CN110087104B - Information pushing device and method, electronic equipment and computer readable storage medium - Google Patents

Information pushing device and method, electronic equipment and computer readable storage medium Download PDF

Info

Publication number
CN110087104B
CN110087104B CN201910353015.9A CN201910353015A CN110087104B CN 110087104 B CN110087104 B CN 110087104B CN 201910353015 A CN201910353015 A CN 201910353015A CN 110087104 B CN110087104 B CN 110087104B
Authority
CN
China
Prior art keywords
intelligent television
equipment
audience
characteristic information
identified
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.)
Active
Application number
CN201910353015.9A
Other languages
Chinese (zh)
Other versions
CN110087104A (en
Inventor
吴济
张宇婷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Miaozhen Information Technology Co Ltd
Original Assignee
Miaozhen Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Miaozhen Information Technology Co Ltd filed Critical Miaozhen Information Technology Co Ltd
Priority to CN201910353015.9A priority Critical patent/CN110087104B/en
Publication of CN110087104A publication Critical patent/CN110087104A/en
Application granted granted Critical
Publication of CN110087104B publication Critical patent/CN110087104B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25Management 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
    • H04N21/251Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25Management 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
    • H04N21/251Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/252Processing of multiple end-users' preferences to derive collaborative data
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45Management 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
    • H04N21/466Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4668Learning 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)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

The application provides an information pushing device, an information pushing method, an electronic device and a computer readable storage medium, wherein the method comprises the following steps: acquiring a device identifier of the intelligent television device to be identified; generating equipment behavior characteristic information for the intelligent television equipment to be identified; inputting the device identification and the device behavior characteristic information of the intelligent television device to be identified into a preset device audience crowd prediction model to obtain audience crowd attribute characteristic information corresponding to the intelligent television device to be identified; and sending the obtained audience population attribute characteristic information to an information processing end.

Description

Information pushing device and method, electronic equipment and computer readable storage medium
Technical Field
The present application relates to the field of data analysis technologies, and in particular, to an information pushing apparatus, an information pushing method, an electronic device, and a computer-readable storage medium.
Background
With the development of information science and technology, smart televisions have been popularized comprehensively, and according to the investigation and display of related data, the quantity of Digital Television (DTV) equipment at the present stage is about 2.27 hundred million, the quantity of interactive network Television equipment is about 1.5 hundred million, the quantity of internet Television equipment is about 1.49 hundred million, the investment and budget of advertisement resources on the smart Television equipment are more and more, and when advertisement resources are released, in order to improve the distribution reasonableness when the advertisement resources are distributed, it is very important to determine the audience crowd attribute feature information of the smart Television equipment.
The method for collecting audience crowd attribute characteristic information corresponding to advertisement exposure in the intelligent television equipment generally includes the steps of selecting a part of intelligent television equipment in advance, and promoting all the intelligent television equipment according to a certain proportion to obtain audience crowds corresponding to all the intelligent television equipment according to the audience crowds corresponding to the selected part of the intelligent television equipment.
Disclosure of Invention
In view of the above, an object of the present application is to provide an apparatus, a method, an electronic device, and a computer-readable storage medium for pushing information, so as to improve accuracy of obtained attribute feature information of an audience group of a smart television device.
In a first aspect, an embodiment of the present application provides an information pushing apparatus, where the apparatus includes:
the acquisition module is used for acquiring the equipment identifier of the intelligent television equipment to be identified;
the generating module is used for generating equipment behavior characteristic information for the intelligent television equipment to be identified;
the prediction module is used for inputting the device identifier of the intelligent television device to be identified, which is acquired by the acquisition module, and the device behavior characteristic information generated by the generation module into a preset device audience crowd prediction model to obtain audience crowd attribute characteristic information corresponding to the intelligent television device to be identified;
and the pushing module is used for sending the audience crowd attribute characteristic information obtained by the predicting module to an information processing end.
Optionally, the apparatus further comprises: a training module to:
constructing a training sample library, wherein the training sample library comprises equipment identification of sample intelligent television equipment and corresponding artificially labeled sample audience crowd attribute characteristic information;
and taking the device identification of the sample intelligent television device and the corresponding device behavior characteristic information as the input characteristics of the device audience crowd prediction model, taking the corresponding sample audience crowd attribute characteristic information as the output characteristics of the device audience crowd prediction model, and training to obtain the device audience crowd prediction model.
