TV equipment, interconnection
Net television equipment etc., the device identification of intelligent television equipment to be identified can be sequence number, the smart television of intelligent television equipment
Device model, MAC Address of intelligent television equipment of equipment etc., device identification is also possible to through the sequence to intelligent television equipment
The secret value that row number, device model, MAC Address are encrypted, Encryption Algorithm can be but not limited to md5 encryption algorithm etc.,
In actual application, the device identification of intelligent television equipment generally utilizes md5 encryption algorithm to the MAC of intelligent television equipment
What address was encrypted, the device identification of obtained each intelligent television equipment is unique, and obtained encryption
The degree of safety of value is higher, device identification can be prevented to be tampered.
The equipment behavior characteristic information of intelligent television equipment is generally by being monitored intelligent television equipment
Extraction obtains in monitoring log, and monitoring in log includes intelligent television equipment using belonging to time, intelligent television equipment
Program category, medium type of program of intelligent television equipment broadcasting that region, intelligent television equipment play etc., wherein use
Time be generally user watch intelligent television equipment time, e.g., on April 12nd, 2019 20:00；Belonging to intelligent television equipment
Region is generally the affiliated region for buying the user of intelligent television equipment, for example, the user of purchase intelligent television equipment is north
The user in capital, then corresponding to region belonging to intelligent television equipment is Beijing；The program category that intelligent television equipment plays includes electricity
Depending on play, film, animation, variety show, sport, amusement, news etc.；The medium type for the program that intelligent television equipment plays can be with
It is the video playing application etc. of intelligent mobile phone terminal, e.g., medium type can apply A, broadcasting using B etc. to play；From monitoring
The equipment behavior characteristic information extracted in log includes the device plays time, equipment fields, device plays program category, sets
The standby medium type etc. for playing program, visual concrete condition determine.
Equipment audient crowd prediction model can be but not limited to convolutional neural networks model, Recognition with Recurrent Neural Network model,
Shot and long term memory network model, Logic Regression Models, Random Forest model etc., can according to practical application scene preference pattern,
The application not limits this, and equipment audient crowd's prediction model is special by obtaining the historical Device behavior of a large amount of equipment
Reference breath and audient crowd's attributive character information input by manually marking are carried out to original equipment audient crowd's prediction model
What training obtained, hereafter it is described in detail.
Audient crowd's attributive character information includes the kinsfolk's composition for possessing intelligent television equipment, member's gender, member
Age, member's educational background, member's income, member's viewing time, member watch program category etc., pre- to original equipment audient crowd
When survey model is trained, the corresponding audient crowd's attributive character information of intelligent television equipment is obtained generally by artificial mark
, in manually mark audient crowd's attributive character information, in order to improve to obtain audient crowd's attributive character letter of model output
24 hours of one day can be divided into multiple periods when marking member's viewing time by the accuracy of breath, for example, dividing
It, can be determines according to actual conditions for 6 periods, 7 periods etc.；When dividing the period, according to working day and can stop
Not busy day divides the different periods, and the length of each period divided for working day or leisure day can be identical, can also be with
Difference, for example, most member or in school or working in family on weekdays, intelligent television equipment uses valence
Value is very low, and evening kinsfolk can be higher to the utilization rate of intelligent television equipment, therefore, the time that daytime on working day divides
The length of section can be longer than the length of the period divided at night, and most of meeting on member's daytime for day of lying fallow, in family
It is in, can also watch amusement and recreation program at night, therefore, the time that the period of leisure division on daytime day can divide with evening
The length of section is consistent.
The embodiment of the present application also provides a kind of devices of information push, as shown in Fig. 2, the device in the device and Fig. 1
It compares, further includes: training module 15, training module 15 is according to following steps training equipment audient crowd prediction model:
Construct training sample database, training sample database include sample intelligent television equipment device identification and corresponding artificial mark
Sample audient crowd's attributive character information of note；
Using the device identification of the sample intelligent television equipment and corresponding equipment behavior characteristic information as the equipment
The input feature vector of audient crowd's prediction model, using corresponding sample audient crowd attributive character information as the equipment by everybody
The output feature of group's prediction model, training obtain the equipment audient crowd prediction model.
When training obtains equipment audient crowd's prediction model, training module 15 is adjusted according to following steps initially by everybody
The model parameter of group's prediction model:
The device identification of the sample intelligent television equipment and corresponding equipment behavior characteristic information are input to and are initially set
By everybody's group's prediction model, forecast sample audient crowd's attributive character information is obtained；
It compares the forecast sample audient crowd attributive character information and manually marks the sample audient crowd attribute spy
Reference breath obtains comparing error；
According to the smallest principle of the comparison error is made, the model of the original equipment audient crowd prediction model is joined
Number is adjusted, equipment audient crowd's prediction model after being adjusted.
Here, comparison error can be is calculated using gradient descent algorithm, maximum- likelihood estimation, the application
This is not limited.
In the specific implementation process, after having constructed training sample database, training sample database can be divided into multiple training
Sample word bank obtains training sample word bank according to preset sequence, utilizes each instruction of acquisition from multiple training sample word banks
Practice sample word bank training original equipment audient crowd prediction model.Wherein, preset sequence can be for according to training sample word bank
The ascending sequence of number successively obtain, or obtained and used from multiple training sample word banks in a manner of arbitrarily unduplicated
It, can be determines according to actual conditions in the training sample word bank of training pattern.
When being trained to initial audient crowd's prediction model, after obtaining first training sample word bank, by first
The device identification for each sample intelligent television equipment for including in training sample word bank and corresponding equipment behavior feature letter
Breath is input to original equipment audient crowd's prediction model, prediction obtain the corresponding forecast sample of each sample intelligent television equipment by
Everybody's group's attributive character information.
Forecast sample audient crowd's attribute of each sample intelligent television equipment in obtaining first training sample word bank
After characteristic information, compares forecast sample audient crowd's attributive character information of each sample intelligent television equipment and manually mark
Sample audient crowd's attributive character information obtains the comparison error for first training sample word bank, so that comparing error
Less than the principle of setting error threshold, the model parameter of original equipment audient crowd prediction model is adjusted, is obtained using first
Equipment audient crowd's prediction model that the training of training sample word bank obtains.Wherein, setting error threshold is generally 3%.
Second training sample word bank is obtained from multiple training sample word banks, using the second training sample word bank to first
Equipment audient crowd's prediction model that a training sample word bank training obtains is trained, corresponding to first training sample word bank
The mode that is trained of equipment audient crowd's prediction model can refer to using first training sample word bank to original equipment by
The process that everybody's group's prediction model is trained, until having trained equipment audient crowd to predict using all training sample word banks
Model.
After training obtains equipment audient crowd's prediction model, the equipment mark of the intelligent television equipment to be identified got
Know, extracts the intelligent television equipment pair to be identified from the corresponding monitoring log of device identification of the intelligent television equipment to be identified
The equipment behavior characteristic information answered, by the equipment of the device identification of intelligent television equipment to be identified and intelligent television equipment to be identified
Behavior characteristic information is input to the equipment audient crowd's prediction model for completing training, and it is corresponding to obtain intelligent television equipment to be identified
Audient crowd's attributive character information.
After obtaining audient crowd's attributive character information of intelligent television equipment to be identified, the audient crowd that can will obtain
Attributive character information is pushed to information processing end.Wherein, information processing end can be intelligent television equipment monitor supervision platform.
Information processing end is after obtaining audient crowd's attributive character information of intelligent television equipment to be identified, with reference to Fig. 2, also
The intelligent television equipment storage table stored in information processing end can be updated by the update module 16 that the device includes,
It is stored in intelligent television equipment storage table between the device identification of intelligent television equipment and audient crowd's attributive character information
Corresponding relationship, specifically includes the following steps:
Utilize the device identification and corresponding audient crowd's attributive character information update of the intelligent television equipment to be identified
Intelligent television equipment storage table.