Optionally, the training module is specifically configured to:
inputting the device identification of the sample intelligent television device and the corresponding device behavior characteristic information into an initial device audience crowd prediction model to obtain predicted sample audience crowd attribute characteristic information;
comparing the predicted sample audience crowd attribute feature information with the manually marked sample audience crowd attribute feature information to obtain a comparison error;
and adjusting the model parameters of the initial equipment audience crowd prediction model according to the principle of minimizing the comparison error to obtain the adjusted equipment audience crowd prediction model.
Optionally, the apparatus further comprises: an update module to:
and updating a storage table of the intelligent television equipment by using the equipment identification of the intelligent television equipment to be identified and the corresponding audience crowd attribute characteristic information.
Optionally, the apparatus further comprises: a query module and a determination module, wherein the query module and the determination module,
the acquisition module is further configured to:
acquiring a query request of a device audience of a user side, wherein the query request carries a device identifier of the intelligent television device to be queried;
the query module is used for querying the smart television equipment which is consistent with the equipment identifier of the smart television equipment to be queried, which is acquired by the acquisition module, in the smart television equipment storage table;
the determining module is used for determining the number of audiences corresponding to the request time of the equipment audience query request based on the inquired audience crowd attribute characteristic information corresponding to the intelligent television equipment if the intelligent television equipment consistent with the equipment identification of the intelligent television equipment to be inquired is inquired by the inquiring module.
In a second aspect, an embodiment of the present application provides an information pushing method, where the method includes:
acquiring a device identifier of the intelligent television device to be identified;
generating equipment behavior characteristic information for the intelligent television equipment to be identified;
inputting the device identification and the device behavior characteristic information of the intelligent television device to be identified into a preset device audience crowd prediction model to obtain audience crowd attribute characteristic information corresponding to the intelligent television device to be identified;
and sending the obtained audience crowd attribute characteristic information to an information processing end.
Optionally, after obtaining the attribute feature information of the audience crowd of the smart television device to be identified, the method further includes:
and updating a storage table of the intelligent television equipment by using the equipment identification of the intelligent television equipment to be identified and the corresponding audience crowd attribute characteristic information.
Optionally, after the storage table of the smart television device is updated, the method further includes:
receiving an equipment audience query request of a user side, wherein the query request carries an equipment identifier of the intelligent television equipment to be queried;
inquiring the intelligent television equipment consistent with the equipment identification of the intelligent television equipment to be inquired in the intelligent television equipment storage table;
and if the intelligent television equipment consistent with the equipment identification of the intelligent television equipment to be inquired is inquired, determining the audience number corresponding to the request time of the equipment audience inquiry request based on the inquired audience population attribute characteristic information corresponding to the intelligent television equipment.
In a third aspect, an embodiment of the present application provides an electronic device, including: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating via the bus when the electronic device is operating, the processor executing the machine-readable instructions to perform the steps of the method as described above.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, performing the steps of the method as described above.
The device for information pushing provided by the embodiment of the application acquires the device identification used for acquiring the intelligent television device to be identified and generates the device behavior characteristic information for the intelligent television device to be identified, inputs the device identification and the device behavior characteristic information of the intelligent television device to be identified into the preset device audience population prediction model, and predicts the audience population attribute characteristic information corresponding to the intelligent television device to be identified, so that the accuracy of the obtained audience population attribute characteristic information is improved, and the application accuracy of the obtained audience population attribute characteristic information is also improved.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a first schematic structural diagram of an information pushing apparatus according to an embodiment of the present disclosure;
fig. 2 is a second schematic structural diagram of an information pushing apparatus according to an embodiment of the present disclosure;
fig. 3 is a third structural diagram of an information pushing apparatus according to an embodiment of the present application;
fig. 4 is a flowchart illustrating an information pushing method according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a computer device 500 according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
When counting the number of audiences corresponding to advertisement exposure in the intelligent television equipment, generally, part of the intelligent television equipment is selected in advance, the selected intelligent television equipment is manually calibrated in advance to determine the advertising audience crowd attribute characteristics (such as the ages, sexes, the number of watching people and the like) corresponding to the selected intelligent television equipment in different time periods, after the number of the audiences in the crowd attribute characteristics corresponding to the selected intelligent television equipment is obtained, the ratio between the number of the selected intelligent television equipment and the number of the full-scale intelligent television equipment is calculated, and the number of the audiences of the full-scale intelligent television equipment is calculated based on the ratio and the number of the audiences corresponding to the selected intelligent television equipment. For example, the number of the selected smart television devices is 1000, the number of the full smart television devices is 10000, and the number of people watched by 100 devices in the selected smart television devices at 7 pm is 4, and the number of people watched by 4 × 100 × 10 in the full smart television devices at 7 pm is 4000, that is, the number of people audience of the full smart television devices at 7 pm is 4000.