When updating intelligent television equipment storage table, the equipment that passes through training pattern and obtain intelligent television equipment to be identified
The mode of audient crowd's attributive character compares Expenses Cost, and each update intelligent television equipment storage table will training pattern
Therefore the more wasteful time generally can over time be updated intelligent television equipment storage table, for example, one month
An intelligent television equipment storage table is updated, updates an intelligent television equipment storage table in a season.
After obtaining audient crowd's attributive character information of intelligent television equipment to be identified, if intelligent television equipment storage table
In the not stored device identification for needing identification intelligent television equipment, then by the device identification of intelligent television equipment to be identified and to drink
Equipment audient crowd's attributive character information read in intelligent television equipment storage table, if being deposited in intelligent television equipment storage table
The device identification for containing intelligent television equipment to be identified, then audient crowd's attribute of the intelligent television equipment to be identified abandoned
Characteristic information.
It, can be with after receiving equipment audient's inquiry request of user terminal after having updated intelligent television equipment storage table
It predicts to obtain the audient crowd's attributive character information for the equipment that user terminal to be inquired using above equipment audient crowd's prediction model,
The audient crowd's attributive character information for the equipment that directly user terminal can also be needed to inquire using intelligent television equipment storage table
It is inquired.
It is responded following with equipment audient inquiry request of the intelligent television equipment storage table to user terminal:
With reference to Fig. 3, the application provides a kind of device of information push, the device again further include: enquiry module 17 and really
Cover half block 18.
Equipment audient's inquiry request that module 11 is also used to obtain user terminal is obtained, is carried in the inquiry request to be checked
Ask the device identification of intelligent television equipment；
Enquiry module 17, in the intelligent television equipment storage table, inquiry to be obtained with the acquisition module 11
The consistent intelligent television equipment of device identification of the intelligent television equipment to be checked；
Determining module 18, if inquiring the equipment mark with the intelligent television equipment to be checked for the enquiry module 17
Know consistent intelligent television equipment, then based on the corresponding audient crowd's attributive character information of intelligent television equipment inquired, really
Fixed audient's number corresponding with the request time of the equipment audient inquiry request.
Here, user terminal can be mobile terminal, the network equipment, computer equipment etc., and the application not limits this；If
By the device identification for carrying the intelligent television equipment that user terminal needs to inquire in many inquiry requests.
In the specific implementation process, after the device identification of the intelligent television equipment to be checked of acquisition, intelligence in the updated
In energy television equipment storage table, the consistent intelligent television equipment of device identification of inquiry and intelligent television equipment to be checked, if looking into
Ask with after the device identification of intelligent television equipment to be checked, from inquiring the corresponding audient crowd's attribute of intelligent television equipment
In play time section in characteristic information, the consistent play time section of request time with equipment audient inquiry request is obtained, it will
The corresponding audient's number of the play time section is as audient's number corresponding with the request time of equipment audient's inquiry request, if intelligence
It does not include the device identification of intelligent television equipment to be checked in energy television equipment storage table, then it can be pre- by equipment audient crowd
It surveys model prediction and obtains audient crowd's attributive character information of the intelligent television equipment to be checked, it can also be by the intelligence to be checked
The average value of audient's number of regional corresponding requests time belonging to television equipment is corresponding as intelligent television equipment to be checked
Audient's number.
For example, the device identification stored in intelligent television equipment storage table includes A, B, A intelligent television equipment it is corresponding by
Play time section in everybody's group's attributive character information includes S1-S2, S3-S4, S5-S6, and above three play time section is corresponding
Audient's number be respectively Q10, Q20, Q30, when broadcasting in the corresponding audient crowd's attributive character information of B intelligent television equipment
Between section include S1-S2, S3-S4, S5-S6, the corresponding audient's number of above three play time section is respectively Q11, Q21, Q31,
If the device identification of the intelligent television equipment to be checked received is A, request time is to fall between S3-S4, it is determined that be checked
Asking the corresponding audient's number of intelligent television equipment is Q20.
The device of information push provided by the embodiments of the present application, is getting for obtaining intelligent television equipment to be identified
Device identification and for after intelligent television equipment generating device behavior characteristic information to be identified, by setting for intelligent television equipment to be identified
Standby mark and equipment behavior characteristic information are input to pre-set equipment audient crowd prediction model, and prediction obtains intelligence to be identified
The corresponding audient crowd's attributive character information of energy television equipment, in this way, the audient crowd's attributive character information improved
Accuracy, the audient crowd's attributive character information also improved apply accuracy.
The embodiment of the present application provides a kind of method of information push, as shown in figure 4, method includes the following steps:
S401 obtains the device identification of intelligent television equipment to be identified；
S402 is the intelligent television equipment generating device behavior characteristic information to be identified；
The device identification of the intelligent television equipment to be identified and the equipment behavior characteristic information are input to pre- by S403
The equipment audient crowd's prediction model being first arranged obtains the corresponding audient crowd's attributive character of the intelligent television equipment to be identified
Information；
Obtained audient crowd's attributive character information is sent to information processing end by S404.
Optionally, according to the following steps training equipment audient crowd prediction model:
Construct training sample database, the training sample database include sample intelligent television equipment device identification and corresponding people
Sample audient crowd's attributive character information of work mark；
Using the device identification of the sample intelligent television equipment and corresponding equipment behavior characteristic information as the equipment
The input feature vector of audient crowd's prediction model, using corresponding sample audient crowd attributive character information as the equipment by everybody
The output feature of group's prediction model, training obtain the equipment audient crowd prediction model.
Optionally, described to make the device identification of the sample intelligent television equipment and corresponding equipment behavior characteristic information
For the input feature vector of the equipment audient crowd prediction model, using corresponding sample audient crowd attributive character information as described in
The output feature of equipment audient crowd's prediction model, training obtain the equipment audient crowd prediction model, comprising:
The device identification of the sample intelligent television equipment and corresponding equipment behavior characteristic information are input to and are initially set
By everybody's group's prediction model, forecast sample audient crowd's attributive character information is obtained；
It compares the forecast sample audient crowd attributive character information and manually marks the sample audient crowd attribute spy
Reference breath obtains comparing error；
According to the smallest principle of the comparison error is made, the model of the original equipment audient crowd prediction model is joined
Number is adjusted, equipment audient crowd's prediction model after being adjusted.
Optionally, it after the audient crowd's attributive character information for obtaining the intelligent television equipment to be identified, also wraps
It includes:
Utilize the device identification and corresponding audient crowd's attributive character information update of the intelligent television equipment to be identified
Intelligent television equipment storage table.
Optionally, after updating the intelligent television equipment storage table, further includes:
Equipment audient's inquiry request of user terminal is received, carries intelligent television equipment to be checked in the inquiry request
Device identification；
In the intelligent television equipment storage table, inquire consistent with the device identification of the intelligent television equipment to be checked
Intelligent television equipment；
If inquiring the consistent intelligent television equipment of device identification with the intelligent television equipment to be checked, it is based on looking into
The corresponding audient crowd's attributive character information of the intelligent television equipment ask, the determining request with the equipment audient inquiry request
Time corresponding audient's number.
Corresponding to the method for the information push in Fig. 4, the embodiment of the present application also provides a kind of computer equipments 500, such as
Shown in Fig. 5, which includes memory 501, processor 502 and is stored on the memory 501 and can be on the processor 502
The computer program of operation, wherein above-mentioned processor 502 realizes the side of above- mentioned information push when executing above-mentioned computer program
Method.
Specifically, above-mentioned memory 501 and processor 502 can be general memory and processor, do not do have here
Body limits, when the computer program of 502 run memory 501 of processor storage, the method for being able to carry out above- mentioned information push,
To solve the problems, such as that the accuracy of audient crowd's attributive character information of prior art intelligent television equipment is low, the application is implemented
Example is in the device identification got for obtaining intelligent television equipment to be identified and is intelligent television equipment generating device to be identified
After behavior characteristic information, the device identification of intelligent television equipment to be identified and equipment behavior characteristic information are input to and are preset
Equipment audient crowd's prediction model, prediction obtain the corresponding audient crowd's attributive character information of intelligent television equipment to be identified,
In this way, the accuracy of the audient crowd's attributive character information improved, the audient crowd's attributive character also improved
Information applies accuracy.