Although the audience number of the full-scale television at a certain time point can be obtained in the above manner, when the number of the selected smart television devices is small, that is, when the ratio between the number of the selected smart television devices and the number of the full-scale smart television devices is large, the possibility that the audience number corresponding to the full-scale smart television devices watches programs is more likely and is not necessarily the same as the behavior of the users in the selected smart television devices, and therefore, the accuracy of estimating the audience population attribute characteristics of the full-scale smart television devices is low.
For convenience of description, the device behavior characteristic information for the smart television device is determined to determine audience crowd attribute characteristic information of the smart television device, so as to facilitate resource delivery in the smart television device. The method is specific to the field of intelligent television equipment, after the equipment identification of the intelligent television equipment to be identified is obtained, the equipment behavior characteristic information of the intelligent television equipment to be identified is determined, the equipment identification of the equipment to be identified and the corresponding equipment behavior attribute characteristic information are input into a preset equipment audience crowd prediction model, and audience crowd attribute characteristic information corresponding to the intelligent television equipment to be identified is obtained through prediction. The embodiments of the present application will be described in detail based on this idea.
The embodiment of the application provides an information pushing device, as shown in fig. 1, the device is applied to a smart television device monitoring platform, and the device includes:
the acquisition module 11 is used for acquiring a device identifier of the smart television device to be identified;
the generating module 12 is configured to generate device behavior feature information for the smart television device to be identified;
the prediction module 13 is configured to input the device identifier of the smart television device to be identified, which is acquired by the acquisition module 11, and the device behavior feature information generated by the generation module 12 into a preset device audience crowd prediction model, so as to obtain audience crowd attribute feature information corresponding to the smart television device to be identified;
and the pushing module 14 is used for sending the audience crowd attribute feature information obtained by the predicting module to an information processing terminal.
The smart television device to be identified may be, but is not limited to, a digital television device, an interactive network television device, an internet television device, and the like, the device identifier of the smart television device to be identified may be, for example, a serial number of the smart television device, a device model of the smart television device, an MAC address of the smart television device, and the like, the device identifier may also be, for example, an encryption value obtained by encrypting the serial number, the device model, and the MAC address of the smart television device, and the encryption algorithm may be, but is not limited to, an MD5 encryption algorithm, and the like.
The equipment behavior characteristic information of the intelligent television equipment is generally extracted from a monitoring log obtained by monitoring the intelligent television equipment, wherein the monitoring log comprises the use time of the intelligent television equipment, the region to which the intelligent television equipment belongs, the type of a program played by the intelligent television equipment, the type of a media of the program played by the intelligent television equipment and the like, wherein the use time is generally the time when a user watches the intelligent television equipment, for example, 20:00 in 4/12/2019; the region to which the smart television device belongs is generally the region to which a user who purchases the smart television device belongs, for example, if the user who purchases the smart television device is a user in beijing, the region to which the corresponding smart television device belongs is beijing; the program types played by the intelligent television equipment comprise TV plays, movies, cartoons, comprehensive programs, sports, entertainment, news and the like; the media type of the program played by the smart television device may be a video playing application of the smart phone terminal, and the like, for example, the media type may be a playing application a, a playing application B, and the like; the device behavior feature information extracted from the monitoring log includes device playing time, the field to which the device belongs, the type of a device playing program, the type of a media of the device playing program, and the like, and can be determined according to specific situations.
The device audience crowd prediction model can be but is not limited to a convolutional neural network model, a cyclic neural network model, a long-short term memory network model, a logistic regression model, a random forest model and the like, the model can be selected according to practical application scenes, the method is not limited by the application, the device audience crowd prediction model is obtained by acquiring a large amount of historical device behavior characteristic information of devices and inputting the audience crowd attribute characteristic information manually marked into an initial device audience crowd prediction model for training, and details are given below.