Corresponding to the method for the information push in Fig. 4, the embodiment of the present application also provides a kind of computer-readable storage mediums
Matter is stored with computer program on the computer readable storage medium, which executes above-mentioned when being run by processor
The step of method of information push.
Specifically, which can be general storage medium, such as mobile disk, hard disk, on the storage medium
Computer program when being run, the method for being able to carry out above- mentioned information push, to solve prior art intelligent television equipment
Audient crowd's attributive character information the low problem of accuracy, the embodiment of the present application getting for obtaining intelligence to be identified
The device identification of television equipment and for after intelligent television equipment generating device behavior characteristic information to be identified, will intelligence electricity to be identified
Device identification and equipment behavior characteristic information depending on equipment are input to pre-set equipment audient crowd prediction model, measure in advance
To the corresponding audient crowd's attributive character information of intelligent television equipment to be identified, in this way, the audient crowd's attribute improved
The accuracy of characteristic information, the audient crowd's attributive character information also improved apply accuracy.
In embodiment provided herein, it should be understood that disclosed system and method, it can be by others side
Formula is realized.System embodiment described above is only schematical, for example, the division of the unit, only one kind are patrolled
Function division is collected, there may be another division manner in actual implementation, in another example, multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some communication interfaces, system or unit
It connects, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in embodiment provided by the present application can integrate in one processing unit, it can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) execute each embodiment the method for the application all or part of the steps.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing, in addition, term " the
One ", " second ", " third " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
Finally, it should be noted that embodiment described above, the only specific embodiment of the application, to illustrate the application
Technical solution, rather than its limitations, the protection scope of the application is not limited thereto, although with reference to the foregoing embodiments to this Shen
It please be described in detail, those skilled in the art should understand that: anyone skilled in the art
Within the technical scope of the present application, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of the embodiment of the present application technical solution.The protection in the application should all be covered
Within the scope of.Therefore, the protection scope of the application shall be subject to the protection scope of the claim.
Claims (10)
1. a kind of device of information push, which is characterized in that the device includes:
Module is obtained, for obtaining the device identification of intelligent television equipment to be identified；
Generation module, for being the intelligent television equipment generating device behavior characteristic information to be identified；
Prediction module, the device identification and the life of the intelligent television equipment to be identified for obtaining the acquisition module
It is input to pre-set equipment audient crowd prediction model at the equipment behavior characteristic information that module generates, is obtained described
The corresponding audient crowd's attributive character information of intelligent television equipment to be identified；
Pushing module, audient crowd's attributive character information for obtaining the prediction module are sent to information processing end.
2. device as described in claim 1, which is characterized in that the device further include: training module, the training module are used
In:
Construct training sample database, the training sample database include sample intelligent television equipment device identification and corresponding artificial mark
Sample audient crowd's attributive character information of note；
Using the device identification of the sample intelligent television equipment and corresponding equipment behavior characteristic information as the equipment audient
The input feature vector of crowd's prediction model, corresponding sample audient crowd attributive character information is pre- as the equipment audient crowd
The output feature of model is surveyed, training obtains the equipment audient crowd prediction model.
3. device as claimed in claim 2, which is characterized in that the training module is specifically used for:
By the device identification of the sample intelligent television equipment and corresponding equipment behavior characteristic information be input to original equipment by
Everybody's group's prediction model, obtains forecast sample audient crowd's attributive character information；
It compares the forecast sample audient crowd attributive character information and manually marks the sample audient crowd attributive character letter
Breath obtains comparing error；
According to making the smallest principle of the comparison error, to the model parameter of the original equipment audient crowd prediction model into
Row adjustment, equipment audient crowd's prediction model after being adjusted.
4. device as described in claim 1, which is characterized in that the device further include: update module, the update module are used
In:
Utilize the device identification of the intelligent television equipment to be identified and corresponding audient crowd's attributive character information update intelligence
Television equipment storage table.
5. device as claimed in claim 4, which is characterized in that the device further include: enquiry module and determining module,
The acquisition module is also used to:
Equipment audient's inquiry request of user terminal is obtained, the equipment of intelligent television equipment to be checked is carried in the inquiry request
Mark；
The enquiry module, it is described with the acquisition module acquisition for inquiring in the intelligent television equipment storage table
The consistent intelligent television equipment of the device identification of intelligent television equipment to be checked；
The determining module, if inquiring the device identification one with the intelligent television equipment to be checked for the enquiry module
The intelligent television equipment of cause, then based on the corresponding audient crowd's attributive character information of intelligent television equipment inquired, determine with
The corresponding audient's number of the request time of the equipment audient inquiry request.
6. a kind of method of information push, which is characterized in that this method comprises:
Obtain the device identification of intelligent television equipment to be identified；
For the intelligent television equipment generating device behavior characteristic information to be identified；
The device identification of the intelligent television equipment to be identified and the equipment behavior characteristic information are input to pre-set
Equipment audient crowd's prediction model obtains the corresponding audient crowd's attributive character information of the intelligent television equipment to be identified；
Obtained audient crowd's attributive character information is sent to information processing end.
7. method as claimed in claim 6, which is characterized in that in the audient for obtaining the intelligent television equipment to be identified
After crowd's attributive character information, further includes:
Utilize the device identification of the intelligent television equipment to be identified and corresponding audient crowd's attributive character information update intelligence
Television equipment storage table.
8. the method for claim 7, which is characterized in that after updating the intelligent television equipment storage table, further includes:
Equipment audient's inquiry request of user terminal is received, the equipment of intelligent television equipment to be checked is carried in the inquiry request
Mark；
In the intelligent television equipment storage table, the consistent intelligence of device identification of inquiry and the intelligent television equipment to be checked
It can television equipment；
If inquiring the consistent intelligent television equipment of device identification with the intelligent television equipment to be checked, it is based on inquiring
The corresponding audient crowd's attributive character information of intelligent television equipment, the determining request time with the equipment audient inquiry request
Corresponding audient's number.
9. a kind of electronic equipment characterized by comprising processor, storage medium and bus, the storage medium storage is
The executable machine readable instructions of processor are stated, when electronic equipment operation, are led between the processor and the storage medium
Bus communication is crossed, the processor executes the machine readable instructions, to execute the step such as any the method for claim 6-8
Suddenly.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program is executed when the computer program is run by processor such as the step of claim 6-8 any the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910353015.9A CN110087104B (en) | 2019-04-29 | 2019-04-29 | Information pushing device and method, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910353015.9A CN110087104B (en) | 2019-04-29 | 2019-04-29 | Information pushing device and method, electronic equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110087104A true CN110087104A (en) | 2019-08-02 |
| CN110087104B CN110087104B (en) | 2021-07-27 |
Family
ID=67417590
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910353015.9A Active CN110087104B (en) | 2019-04-29 | 2019-04-29 | Information pushing device and method, electronic equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110087104B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111222923A (en) * | 2020-01-13 | 2020-06-02 | 秒针信息技术有限公司 | Method and device for judging potential customer, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140082643A1 (en) * | 2006-10-17 | 2014-03-20 | Google Inc. | Targeted Video Advertising |
| US20140229280A1 (en) * | 2007-04-06 | 2014-08-14 | Awel Llc | Systems and methods for targeted advertising |