The audience crowd attribute characteristic information comprises family member composition, member gender, member age, member academic history, member income, member watching time, member watching program types and the like of intelligent television equipment, when an initial equipment audience crowd prediction model is trained, the audience crowd attribute characteristic information corresponding to the intelligent television equipment is generally obtained through manual marking, when the audience crowd attribute characteristic information is marked manually, in order to improve the accuracy of the audience crowd attribute characteristic information output by the model, 24 hours of a day can be divided into a plurality of time periods when the member watching time is marked, for example, the time periods are divided into 6 time periods, 7 time periods and the like, and the time periods can be determined according to actual conditions; when dividing the time slot, can divide different time slots according to weekday and leisure day, the length of each time slot of dividing to weekday or leisure day can be the same, also can be different, for example, most members in weekday family or at school or at work, the use value of smart television equipment is very low, and family member can be higher to the rate of use of smart television equipment evening, therefore, the length of the time slot of dividing daytime in weekday can be longer than the length of the time slot of dividing evening, and for the leisure day, most members in family can be at home daytime, also can watch leisure entertainment program evening, therefore, the time slot of dividing daytime in leisure day can be unanimous with the length of the time slot of dividing evening.
An embodiment of the present application further provides an information pushing apparatus, as shown in fig. 2, the apparatus further includes, compared with the apparatus in fig. 1: the training module 15, the training module 15 trains the device audience crowd prediction model according to the following steps:
constructing a training sample library, wherein the training sample library comprises equipment identification of sample intelligent television equipment and corresponding artificially labeled sample audience crowd attribute characteristic information;
and taking the device identification of the sample intelligent television device and the corresponding device behavior characteristic information as the input characteristics of the device audience crowd prediction model, taking the corresponding sample audience crowd attribute characteristic information as the output characteristics of the device audience crowd prediction model, and training to obtain the device audience crowd prediction model.
When the device audience population prediction model is obtained by training, the training module 15 adjusts the model parameters of the initial audience population prediction model according to the following steps:
inputting the device identification of the sample intelligent television device and the corresponding device behavior characteristic information into an initial device audience crowd prediction model to obtain predicted sample audience crowd attribute characteristic information;
comparing the predicted sample audience crowd attribute feature information with the manually marked sample audience crowd attribute feature information to obtain a comparison error;
and adjusting the model parameters of the initial equipment audience crowd prediction model according to the principle of minimizing the comparison error to obtain the adjusted equipment audience crowd prediction model.
Here, the comparison error may be calculated by using a gradient descent algorithm or a maximum likelihood estimation algorithm, which is not limited in the present application.
In a specific implementation process, after a training sample library is constructed, the training sample library can be divided into a plurality of training sample sub-libraries, the training sample sub-libraries are obtained from the plurality of training sample sub-libraries according to a preset sequence, and the obtained training sample sub-libraries are used for training an initial device audience crowd prediction model. The preset sequence can be obtained in sequence from small to large according to the numbers of the training sample sub-libraries, or the training sample sub-libraries used for training the model are obtained from a plurality of training sample sub-libraries in a random non-repeating mode and can be determined according to actual conditions.
When the initial audience crowd prediction model is trained, after a first training sample sub-library is obtained, the device identifications of all sample intelligent television devices and the device behavior characteristic information corresponding to the device identifications and the device behavior characteristic information are input into the initial device audience crowd prediction model, and the predicted sample audience crowd attribute characteristic information corresponding to each sample intelligent television device is obtained through prediction.
After the predicted sample audience crowd attribute feature information of each sample intelligent television device in the first training sample sub-library is obtained, the predicted sample audience crowd attribute feature information of each sample intelligent television device is compared with the artificially labeled sample audience crowd attribute feature information, a comparison error for the first training sample sub-library is obtained, the comparison error is smaller than a set error threshold value, model parameters of an initial device audience crowd prediction model are adjusted, and a device audience crowd prediction model obtained by training through the first training sample sub-library is obtained. Wherein the set error threshold is typically 3%.
And obtaining a second training sample sub-library from the plurality of training sample sub-libraries, training the equipment audience crowd prediction model obtained by training the first training sample sub-library by using the second training sample sub-library, and training the equipment audience crowd prediction model corresponding to the first training sample sub-library by referring to the process of training the initial equipment audience crowd prediction model by using the first training sample sub-library until the equipment audience crowd prediction model is trained by using all the training sample sub-libraries.
After the device audience crowd prediction model is obtained through training, the device identification of the to-be-recognized intelligent television device is obtained, device behavior characteristic information corresponding to the to-be-recognized intelligent television device is extracted from a monitoring log corresponding to the device identification of the to-be-recognized intelligent television device, the device identification of the to-be-recognized intelligent television device and the device behavior characteristic information of the to-be-recognized intelligent television device are input into the trained device audience crowd prediction model, and audience crowd attribute characteristic information corresponding to the to-be-recognized intelligent television device is obtained.
After the audience crowd attribute feature information of the intelligent television equipment to be identified is obtained, the obtained audience crowd attribute feature information can be pushed to an information processing end. The information processing terminal can be an intelligent television equipment monitoring platform.
After obtaining audience crowd attribute feature information of the intelligent television equipment to be identified, the information processing terminal, referring to fig. 2, may also update an intelligent television equipment storage table stored in the information processing terminal through an update module 16 included in the apparatus, where a correspondence between an equipment identifier of the intelligent television equipment and the audience crowd attribute feature information is stored in the intelligent television equipment storage table, and specifically includes the following steps:
and updating a storage table of the intelligent television equipment by using the equipment identification of the intelligent television equipment to be identified and the corresponding audience crowd attribute characteristic information.
When the storage table of the intelligent television device is updated, the model is trained and the attribute characteristics of the device audience crowd of the intelligent television device to be identified are obtained, so that the cost is relatively consumed, and the model is relatively wasted when the storage table of the intelligent television device is updated every time, so that the storage table of the intelligent television device is generally updated after a period of time, for example, the storage table of the intelligent television device is updated once a month, and the storage table of the intelligent television device is updated once a quarter.
After the attribute feature information of the audience crowd of the intelligent television equipment to be identified is obtained, if the equipment identification of the intelligent television equipment to be identified is not stored in the intelligent television equipment storage table, reading the equipment identification of the intelligent television equipment to be identified and the attribute feature information of the audience crowd of the drunk equipment into the intelligent television equipment storage table, and if the equipment identification of the intelligent television equipment to be identified is stored in the intelligent television equipment storage table, discarding the obtained attribute feature information of the audience crowd of the intelligent television equipment to be identified.
After the storage table of the intelligent television device is updated and a device audience query request of the user side is received, the device audience crowd prediction model can be used for predicting and obtaining audience crowd attribute characteristic information of the device to be queried by the user side, and the storage table of the intelligent television device can also be directly used for querying the audience crowd attribute characteristic information of the device to be queried by the user side.
Responding to the equipment audience query request of the user side by using the intelligent television equipment storage table as follows:
referring to fig. 3, the present application further provides an information pushing apparatus, which further includes: a query module 17 and a determination module 18.
The obtaining module 11 is further configured to obtain an equipment audience query request of a user side, where the query request carries an equipment identifier of the intelligent television equipment to be queried;
the query module 17 is configured to query, in the smart television device storage table, smart television devices that are consistent with the device identifier of the smart television device to be queried, which is obtained by the obtaining module 11;
a determining module 18, configured to determine, if the smart television device that is consistent with the device identifier of the smart television device to be queried is queried by the querying module 17, the number of audiences corresponding to the request time of the device audience query request based on the queried audience crowd attribute feature information corresponding to the smart television device.
Here, the user terminal may be a mobile terminal, a network device, a computer device, etc., which is not limited in this application; the device audience query request carries the device identifier of the smart television device which the user side needs to query.
In the specific implementation process, after the device identifier of the intelligent television device to be queried is obtained, the intelligent television device consistent with the device identifier of the intelligent television device to be queried is queried in an updated intelligent television device storage table, if the device identifier of the intelligent television device to be queried is queried, a playing time period consistent with the request time of the device audience query request is obtained from a playing time period in the audience population attribute feature information corresponding to the intelligent television device to be queried, the number of audiences corresponding to the playing time period is taken as the number of audiences corresponding to the request time of the device audience query request, if the intelligent television device storage table does not contain the device identifier of the intelligent television device to be queried, the audience attribute feature information of the intelligent television device to be queried can be obtained through prediction of a device audience population prediction model, the average value of the number of the audiences of the area to which the intelligent television device to be inquired belongs and corresponding to the request time can also be used as the number of the audiences corresponding to the intelligent television device to be inquired.
For example, the device identifiers stored in the storage table of the smart television device include A, B, the playing time periods in the attribute feature information of the audience population corresponding to the smart television device a include S1-S2, S3-S4 and S5-S6, the audience numbers corresponding to the three playing time periods are Q10, Q20 and Q30 respectively, the playing time periods in the attribute feature information of the audience population corresponding to the smart television device B include S1-S2, S3-S4 and S5-S6, the audience numbers corresponding to the three playing time periods are Q11, Q21 and Q31 respectively, and if the received device identifier of the smart television device to be queried is a and the request time falls between S3 and S4, the number of the audience numbers corresponding to the smart television device to be queried is determined to be Q20.
The device for information pushing provided by the embodiment of the application acquires the device identification used for acquiring the intelligent television device to be identified and generates the device behavior characteristic information for the intelligent television device to be identified, inputs the device identification and the device behavior characteristic information of the intelligent television device to be identified into the preset device audience population prediction model, and predicts the audience population attribute characteristic information corresponding to the intelligent television device to be identified, so that the accuracy of the obtained audience population attribute characteristic information is improved, and the application accuracy of the obtained audience population attribute characteristic information is also improved.
An embodiment of the present application provides an information pushing method, as shown in fig. 4, the method includes the following steps:
s401, acquiring a device identifier of the intelligent television device to be identified;
s402, generating equipment behavior characteristic information for the intelligent television equipment to be identified;
s403, inputting the device identification and the device behavior characteristic information of the intelligent television device to be identified into a preset device audience crowd prediction model to obtain audience crowd attribute characteristic information corresponding to the intelligent television device to be identified;
and S404, sending the obtained audience population attribute feature information to an information processing terminal.
Optionally, the device audience crowd prediction model is trained according to the following steps:
constructing a training sample library, wherein the training sample library comprises equipment identification of sample intelligent television equipment and corresponding artificially labeled sample audience crowd attribute characteristic information;
and taking the device identification of the sample intelligent television device and the corresponding device behavior characteristic information as the input characteristics of the device audience crowd prediction model, taking the corresponding sample audience crowd attribute characteristic information as the output characteristics of the device audience crowd prediction model, and training to obtain the device audience crowd prediction model.
Optionally, the method for predicting the audience population of the device includes training, by taking the device identifier of the sample smart television device and the corresponding device behavior feature information as input features of the device audience population prediction model, taking corresponding sample audience population attribute feature information as output features of the device audience population prediction model, to obtain the device audience population prediction model, and includes:
inputting the device identification of the sample intelligent television device and the corresponding device behavior characteristic information into an initial device audience crowd prediction model to obtain predicted sample audience crowd attribute characteristic information;
comparing the predicted sample audience crowd attribute feature information with the manually marked sample audience crowd attribute feature information to obtain a comparison error;
and adjusting the model parameters of the initial equipment audience crowd prediction model according to the principle of minimizing the comparison error to obtain the adjusted equipment audience crowd prediction model.
Optionally, after obtaining the attribute feature information of the audience crowd of the smart television device to be identified, the method further includes:
and updating a storage table of the intelligent television equipment by using the equipment identification of the intelligent television equipment to be identified and the corresponding audience crowd attribute characteristic information.
Optionally, after the storage table of the smart television device is updated, the method further includes:
receiving an equipment audience query request of a user side, wherein the query request carries an equipment identifier of the intelligent television equipment to be queried;
inquiring the intelligent television equipment consistent with the equipment identification of the intelligent television equipment to be inquired in the intelligent television equipment storage table;
and if the intelligent television equipment consistent with the equipment identification of the intelligent television equipment to be inquired is inquired, determining the audience number corresponding to the request time of the equipment audience inquiry request based on the inquired audience population attribute characteristic information corresponding to the intelligent television equipment.
Corresponding to the information pushing method in fig. 4, an embodiment of the present application further provides a computer device 500, as shown in fig. 5, the device includes a memory 501, a processor 502, and a computer program stored on the memory 501 and executable on the processor 502, where the processor 502 implements the information pushing method when executing the computer program.
In particular, the memory 501 and the processor 502 can be general-purpose memory and processor, which are not limited in particular, when the processor 502 executes the computer program stored in the memory 501, the above-described information push method can be performed, therefore, the problem of low accuracy of the attribute characteristic information of the audience population of the intelligent television equipment in the prior art is solved, and after the equipment identification for acquiring the intelligent television equipment to be identified and the equipment behavior characteristic information generated for the intelligent television equipment to be identified are acquired, inputting the device identification and the device behavior characteristic information of the intelligent television device to be identified into a preset device audience crowd prediction model, predicting to obtain audience crowd attribute characteristic information corresponding to the intelligent television device to be identified, therefore, the accuracy of the obtained audience crowd attribute characteristic information is improved, and the application accuracy of the obtained audience crowd attribute characteristic information is also improved.
Corresponding to the information pushing method in fig. 4, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the information pushing method.
In particular, the storage medium can be a general-purpose storage medium, such as a removable disk, a hard disk, etc., and when the computer program on the storage medium is executed, the above-mentioned information push method can be executed, therefore, the problem of low accuracy of the attribute characteristic information of the audience population of the intelligent television equipment in the prior art is solved, and after the equipment identification for acquiring the intelligent television equipment to be identified and the equipment behavior characteristic information generated for the intelligent television equipment to be identified are acquired, inputting the device identification and the device behavior characteristic information of the intelligent television device to be identified into a preset device audience crowd prediction model, predicting to obtain audience crowd attribute characteristic information corresponding to the intelligent television device to be identified, therefore, the accuracy of the obtained audience crowd attribute characteristic information is improved, and the application accuracy of the obtained audience crowd attribute characteristic information is also improved.
In the embodiments provided in the present application, it should be understood that the disclosed system and method may be implemented in other ways. The above-described system embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and there may be other divisions in actual implementation, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of systems or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus once an item is defined in one figure, it need not be further defined and explained in subsequent figures, and moreover, the terms "first", "second", "third", etc. are used merely to distinguish one description from another and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope disclosed in the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the present disclosure, which should be construed in light of the above teachings. Are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (6)

1. An information pushing device, characterized in that the device comprises:
the acquisition module is used for acquiring the equipment identifier of the intelligent television equipment to be identified;
the generating module is used for generating equipment behavior characteristic information for the intelligent television equipment to be identified;
the prediction module is used for inputting the device identifier of the intelligent television device to be identified, which is acquired by the acquisition module, and the device behavior characteristic information generated by the generation module into a preset device audience crowd prediction model to obtain audience crowd attribute characteristic information corresponding to the intelligent television device to be identified; wherein the audience crowd attribute feature information comprises: family member composition, member gender, member age, member scholarship, member income, member watching time, playing time period and member watching program type;
the pushing module is used for sending the audience crowd attribute characteristic information obtained by the predicting module to an information processing end;
the device also includes: an update module to:
updating a storage table of the intelligent television equipment by using the equipment identification of the intelligent television equipment to be identified and the corresponding audience crowd attribute characteristic information;
the device also includes: the acquisition module is further used for:
acquiring a query request of a device audience of a user side, wherein the query request carries a device identifier of the intelligent television device to be queried;
the query module is used for querying the smart television equipment which is consistent with the equipment identifier of the smart television equipment to be queried, which is acquired by the acquisition module, in the smart television equipment storage table;
the determining module is used for acquiring a playing time period consistent with the request time of the equipment audience query request based on the searched playing time period in the audience population attribute characteristic information corresponding to the intelligent television equipment if the intelligent television equipment consistent with the equipment identification of the intelligent television equipment to be queried is searched by the searching module, and taking the number of the audiences corresponding to the playing time period as the number of the audiences corresponding to the request time of the equipment audience query request.
2. The apparatus of claim 1, further comprising: a training module to:
constructing a training sample library, wherein the training sample library comprises equipment identification of sample intelligent television equipment and corresponding artificially labeled sample audience crowd attribute characteristic information;
and taking the device identification of the sample intelligent television device and the corresponding device behavior characteristic information as the input characteristics of the device audience crowd prediction model, taking the corresponding sample audience crowd attribute characteristic information as the output characteristics of the device audience crowd prediction model, and training to obtain the device audience crowd prediction model.
3. The apparatus of claim 2, wherein the training module is specifically configured to:
inputting the device identification of the sample intelligent television device and the corresponding device behavior characteristic information into an initial device audience crowd prediction model to obtain predicted sample audience crowd attribute characteristic information;
comparing the predicted sample audience crowd attribute feature information with the manually marked sample audience crowd attribute feature information to obtain a comparison error;
and adjusting the model parameters of the initial equipment audience crowd prediction model according to the principle of minimizing the comparison error to obtain the adjusted equipment audience crowd prediction model.
4. A method for pushing information, the method comprising:
acquiring a device identifier of the intelligent television device to be identified;
generating equipment behavior characteristic information for the intelligent television equipment to be identified;
inputting the device identification and the device behavior characteristic information of the intelligent television device to be identified into a preset device audience crowd prediction model to obtain audience crowd attribute characteristic information corresponding to the intelligent television device to be identified; wherein the audience crowd attribute feature information comprises: family member composition, member gender, member age, member scholarship, member income, member watching time, playing time period and member watching program type;
sending the obtained audience crowd attribute characteristic information to an information processing end;
after the attribute characteristic information of the audience crowd corresponding to the intelligent television equipment to be identified is obtained, the method further comprises the following steps:
updating a storage table of the intelligent television equipment by using the equipment identification of the intelligent television equipment to be identified and the corresponding audience crowd attribute characteristic information;
after the storage table of the intelligent television device is updated, the method further comprises the following steps:
receiving an equipment audience query request of a user side, wherein the query request carries an equipment identifier of the intelligent television equipment to be queried;
inquiring the intelligent television equipment consistent with the equipment identification of the intelligent television equipment to be inquired in the intelligent television equipment storage table;
if the intelligent television equipment which is consistent with the equipment identification of the intelligent television equipment to be inquired is inquired, acquiring a playing time period which is consistent with the request time of the equipment audience inquiry request based on the inquired playing time period in the audience population attribute characteristic information corresponding to the intelligent television equipment, and taking the number of the audiences corresponding to the playing time period as the number of the audiences corresponding to the request time of the equipment audience inquiry request.
5. An electronic device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating via the bus when the electronic device is operating, the processor executing the machine-readable instructions to perform the steps of the method of claim 4.
6. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method as set forth in claim 4.
CN201910353015.9A 2019-04-29 2019-04-29 Information pushing device and method, electronic equipment and computer readable storage medium Active CN110087104B (en)

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 CN110087104A (en) 2019-08-02
CN110087104B true 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)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7806329B2 (en) * 2006-10-17 2010-10-05 Google Inc. Targeted video advertising
US20080250450A1 (en) * 2007-04-06 2008-10-09 Adisn, Inc. Systems and methods for targeted advertising
CN104702981B (en) * 2013-12-06 2018-09-11 秒针信息技术有限公司 A kind of method and system calculating DTV target audience
CN105208411B (en) * 2014-06-05 2018-09-07 北京秒针信息咨询有限公司 A kind of method and device for realizing DTV target audience statistics
CN108352025B (en) * 2015-07-24 2022-10-11 安普视频有限公司 Television advertisement slot targeting based on consumer online behavior
CN105959745B (en) * 2016-05-25 2019-10-22 北京铭嘉实咨询有限公司 Advertisement placement 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

Also Published As

Publication number Publication date
CN110087104A (en) 2019-08-02

Similar Documents

Publication Publication Date Title
CN105245958B (en) Live television program recommendation method and device
CN109074593B (en) Information processing device, information processing method, information processing system, and program
CN106792242B (en) Method and device for pushing information
CN107968952B (en) Method, device, server and computer-readable storage medium for recommending videos
KR102068790B1 (en) Estimating and displaying social interest in time-based media
CN106326391B (en) Multimedia resource recommendation method and device
CN108563670B (en) Video recommendation method and device, server and computer-readable storage medium
WO2017041532A1 (en) Information pushing method and device
CN108596690B (en) Advertisement processing method and device
CN109429103B (en) Method and device for recommending information, computer readable storage medium and terminal equipment
CN106202393B (en) Media information pushing method and device
CN111125497A (en) Information recommendation method, device, processor and storage medium
CN104967690A (en) Information push method and device
CN106792001B (en) Advertisement operation method and system for smart television
CN111046292A (en) Live broadcast recommendation method and device, computer-readable storage medium and electronic device
JP2019092067A (en) Information processing apparatus, information processing method, information processing system, and program
CN106960033B (en) Method and device for labeling information stream
CN113127723B (en) User portrait processing method, device, server and storage medium
CN110381378B (en) Estimation method, device, server and storage medium of network multimedia playing amount
CN105956061B (en) Method and device for determining similarity between users
CN110087104B (en) Information pushing device and method, electronic equipment and computer readable storage medium
CN110110206B (en) Method, device, computing equipment and storage medium for mining and recommending relationships among articles
CN112770126A (en) Live broadcast room pushing method and device, server and storage medium
JP6953643B1 (en) Equipment, methods and programs for evaluating the effects of TV commercials
CN111669654B (en) Program recommendation method and device, electronic equipment and readable 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