| CN104702981A (en) * | 2013-12-06 | 2015-06-10 | 北京思博途信息技术有限公司 | Method and system for computing digital television target audiences |
| CN105208411A (en) * | 2014-06-05 | 2015-12-30 | 北京秒针信息咨询有限公司 | Method and device for realizing digital television target audience statistics |
| CN105959745A (en) * | 2016-05-25 | 2016-09-21 | 北京铭嘉实咨询有限公司 | Advertising method and system |
| CN106469202A (en) * | 2016-08-31 | 2017-03-01 | 杭州探索文化传媒有限公司 | A kind of data analysing method of video display big data platform |
| CN107770576A (en) * | 2017-10-31 | 2018-03-06 | 深圳红点点互动技术发展有限公司 | A kind of interaction platform management method and system |
| CN108352025A (en) * | 2015-07-24 | 2018-07-31 | 安普视频有限公司 | Television advertising period positioning based on the online behavior of consumer |
-
2019
- 2019-04-29 CN CN201910353015.9A patent/CN110087104B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140082643A1 (en) * | 2006-10-17 | 2014-03-20 | Google Inc. | Targeted Video Advertising |
| US20140229280A1 (en) * | 2007-04-06 | 2014-08-14 | Awel Llc | Systems and methods for targeted advertising |
| CN104702981A (en) * | 2013-12-06 | 2015-06-10 | 北京思博途信息技术有限公司 | Method and system for computing digital television target audiences |
| CN105208411A (en) * | 2014-06-05 | 2015-12-30 | 北京秒针信息咨询有限公司 | Method and device for realizing digital television target audience statistics |
| CN108352025A (en) * | 2015-07-24 | 2018-07-31 | 安普视频有限公司 | Television advertising period positioning based on the online behavior of consumer |
| CN105959745A (en) * | 2016-05-25 | 2016-09-21 | 北京铭嘉实咨询有限公司 | Advertising method and system |
| CN106469202A (en) * | 2016-08-31 | 2017-03-01 | 杭州探索文化传媒有限公司 | A kind of data analysing method of video display big data platform |
| CN107770576A (en) * | 2017-10-31 | 2018-03-06 | 深圳红点点互动技术发展有限公司 | A kind of interaction platform management method and system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111222923A (en) * | 2020-01-13 | 2020-06-02 | 秒针信息技术有限公司 | Method and device for judging potential customer, electronic equipment and storage medium |
| CN111222923B (en) * | 2020-01-13 | 2023-12-15 | 秒针信息技术有限公司 | Method and device for judging potential clients, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110087104B (en) | 2021-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109902849B (en) | User behavior prediction method and device, and behavior prediction model training method and device | |
| CN109902708A (en) | A kind of recommended models training method and relevant apparatus | |
| CN105872830B (en) | Interactive approach and device in direct broadcast band | |
| CN107968952B (en) | Method, device, server and computer-readable storage medium for recommending videos | |
| CN108090208A (en) | Fused data processing method and processing device | |
| CN108108821A (en) | Model training method and device | |
| TW202007178A (en) | Method, device, apparatus, and storage medium of generating features of user | |
| CN107071578A (en) | IPTV program commending methods | |
| CN111442778A (en) | Travel scheme recommendation method, device and equipment and computer readable storage medium | |
| CN105100886B (en) | Distribution control method and device, the server and system of network media information | |
| CN105718510B (en) | A kind of multi-medium data recommended method and device | |
| CN106202393B (en) | Media information pushing method and device | |
| CN108269109A (en) | A kind of Advertisement arrangement injected volume equalization methods and device | |
| CN110472154A (en) | A kind of resource supplying method, apparatus, electronic equipment and readable storage medium storing program for executing | |
| CN108776904A (en) | A kind of methods of exhibiting and its equipment of advertisement information | |
| CN108090107A (en) | Business object recommends method, apparatus, electronic equipment and storage medium | |
| CN104967690A (en) | Information push method and device | |
| CN108475256A (en) | Feature insertion is generated from homologous factors | |
| CN105930532B (en) | A kind of method and apparatus from multimedia resource to user that recommending | |
| CN110362751B (en) | Service recommendation method, device, computer equipment and storage medium | |
| CN108770002A (en) | Base station flow analysis method, device, equipment and storage medium | |
| CN110087104A (en) | Device, method, electronic equipment and the computer readable storage medium of information push | |
| Yates et al. | Evaluation of synthetic aerial imagery using unconditional generative adversarial networks | |
| CN112559777A (en) | Content item delivery method and device, computer equipment and storage medium | |
| CN114339362A (en) | Video bullet screen matching method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |