CN116095409A - Audience data analysis method and electronic equipment - Google Patents
Audience data analysis method and electronic equipment Download PDFInfo
- Publication number
- CN116095409A CN116095409A CN202310368527.9A CN202310368527A CN116095409A CN 116095409 A CN116095409 A CN 116095409A CN 202310368527 A CN202310368527 A CN 202310368527A CN 116095409 A CN116095409 A CN 116095409A
- Authority
- CN
- China
- Prior art keywords
- viewing
- user
- data
- channel
- target
- 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
Images
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]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44222—Analytics of user selections, e.g. selection of programs or purchase activity
-
- 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
- H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The application relates to a viewing data analysis method and electronic equipment. The viewing data analysis method comprises the following steps: obtaining a plurality of viewing data; for each piece of viewing data, disassembling the viewing data to obtain three-dimensional decomposition data of the viewing data, wherein the three-dimensional decomposition data comprises user identifications, viewing channels and viewing moments; establishing a graphical three-dimensional data model according to the three-dimensional decomposition data of the plurality of viewing data; receiving an input of a user; generating and displaying a target data slice from the three-dimensional data model in response to the input; analyzing the target data slice to obtain target information; the target information comprises at least one of preference information of users on viewing channels, preference information of users on viewing moments, user group distribution information of viewing channels, viewing curve information of viewing channels, instant viewing distribution information of viewing channels and instant viewing distribution information of user groups.
Description
Technical Field
The embodiment of the application relates to the technical field of audience data analysis, in particular to an audience data analysis method and electronic equipment.
Background
In recent years, developments in mobile multimedia broadcasting technology and enhancement of service functions provide users with rich video services, audio services, and data services. The service has rich content and novel form, and provides a good leisure and entertainment platform for multimedia users.
With the progress of technology, the statistical methods of viewing behavior data based on big data technology are increasing. The conventional big data audience rating analysis method is used for directly counting audience rating indexes based on user audience rating behaviors, and the analysis dimension is relatively single.
However, as the number of multimedia users increases, how to accurately understand behavior data of the multimedia users when using multimedia, so as to determine preference demands of the users according to the behavior data, becomes a very important issue for a wide range of multimedia operators.
Disclosure of Invention
An object of the embodiments of the present application is to provide a viewing data analysis method and a new technical solution of an electronic device.
According to a first aspect of the present application, there is provided a viewing data analysis method, the method comprising: obtaining a plurality of viewing data; for each viewing data, disassembling the viewing data to obtain three-dimensional decomposition data of the viewing data, wherein the three-dimensional decomposition data comprises a user identifier, a viewing channel and a viewing time; establishing a graphical three-dimensional data model according to the three-dimensional decomposition data of a plurality of the viewing data; receiving an input of a user; generating and displaying a target data slice from the three-dimensional data model in response to the input; analyzing the target data slice to obtain target information; the target information comprises at least one of preference information of users on viewing channels, preference information of users on viewing moments, user group distribution information of viewing channels, viewing curve information of viewing channels, instant viewing distribution information of viewing channels and instant viewing distribution information of user groups.
According to a second aspect of the present application, there is also provided an electronic device comprising a memory for storing a computer program and a processor; the processor is configured to execute the computer program to implement the method according to the first aspect of the present application.
According to a third aspect of the present application there is also provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method according to the first aspect of the present application.
The method has the advantages that a three-dimensional data model is built according to a plurality of viewing data, the three-dimensional data model is sliced according to the input of users to the three-dimensional data model, target data slices are obtained, preference information of users to viewing channels, preference information of users to viewing moments, user group distribution information of viewing channels, viewing curve information of viewing channels, instantaneous viewing distribution information of viewing channels and instantaneous viewing distribution information of user groups can be obtained through flexible and efficient analysis of the target data slices, analysis dimension of the viewing data is effectively expanded, and the analysis method is simple and efficient; meanwhile, through multidimensional audience data analysis, the method can provide fine data support for content production, arrangement and delivery for a program content production mechanism, a program content broadcasting mechanism, an advertisement delivery mechanism and the like, so that the content quality and the economic value of broadcast television programs are improved.
Other features of embodiments of the present application and their advantages will become apparent from the following detailed description of exemplary embodiments of the present application with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description, serve to explain the principles of the embodiments of the application.
Fig. 1 is a flow chart of a viewing data analysis method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a three-dimensional data model provided by an embodiment of the present application;
FIG. 3 is one of the schematic diagrams of a first target data slice provided in an embodiment of the present application;
FIG. 4 is a second schematic diagram of a first target data slice according to an embodiment of the present application
FIG. 5 is a schematic diagram of user preference information for viewing channels provided by embodiments of the present application;
FIG. 6 is a schematic diagram of preference information of users for viewing moments provided in an embodiment of the present application;
FIG. 7 is a schematic diagram of a second target data slice provided by an embodiment of the present application;
fig. 8 is a schematic diagram of user group distribution information of viewing channels according to an embodiment of the present application;
FIG. 9 is a schematic diagram of viewing curve information of viewing channels provided by embodiments of the present application;
FIG. 10 is a second schematic diagram of viewing curve information for viewing channels provided in accordance with an embodiment of the present application;
FIG. 11 is a schematic diagram of a third target data slice provided by an embodiment of the present application;
FIG. 12 is a schematic diagram of data deduplication provided by embodiments of the present application;
FIG. 13 is a schematic diagram of instantaneous viewing distribution information for viewing channels provided by embodiments of the present application;
FIG. 14 is a schematic diagram of instant view distribution information of a user group provided in an embodiment of the present application;
fig. 15 is a schematic structural diagram of an audience data analysis apparatus according to an embodiment of the present application.
Detailed Description
Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless it is specifically stated otherwise.
The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the invention, its application, or uses.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of exemplary embodiments may have different values.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.
< method example >
The following describes in detail the viewing data analysis method provided in the embodiment of the present application through specific embodiments and application scenarios thereof with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a viewing data analysis method according to an embodiment of the present application. The viewing data analysis method may include steps 110 to 160.
In the present embodiment, viewing data may be acquired by various existing viewing data acquisition methods, which is not particularly limited in the present embodiment.
In this embodiment, the plurality of viewing data includes viewing data of users of different ages and different areas.
And 120, for each viewing data, disassembling the viewing data to obtain three-dimensional decomposition data of the viewing data, wherein the three-dimensional decomposition data comprises a user identifier, a viewing channel and a viewing time.
In this embodiment, when a plurality of viewing data are acquired, data cleansing and data conversion are performed on each of the plurality of viewing data, respectively, to obtain structured viewing data, and the structured viewing data is stored in a Hive data warehouse of a large data platform.
In this embodiment, each of the viewing data stored in the Hive data storeComprising at least a user identity of a userViewing channel for user to watch>User watching viewing channel->Viewing start time->And user watching viewing channel->Viewing end time->Wherein, viewing the viewing channel according to the user +.>Viewing start time->And user watching viewing channel->Viewing end time->The user can watch the viewing channelIs a viewing duration of (a).
In this embodiment, the same user can watch only one viewing channel at any time, and the same user can watch different viewing channels at different times, or watch the same viewing channel at different viewing times.
And 130, building a graphical three-dimensional data model according to the three-dimensional decomposition data of the plurality of viewing data.
In this embodiment, a graphical three-dimensional data model is created from three-dimensional decomposition data of a plurality of viewing data, and a slicing tool and an analysis tool associated with the three-dimensional data model are generated.
In step 140, input from a user is received.
In the present embodiment, the input is used to generate and display a target data slice, wherein the target data slice is any one of a first target data slice, a second target data slice, or a third target data slice.
In this embodiment, the input includes a first sub-input and a second sub-input, where the first sub-input and the second sub-input may be respectively a click input of the slicing tool by the data analyzer, or a voice command input by the data analyzer, or a specific gesture input by the data analyzer, and may be determined according to an actual use requirement in practical application, and this embodiment is not limited specifically.
In this embodiment, the first sub-input may be a click operation of the slicing tool by the data analyst, and the second sub-input may be an input operation of the target control by the data analyst.
In response to the input, a target data slice is generated and displayed according to the three-dimensional data model, step 150.
In the embodiment, in the case that the first sub-input is a clicking operation of the slicing tool by a data analyzer, a target control is displayed on a display interface in response to the first sub-input; and under the condition that the second sub-input is the input operation of the data analyzer on the target control, responding to the second sub-input, inputting the target parameter in the target control, and generating and displaying a target data slice corresponding to the target parameter according to the target parameter and the three-dimensional data model.
In this embodiment, the target control is used for the data analyst to input target parameters. For example, after acquiring the first user identifier corresponding to the first userIn the case of the corresponding first target data slice, the target parameter is +.>The data analyst inputs +_ in the target control>And obtaining a first target data slice corresponding to the first user.
In this embodiment, the data analyzer may analyze the first target data slice through an analysis tool, so as to obtain preference information of the user for viewing channels and preference information of the user for viewing moments; the data analyzer analyzes the second target data slice through an analysis tool, so that user group distribution information of the viewing channels and viewing curve information of the viewing channels can be obtained; the data analyzer analyzes the third target data slice through an analysis tool to obtain instantaneous viewing distribution information of the viewing channels and instantaneous viewing distribution information of the user group.
In the embodiment of the application, a three-dimensional data model is built according to a plurality of viewing data, the three-dimensional data model is sliced according to the input of a user to the three-dimensional data model, a target data slice is obtained, preference information of the user to the viewing channels, preference information of the user to the viewing moment, user group distribution information of the viewing channels, viewing curve information of the viewing channels, instantaneous viewing distribution information of the viewing channels and instantaneous viewing distribution information of the user groups can be obtained through flexible and efficient analysis of the target data slice, the analysis dimension of the viewing data is effectively expanded, and the analysis method is simple and efficient; meanwhile, through multidimensional audience data analysis, the method can provide fine data support for content production, arrangement and delivery for a program content production mechanism, a program content broadcasting mechanism, an advertisement delivery mechanism and the like, so that the content quality and the economic value of broadcast television programs are improved.
In one embodiment, building a graphical three-dimensional data model from three-dimensional decomposition data includes: and establishing a graphical three-dimensional data model according to the three-dimensional decomposition data by taking the user identification of the viewing data as a first dimension, the viewing channel of the viewing data as a second dimension and the viewing time of the viewing data as a third dimension. The first dimension and the second dimension form a first preset plane, the second dimension and the third dimension form a second preset plane, and the first dimension and the third dimension form a third preset plane.
In this embodiment, for the first user identificationThe corresponding first user's collection of viewing behaviors for the first user may be expressed as equation one:
Wherein, in the formula one,and->For representing different viewing channels +.>,/>.../>Respectively for indicating the first user watching viewing channel +.>Viewing start time of->,.../>Respectively for indicating the first user watching viewing channel +.>At the time of the end of the viewing of the (c),,/>.../>respectively for indicating the first user watching viewing channel +.>Viewing start time of->,/>.../>Respectively for indicating the first user watching viewing channel +.>Is a viewing end time of (c).
Using viewing channel as independent dimension, first user identificationPerforming two-dimensional processing on the corresponding set of viewing behaviors of the first user to obtain a formula II:
For the first user identificationCorresponding first user, using viewing channel and viewing time as two dimensions, establishing a two-dimensional data structure of first user +.>,/>Called first user identification +.>And the viewing behavior plane of the corresponding first user. In the interval of +.>All channels within the time period of (2)>In traversing allFor the first user identification +.>Viewing behavior plane of the corresponding first user +.>The assignment is performed according to the following rules:
By user identificationViewing channel->And viewing time->Three dimensions, a three-dimensional data structure is establishedThree-dimensional data structure->Namely a three-dimensional data model. Three-dimensional data modelBy all viewing behavior planes->The composition is as follows: />Thus, for all users +.>Three-dimensional data model->The assignment rule of (2) is:
in the present embodiment of the present invention, in the present embodiment,is a three-dimensional sparse matrix with non-zero values of 1.
For example, as shown in Table 1, table 1 builds a three-dimensional data model from the viewing data in Table 1 for a plurality of viewing data obtainedIn the case of (1), processing the viewing data in table 1 to obtain three-dimensional decomposition data in table 2, and creating an imaged three-dimensional data model based on the three-dimensional decomposition data in table 2>。
TABLE 1
TABLE 2
In this embodiment, it should be noted that the data analyzer may identify the user according to its own usage habitViewing channel->And viewing time->Respectively as three partsThe x-axis, y-axis, and z-axis of the dimensional coordinate system. The present embodiment is not particularly limited thereto.
For example, as shown in FIG. 2, the data analyst may compare the viewing timeAs the x-axis of the three-dimensional coordinate system (third dimension of the three-dimensional data model), the viewing channel +. >Y-axis as three-dimensional coordinate system (second dimension of three-dimensional data model), and user identification +.>As the z-axis of the three-dimensional coordinate system (the first dimension of the three-dimensional data model).
For another example, the data analyst may identify the userAs x-axis of three-dimensional coordinate system, viewing channel +.>As y-axis of three-dimensional coordinate system, and viewing time +.>As the z-axis of the three-dimensional coordinate system.
In this embodiment, in order to improve analysis processing efficiency of viewing data, a three-dimensional data model is constructed to facilitate subsequent multidimensional statistical analysis of target data slicesThe x, y and z axes of the three-dimensional coordinate system are organized and arranged as follows: in the x-axis (viewing moment->) Sequentially arranging according to time sequence in the direction; in the y-axis (viewing channel->) In the direction, dividing according to the viewing channel groups, and storing data in the same viewing channel group in a centralized manner; in the z-axis (user identification +.>) In the direction, the data are divided according to the region to which the user belongs, and the data are stored in the same region in a concentrated manner.
In this embodiment, the viewing channel group is divided according to a satellite channel group and a ground channel group, the satellite channel group is divided according to a central viewing channel, a local satellite channel, a satellite television professional channel, other satellite channels, and the like, and the ground channel group is divided according to a region (two levels of province and city and county).
In this embodiment, the satellite channel is a television channel for transmitting and retransmitting a television program by using a communication satellite, and the television program is transmitted from a certain ground station to the communication satellite and then retransmitted to other ground stations, and the other ground stations receive signals and then transmit the signals to a local television station for retransmission.
In this embodiment, the ground channel, which is also called a common channel, belongs to regional media, and the signal is transmitted by the transmitting tower, has limited power, can only be watched in the city or nearby, and is transmitted by laying optical fibers on the ground.
In this embodiment, the user identification is displayed in the z-axis (user identification) In the direction, when dividing the region to which the user belongs, the region to which the user belongs (province, city, county, two levels) is divided.
In this embodiment, channels that a user can view are of two types: one is a satellite channel and the other is a terrestrial channel in the area to which the user belongs. Thus, the y-axis (viewing channel) The behavior of the user in the direction will only exist in these two areas.
For example, as shown in fig. 3, the area to which the first user corresponding to the first target data slice belongs is region D, and thus, the viewing data of the first user is concentrated on the satellite channel group and region D channel group (hatched portion in the figure). Therefore, when the data slice of the user is further analyzed and processed, compared with the randomly scattered data, the specific area is limited, so that the processing efficiency is greatly improved.
In one embodiment, the input is used to indicate that a first target data slice corresponding to a first user identification is generated. Step 150, in response to the input, generating and displaying a target data slice from the three-dimensional data model, comprising: and responding to the input, carrying out slicing processing on a first plane corresponding to the first user identification in the three-dimensional data model, and generating and displaying a first target data slice. The first plane and the second preset plane are arranged in parallel, and the first target data slice comprises at least one viewing channel and at least one viewing moment corresponding to the first user identification in the three-dimensional data model.
In this embodiment, the first user identification is entered for the data analyst to the target control at the second sub-inputIn response to the second sub-input, a three-dimensional data model is +.>Is +.>Slicing the corresponding first plane to obtain a first user identifier +.>Data slice of corresponding first userData slice of the first user +.>I.e. the first target data slice. Wherein the first target data slice->With the z-axis (user identification +.>) Crossing of->Representing a first target data slice->Belonging to the first user.
In this embodiment, for the first user identificationCorresponding first user, in three-dimensional data modelCondition->Performing data query to obtain data set +.>Namely, a first target data slice corresponding to the first user.
As shown in fig. 4, in this embodiment, the first target data slice depicts a trace of the viewing behavior of the first user between the viewing channels, and the viewing channel preference or viewing time preference of the first user may be further analyzed by superposition on the viewing time or viewing channel dimension. At the first target data sliceIn (a) for a unique viewing moment->Viewing channel corresponding to the same>At most only one, indicating that the first user is only at one viewing timeA viewing channel may be viewed; for a single viewing channel +.>Viewing time corresponding to the above>There may be multiple, meaning that the first user may view the same viewing channel at multiple different viewing moments.
In the present embodiment, the viewing time is shown on the x-axis (viewing time) In the direction, the value of y is continuous, which means that the viewing behavior of the user is generally continuous in time; conversely, in the y-axis (viewing channel +.>) In the direction, the value of x is generally discrete.
For example, in the three-dimensional decomposition data shown in table 2, for the userIn->Medium conditionThe data query is carried out, and the obtained data set is the user +.>As shown in table 3.
TABLE 3 Table 3
In one embodiment, step 160, analyzing the target data slice to obtain target information includes: calculating a sum value of first viewing moments corresponding to the video receiving channels in a first preset time period for each viewing channel in at least one viewing channel to obtain first viewing duration; the first viewing duration is the total viewing duration of the first user on the viewing channel in a first preset time period; and obtaining preference information of the first user for the viewing channel in a first preset time period according to the first viewing time period.
In this embodiment, a first target data slice based on a first userThe preference information for the viewing channel of the first user may be analyzed. For the first target data slice->Any one of the plurality of viewing channels of (a) is regarded as a specific viewing channel +.>In the first target data slice +.>Get->Obtain->,/>Representing the first user identity +.>Corresponding first user is in the specific viewing channel +. >A set of viewing behaviors on the display. Selecting a first preset time period +.>The first user is in the specific viewing channel +.>The calculation formula of the first viewing time length is shown as a formula III:
In the third formula of the present invention,representing the first user identity +.>The corresponding first user is +_ for a first preset period of time>Go up to the specific viewing channel->Is a preference for (a); />Representing from->Data on plane->Accumulating the axes; />Representing a starting time of a first preset time period; />Indicating the end time of the first preset time period.
In this embodiment, a first user identifier within a first preset time period is calculatedCorresponding first user is in the specific viewing channel +.>The physical meaning of the first viewing duration is: representing +.>Is added to the viewing data analysis system of (1) for a first predetermined period of time>The first user is in the specific viewing channel +.>The total viewing length (i.e. the first viewing length) is +.>Or watch->A minimum time unit.
As shown in fig. 5, in this embodiment, for all viewing channelsCalculate each +.>A kind of electronic deviceThe result set is the first user mark +.>The corresponding first user is in a first preset time period Viewing duration of each viewing channel, wherein +.>The larger the value of (a) indicates that the user is +.>The stronger the degree of preference.
For example, the user shown in Table 3Is analyzed to obtain the user +.>Preference information for each viewing channel as shown in table 4; and based on the data in table 4, user +.>Viewing channel CH002 is more preferred for a first preset period of time.
TABLE 4 Table 4
In one embodiment, step 160, analyzing the target data slice to obtain target information includes: dividing a second preset time period according to preset time intervals to obtain n time intervals, wherein n is a positive integer, and n is more than or equal to 1; dividing any one of n time intervals into a plurality of target viewing moments; calculating the sum of the viewing moments of the first user viewing the viewing channels at the target viewing moment in n time intervals aiming at each target viewing moment to obtain a second duration, wherein the second duration is the total viewing duration of the first user viewing the viewing channels at the target viewing moment in a second preset time period; and obtaining preference information of the first user for the target viewing moment in a second preset time period according to the second time period.
In this embodiment, a first target data slice based on a first userPreference information for viewing moments of the first user may be analyzed. In the first object data slice->Is the time of viewing by the user of (a)In the case of analyzing preference information of (a) by performing segmentation at preset time intervals (preset time intervals are a fixed period, such as 1 day) over a second preset time period (the second preset time period is a natural period, such as a week, a month, etc.), obtaining ++>To->A total of n time intervals. To->Representing the relative time in the time interval (for example, the period is day, the relative time of time 2021-05-01 13:12:11 in 1 day is 13:12:11), for a particular viewing time +.>Calculating the first user identification +.>Corresponding first user is +.>A second time period for watching any viewing channel, the calculation formula of which is shown as a formula four,
In the fourth formula of the present invention,representing the first user identity +.>Corresponding first user to specific viewing timeIs a preference for (a); />Representing from->Accumulating the data on the plane to the X axis; />Indicating the first user's +.>A set of viewing behaviors on the display.
In this embodiment, the second preset time period and the preset time interval may be set by the data analyzer, which is not limited in particular.
In this embodiment, equation four represents the accumulated value of viewing times for all viewing channels viewed by the user at a selected viewing time (e.g., 13:12:11) for a second predetermined time period (e.g., 1 week) at a selected viewing time (e.g., 13:12:11) for a selected predetermined time interval (e.g., 1 day). In the actual calculation process, as can be seen from the above description, in the first target data sliceIn (a) for a unique viewing moment->Viewing channel corresponding to the same>At most, there is only one, meaning that the first user is only likely to view one viewing channel at one viewing time. Therefore, in the cumulative calculation of the fourth formula, the fourth formula may be simplified to the fifth formula without considering the viewing channel watched by the first user.
As shown in fig. 6, in the present embodiment, for each time within the second preset time periodCalculate->The obtained result set is preference information of the first user for each viewing moment in a second preset time period, wherein,the larger the value of (c) indicates the stronger the preference of the first user for the viewing moment in the second preset time period.
For example, the user shown in Table 3Is analyzed to obtain the user +.>For preference information at each viewing time, as shown in table 5, the present example requires multi-day data, assuming that the behavior data in table 3 occurs +.>And additionally have->、/>… … data, remaining day data at viewing time +.>The sum of the above is->The method comprises the steps of carrying out a first treatment on the surface of the Based on the data in table 5, the viewing preference of the user for the viewing time in the second preset period of time is in an ascending trend from 8:00 to 8:03.
TABLE 5
In one embodiment, the input is indicative of generating a second target data slice corresponding to the first viewing channel. Step 150, in response to the input, generating and displaying a target data slice from the three-dimensional data model, comprising: and in response to the input, slicing a second plane corresponding to the first viewing channel in the three-dimensional data model to generate and display a second target data slice. The second plane and the third preset plane are arranged in parallel, and the second target data slice comprises at least one user identifier and at least one viewing moment corresponding to the first viewing channel in the three-dimensional data model.
In this embodiment, the first viewing channel is entered for the target control by the data analyst at the second sub-input In response to the second sub-input, a three-dimensional data model is +.>First viewing channel of (a)Slicing the corresponding second plane to obtain data slice of the first viewing channel>Data slice of the first viewing channel +.>I.e. the second target data slice. Wherein the second target data slice->With y-axis (viewing channel->) Crossing of->Representing a second target data slice->Belonging to the first viewing channel.
For example, for a first viewing channelIn three-dimensional data model->Condition->Performing data query to obtain data set +.>Namely, the first viewing channel->A corresponding second target data slice.
As shown in FIG. 7, in this embodiment, the second target data slice depicts the first viewing channelThe time trend of the watching condition of each user or each user group can be further analyzed to obtain the user group distribution information of the watching channels and the watching curve information of the watching channels through superposition on watching time or user identification dimension. In the second target data slice->In (a) for a unique viewing moment->User identification corresponding to the same +.>There may be a plurality of the first viewing channel +. >At a viewing time->Possibly identified by multiple users +.>A plurality of corresponding users watch at the same time; for a unique user identifier +.>Viewing time corresponding to the above>There may be a plurality of them, indicating that a user may be at a plurality of different viewing moments +.>The same viewing channel is watched.
In the present embodiment, the viewing time is shown on the x-axis (viewing time) In the direction, the value of z is continuous, which means that the viewing behavior of the user is generally continuous in time; conversely, in the z-axis (viewing channel +.>) In the direction, the value of x is generally discrete.
For example, in the three-dimensional decomposition data shown in table 2, for viewing channelsIn->Condition->The data inquiry is carried out, and the obtained data set is the viewing channel +.>Is a data slice of (1), viewing channel->The data slices of (2) are shown in Table 6.
TABLE 6
In one embodiment, step 160, analyzing the target data slice to obtain target information includes: calculating the sum of the viewing moments of the user identifiers to the first viewing channels in a third preset time period for each user identifier in at least one user identifier to obtain a third duration, wherein the third duration is the total viewing duration of the user identifiers to the first viewing channels in the third preset time period; dividing at least one user identifier according to a first preset rule to obtain at least one first user group, wherein the first preset rule is one of a region to which the user identifier corresponds to a user, an age of the user identifier corresponds to the user and a gender of the user identifier corresponds to the user; calculating a sum of third time lengths of user identifiers in the first user groups in a third preset time period for each of at least one first user group to obtain a fourth time length; and obtaining the first user group distribution information of the first viewing channel in the third preset time period according to the fourth time period.
In this embodiment, the first viewing channel is based onSecond target data slice +.>The first viewing channel is available>Is a first user group distribution information. In the acquisition of the first viewing channel->In the case of the first user group distribution information for the second target data slice +.>Is->At the second target data sliceGet->Obtain->,/>Representing the first viewing channel->Is specified by the userA set of behaviors for viewing. Selecting a third preset time period +.>Then in a third preset time periodFirst viewing channel->Is (are) subject to special users>The calculation formula of the third time period is shown as formula six:
In the sixth of the formulas (a) to (b),representing the first viewing channel->In a third preset period of time +.>Is surrounded by special users>The total duration of viewing (i.e., the third duration); />Representing from Z->Accumulating the data on the plane to the Z axis; />Representing a starting time of a third preset time period; />Indicating the end time of the third preset time period.
In this embodiment, the data analyst is more concerned about the distribution of the user groups of viewing channels than the distribution of the individual users when analyzing the viewing data. According to the first preset rule, the second target data can be sliced Dividing all user identifications in the system to obtain +.>To->In total->A first group of users to->Any one of the first user groups +.>For example, for the group belonging to the first user group +.>Accumulating the third time lengths of all users to obtain a first user groupI.e. the fourth time period), wherein the first user group +.>The calculation formula of the viewing amount of (c) is shown as formula seven:
As shown in fig. 8, in the present embodiment, the slave is calculatedTo->In total->The viewing quantity of the first user group can obtain the first user group distribution information of the first viewing channel, and the larger the viewing quantity of the first user group is, the stronger the preference degree of the first user group for the first viewing channel is.
TABLE 7
Based on the data in Table 7, the user can see thatAnd user->For viewing channel->Is the same as the preference degree of the user->For viewing channel->Is most preferred.
If the user dimension data shown in table 8 is also present in the viewing data analysis system, viewing channels are viewed according to tables 7 and 8 Grouping users of (1) to obtain viewing channels +.>As shown in tables 9 and 10.
TABLE 8
TABLE 9
Table 10
In one embodiment, step 160, analyzing the target data slice to obtain target information includes: for each viewing time in at least one viewing time, calculating the number of user identifiers for viewing any viewing channel in the fourth preset time period at the viewing time to obtain the viewing total of the viewing time in the fourth preset time period; and obtaining the viewing curve information of the first viewing channel in the fourth preset time period according to the viewing total amount of each viewing moment in the fourth preset time period.
In this embodiment, the first viewing channel is based onSecond target data slice +.>The first viewing channel is available>Is a viewing curve information of the video camera. In the case of acquiring viewing curve information of the first viewing channel, in the second target data slice +.>In (1) for a specific viewing time>In the second target data slice +.>Middle fetchObtain->,/>Indicating +.>First viewing channel->Is then +.>First viewing channel->The calculation formula of the audience share of (2) is shown as a formula eight:
In the case of the formula eight,representing the first viewing channel->At a specific viewing time->Viewing total amount on the table,/>Representing accumulation of data from the XZ plane to the X axis; />Representing a user corpus.
As shown in fig. 9, in the present embodiment, for a selected fourth preset time periodCalculate each +.>Is->The result set is the first viewing channel +.>In a fourth preset time period +.>And a viewing curve. For minimum sampling interval +.>Viewing data analysis system of (1), in each ofFirst viewing channel->The total viewing time of (2) is +.>。
For example, viewing channels shown in Table 6Is analyzed to obtain viewing channelsViewing curve information, wherein the data in table 6 are subjected to inductive analysis to obtain table 11, and viewing channels +.>Is a schematic view of the viewing curve.
TABLE 11
In this embodiment, based on the viewing curve of the viewing channel, the common viewing indicators such as the viewing duration of the viewing channel, the viewing duration of the program, the viewing rate of the viewing channel, the viewing rate of the program, etc. may be obtained, and this process is a conventional method, which is not described in detail in this embodiment.
In one embodiment, a third target data slice is input indicating that a first viewing time corresponds to generation. Step 150, in response to the input, generating and displaying a target data slice from the three-dimensional data model, comprising: and responding to the input, slicing a third plane corresponding to the first viewing moment in the three-dimensional data model, and generating and displaying a third target data slice. The third plane is arranged in parallel with the first preset plane, and the third target data slice comprises at least one user identifier and at least one viewing channel corresponding to the first viewing moment in the three-dimensional data model.
In this embodiment, the second sub-input is the first viewing time of the data analyst's input of the target controlIn response to the second sub-input, a three-dimensional data model is +.>Is +.>Slicing the corresponding third plane to obtain first viewing time +.>Data slice +.>Data slice of the first viewing channel +.>I.e. the third target data slice. Wherein the third target data slice->With x-axis (viewing moment->) Crossing of->Representing a third target data slice->Belonging to the first viewing moment.
For example, for the first viewing momentIn->Condition->Performing data query to obtain data set +.>Namely, the first viewing time is->A corresponding third target data slice.
As shown in fig. 11, in the present embodiment, the third target data slice depicts the user identification of the first viewing momentAnd viewing channel->Further analysis may be performed to obtain instantaneous viewing distribution information for viewing channels at a first viewing time and instantaneous viewing distribution information for a group of users by stacking in a viewing channel or user identification dimension. In the third target data slice->In the above, for a unique user identification +. >Viewing channel corresponding to the same>Is unique in that it is possible for a user to view only one viewing channel at a first viewing time; for a single viewing channel +.>User identification corresponding to the same +.>There may be a plurality of the user identifiers indicating that a viewing channel may be marked by a plurality of the users at a viewing time>A corresponding plurality of users view simultaneously.
In this embodiment, the channel is viewed in the y-axis (viewing channel) And z-axis (user identification +.>) The values in both directions are discrete.
For example, in the three-dimensional decomposition data shown in table 2, the viewing time is 8:07Condition->The data query was performed and the resulting dataset was the data slice at viewing time 8:07, as shown in Table 12.
Table 12
In this embodiment, in the process of analyzing the viewing data, it is often necessary to perform deduplication on the user. Viewing big data model in three dimensionsIn the method, the effect of removing the duplication of the user can be achieved by continuously exposing the data slice corresponding to the specific moment.
As shown in fig. 12, for oneMinimum sampling interval isIs a viewing data analysis system of three users +.>,/>Andat viewing time->Viewing time- >On the data slice +.>And data slice->Leave->、/>、/>And->Four data points. Slicing data->And data slice->Performing OR operation to obtain new data slice +.>I.e. data slice->And data slicingThe user in (a) performs a temporal de-duplication operation (similar to a continuous "exposure" of the image of the user slice over time) to obtain a de-duplication result +.>,/>And->Data points for three users. By adopting the method, the de-duplication operation can be carried out on the target period by selecting the start-stop time of 'exposure' to obtain de-duplicated slice data.
For example, the viewing time period from the viewing time 8:05 to the viewing time 8:07 is taken as a target time period, and the data of the target time period in the three-dimensional decomposition data shown in table 2 is de-duplicated to obtain the data shown in table 13; the data in table 13 has been subjected to deduplication processing, and thus no data unique number is present.
TABLE 13
In one embodiment, step 160, analyzing the target data slice to obtain target information includes: for each viewing channel in at least one viewing channel, calculating the number of user identifiers of the viewing channels at the first viewing moment to obtain the viewing total number of the viewing channels at the first viewing moment; and obtaining the instantaneous audience distribution information of each audience channel at the first audience moment according to the audience quantity of each audience channel at the first audience moment.
In the present embodiment, the first viewing time is based onThird target data slice +.>Instantaneous viewing distribution information for each viewing channel at a first viewing time may be obtained. In the case of acquiring the instantaneous viewing distribution information of any viewing channel at the first viewing moment, the method for acquiring the instantaneous viewing distribution information of any viewing channel is similar to the method for acquiring the viewing curve information of the first viewing channel in the fourth preset time period, which is not described in detail in this embodiment.
In this embodiment, the difference between the "instantaneous viewing profile of each viewing channel at the first viewing time" and the "viewing profile of the first viewing channel in the fourth preset period" is that: the instantaneous viewing distribution of each viewing channel at the first viewing moment analyzes the viewing condition of each viewing channel, and the viewing curve of the first viewing channel in the fourth preset time period analyzes the viewing condition of each viewing moment.
In this embodiment, the point of "the instantaneous viewing profile of each viewing channel at the first viewing moment" is the same as "the viewing profile of the first viewing channel in the fourth preset period" is: the smallest units analyzed by both are the specific viewing channels at the specific viewing time.
In the present embodiment, at the first viewing timeSpecific viewing channel->The calculation formula of the audience share of (2) is shown as a formula nine:
In the ninth-order of the formula,representing a particular viewing channel->At the first viewing time->Total amount of viewing on; />Representing accumulation of data from the YZ plane to the Y-axis; />Representing the first viewing time +.>Go up specific viewing channel->Is a set of viewing behaviors; />Representing a user corpus.
As shown in fig. 13, in the present embodiment, for all viewing channelsCalculate each +.>Is->Obtaining instantaneous viewing distribution information of each viewing channel at the first viewing moment, and +.>The larger the calculation result of (c) means the longer the total viewing time period at this time.
For example, analysis of the data at viewing time 8:07 shown in table 12 yields instantaneous viewing distribution information for each viewing channel at viewing time 8:07, as shown in table 14, and in table 14, viewing channels at viewing time 8:07And viewing channel->The total viewing amount of (2) is the same.
TABLE 14
In one embodiment, step 160, analyzing the target data slice to obtain target information includes: dividing at least one user identifier according to a second preset rule to obtain at least one second user group, wherein the second preset rule is one of the region to which the user identifier corresponds to the user, the age of the user identifier corresponds to the user and the gender of the user identifier corresponds to the user; calculating the number of user identifiers for watching channels in the second user groups at the first watching time aiming at each second user group in at least one second user group to obtain the instantaneous watching quantity of the second user groups at the first watching time; and obtaining the instantaneous audience distribution information of the second user group at the first audience moment according to the instantaneous audience quantity of each second user group.
In the present embodiment, the first viewing time is based onThird target data slice +.>The instantaneous viewing distribution information of the second user group at the first viewing moment can be obtained. In the case of acquiring instantaneous viewing distribution information of a second user group at a first viewing moment, the user identification is +.>In the third target data slice +.>Middle fetchObtain->,/>Representing viewing channel->Is marked by the specific user->Corresponding set of user-viewed actions, then at first viewing moment +.>Specific user identification +.>The calculation formula of the viewing total amount of (2) is shown as formula ten:
In the formula ten, the formula is given,indicating +.>Top specific user identification +.>Is a viewing amount of (a); />Representing from Z->Accumulating the data on the plane to the Z axis; />Representing all viewing channels.
In this embodiment, when viewing data is analyzed, the data analyzer is more concerned about the distribution of user groups at the time of viewing than the distribution of individual users. Similar to the above-mentioned "user group distribution information of the first viewing channel in the third preset time period", the third target data may be sliced according to the second preset ruleDividing all user identifications in the list to obtain +.>To->In total- >A second user group for->Any one of the second user groups +.>For example, for the group belonging to the second user group +.>The number of all subscriber identities of the second subscriber group is accumulated to obtain +.>At the first viewing time->Instantaneous viewing volume on, wherein the second user group +.>At the first viewing time->The calculation formula of the instantaneous viewing amount is shown as formula eleven:
As shown in fig. 14, in the present embodiment, the slave is calculatedTo->A total of n second user groups at the first viewing timeThe instantaneous watching quantity can obtain the distribution condition of the second user group at the first watching time, and the larger the calculation result is, the stronger the preference degree of the second user group for the first watching time is.
For example, the data of viewing time 8:07 shown in table 12 is analyzed to obtain distribution information of each user at viewing time 8:07, as shown in table 15. If the user dimension data exists in the audience data analysis system, grouping users in the table 15 according to the table 15 and the user dimension data, and obtaining the user group distribution information of the audience moment 8:07. Wherein, in Table 15, the user identifications are at viewing time 8:07And user identification +. >The total viewing amount of (2) is the same.
TABLE 15
In the present embodiment, in addition to the above-described target information, a common viewing index may be obtained by analyzing viewing data in the viewing data analysis system. For example, by modeling three-dimensional dataAnd (3) analyzing the received video data to obtain common audience rating indexes such as audience rating, arrival rate and the like.
In one embodiment, it is generally necessary to analyze the viewing time of a particular viewing channel or a particular viewing program, and calculate a common indicator such as a rating or a share of the viewing program. In three-dimensional data modelSlicing according to viewing channels to obtain data slices of specific viewing channels>. According to the method for analyzing the second target data slice corresponding to the first viewing channel, the viewing total amount +.>. Assume that the minimum sampling interval of the viewing data analysis system is +.>The total viewing time of each viewing time of the viewing channel is. Accumulating the total viewing duration of each viewing moment in the whole day or a specific time period (such as a golden time period) to obtain the total viewing duration of the whole day or the specific time period of the viewing channel; and accumulating the total viewing time length of each viewing time in the starting and ending time of the specific viewing program to obtain the total viewing time length of the specific viewing program.
In another embodiment, the audience share of the audience channels and the audience share of the audience programs can be obtained based on the audience channels and the audience duration of the audience programs.
In another embodiment, for a certain viewing channel and a certain viewing program, the viewing durations of all viewing channels and all viewing programs in the same time period of the target time period are accumulated, so that the viewing total duration of the target time period can be obtained, and further the viewing share is obtained.
In another embodiment, it is generally necessary to analyze the number of users arriving at a particular viewing channel or particular viewing program, and calculate common indicators such as arrival rate, loyalty, etc. In three-dimensional data modelAccording to the above-mentioned method for removing duplication of users, the data slice of a specific viewing time can be sliced +.>Performing de-duplication, and determining the time range of de-duplication operation according to the waiting time period of the specific viewing channel or the start-stop time of the specific viewing program> Reading the time range +.> Data slice at a specific viewing time in> For a pair of After the data slices are subjected to the de-duplication operation, the de-duplicated data slices are obtained. According to the method in 'instantaneous audience distribution of each audience channel at first audience moment', the method comprises the following steps of Calculating to obtain->,/>I.e., the number of users reached per viewing channel over the target viewing period.
In another embodiment, the arrival rates of the particular viewing channel and the particular viewing program may be derived based on the particular viewing channel, the number of users reached for the particular viewing program.
In another embodiment, after the calculation of the total viewing time length of the specific viewing channel and the specific viewing program is completed, the average viewing rate, the simulcast viewing rate, the period contribution, the period index, the viewing proportion and other common indexes calculated based on the time length and the number of users can be obtained.
< device example one >
Referring to fig. 15, an embodiment of the present disclosure provides a viewing data analysis apparatus 1500 that includes an acquisition module 1501, a disassembly module 1502, a setup module 1503, a reception module 1504, a generation module 1505, and an analysis module 1506.
Wherein, the obtaining module 1501 is configured to obtain a plurality of viewing data; a disassembling module 1502, configured to disassemble viewing data for each viewing data to obtain three-dimensional decomposed data of the viewing data, where the three-dimensional decomposed data includes a user identifier, a viewing channel, and a viewing time; a building module 1503, configured to build a patterned three-dimensional data model according to the three-dimensional decomposition data of the plurality of viewing data; a receiving module 1504 for receiving an input of a user; a generation module 1505 for generating and displaying a target data slice from the three-dimensional data model in response to the input; the analysis module 1506 is configured to analyze the target data slice to obtain target information; the target information comprises at least one of preference information of users on viewing channels, preference information of users on viewing moments, user group distribution information of viewing channels, viewing curve information of viewing channels, instant viewing distribution information of viewing channels and instant viewing distribution information of user groups.
In the embodiment of the application, a three-dimensional data model is built according to a plurality of viewing data, the three-dimensional data model is sliced according to the input of a user to the three-dimensional data model, a target data slice is obtained, preference information of the user to the viewing channels, preference information of the user to the viewing moment, user group distribution information of the viewing channels, viewing curve information of the viewing channels, instantaneous viewing distribution information of the viewing channels and instantaneous viewing distribution information of the user groups can be obtained through flexible and efficient analysis of the target data slice, the analysis dimension of the viewing data is effectively expanded, and the analysis method is simple and efficient; meanwhile, through multidimensional audience data analysis, the method can provide fine data support for content production, arrangement and delivery for a program content production mechanism, a program content broadcasting mechanism, an advertisement delivery mechanism and the like, so that the content quality and the economic value of broadcast television programs are improved.
< device example two >
An embodiment of the present disclosure provides an electronic device, including a memory for storing a computer program and a processor; the processor is configured to execute the computer program to implement the method described in the method embodiments above.
The present invention may be a system, method, and/or computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement aspects of the present invention.
The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, are not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical pulses through fiber optic cables), or electrical signals transmitted through wires.
The computer readable program instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.
Computer program instructions for carrying out operations of the present invention may be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, c++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present invention are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information for computer readable program instructions, which can execute the computer readable program instructions.
Various aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are all equivalent.
The foregoing description of embodiments of the invention has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the technical improvements in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the invention is defined by the appended claims.
Claims (12)
1. A method of viewing data analysis, the method comprising:
obtaining a plurality of viewing data;
for each viewing data, disassembling the viewing data to obtain three-dimensional decomposition data of the viewing data, wherein the three-dimensional decomposition data comprises a user identifier, a viewing channel and a viewing time;
establishing a graphical three-dimensional data model according to the three-dimensional decomposition data of a plurality of the viewing data;
receiving an input of a user;
generating and displaying a target data slice from the three-dimensional data model in response to the input;
Analyzing the target data slice to obtain target information;
the target information comprises at least one of preference information of users on viewing channels, preference information of users on viewing moments, user group distribution information of viewing channels, viewing curve information of viewing channels, instant viewing distribution information of viewing channels and instant viewing distribution information of user groups.
2. The viewing data analysis method of claim 1, wherein the creating a patterned three-dimensional data model from the three-dimensional decomposition data comprises:
establishing a graphical three-dimensional data model according to the three-dimensional decomposition data by taking a user identification of the viewing data as a first dimension, a viewing channel of the viewing data as a second dimension and a viewing moment of the viewing data as a third dimension;
the first dimension and the second dimension form a first preset plane, the second dimension and the third dimension form a second preset plane, and the first dimension and the third dimension form a third preset plane.
3. The viewing data analysis method of claim 2, wherein the input is indicative of generating a first target data slice corresponding to a first user identification;
The generating and displaying, in response to the input, a target data slice from the three-dimensional data model, comprising:
responding to the input, slicing a first plane corresponding to the first user identification in the three-dimensional data model, and generating and displaying a first target data slice;
the first plane and the second preset plane are arranged in parallel, and the first target data slice comprises at least one viewing channel and at least one viewing moment corresponding to the first user identification in the three-dimensional data model.
4. The viewing data analysis method of claim 3, wherein the analyzing the target data slice to obtain target information comprises:
calculating a sum value of first viewing moments corresponding to the viewing channels in a first preset time period for each viewing channel in the at least one viewing channel to obtain first viewing duration; the first viewing duration is the total viewing duration of the first user on the viewing channel in the first preset time period;
and obtaining preference information of the first user for the viewing channel in the first preset time period according to the first viewing time period.
5. The viewing data analysis method of claim 3, wherein the analyzing the target data slice to obtain target information comprises:
dividing a second preset time period according to preset time intervals to obtain n time intervals, wherein n is a positive integer, and n is more than or equal to 1;
dividing any one of the n time intervals into a plurality of target viewing moments;
calculating the sum of the viewing moments of the first user viewing the viewing channels at the target viewing moment in n time intervals according to each target viewing moment to obtain a second duration, wherein the second duration is the total viewing duration of the first user viewing the viewing channels at the target viewing moment in the second preset time period;
and obtaining preference information of the first user for the target viewing time in the second preset time period according to the second time length.
6. The viewing data analysis method of claim 2 wherein the input is indicative of generating a second target data slice corresponding to the first viewing channel;
the generating and displaying, in response to the input, a target data slice from the three-dimensional data model, comprising:
Responding to the input, slicing a second plane corresponding to the first viewing channel in the three-dimensional data model, and generating and displaying a second target data slice;
the second plane and the third preset plane are arranged in parallel, and the second target data slice comprises at least one user identifier and at least one viewing moment corresponding to the first viewing channel in the three-dimensional data model.
7. The viewing data analysis method of claim 6, wherein the analyzing the target data slice to obtain target information comprises:
calculating a sum of the viewing moments of the user identifiers to the first viewing channel in a third preset time period for each user identifier in the at least one user identifier to obtain a third duration, wherein the third duration is a total viewing duration of the user identifiers to the first viewing channel in the third preset time period;
dividing the at least one user identifier according to a first preset rule to obtain at least one first user group, wherein the first preset rule is any one of a region to which the user identifier corresponds to a user, an age of the user identifier corresponds to the user and a gender of the user identifier corresponds to the user;
Calculating a sum of the third time durations of the user identifications in the first user groups in the third preset time period for each first user group in the at least one first user group to obtain a fourth time duration;
and obtaining first user group distribution information of the first viewing channel in the third preset time period according to the fourth time period.
8. The viewing data analysis method of claim 6, wherein the analyzing the target data slice to obtain target information comprises:
for each of the at least one viewing time, calculating the number of user identifiers for viewing any viewing channel at the viewing time in a fourth preset time period, and obtaining the total viewing amount of the viewing time in the fourth preset time period;
and obtaining the viewing curve information of the first viewing channel in the fourth preset time period according to the viewing total amount of each viewing moment in the fourth preset time period.
9. The viewing data analysis method of claim 2 wherein the input is indicative of generating a third target data slice corresponding to the first viewing time;
The generating and displaying, in response to the input, a target data slice from the three-dimensional data model, comprising:
responding to the input, slicing a third plane corresponding to the first viewing moment in the three-dimensional data model, and generating and displaying a third target data slice;
the third plane is arranged in parallel with the first preset plane, and the third target data slice comprises at least one user identifier and at least one viewing channel corresponding to the first viewing moment in the three-dimensional data model.
10. The viewing data analysis method of claim 9, wherein the analyzing the target data slice to obtain target information comprises:
for each of the viewing channels in the at least one viewing channel, calculating the number of user identifiers for viewing the viewing channel at the first viewing moment to obtain the viewing total number of the viewing channels at the first viewing moment;
and obtaining the instantaneous audience distribution information of each audience channel at the first audience moment according to the audience quantity of each audience channel at the first audience moment.
11. The viewing data analysis method of claim 9, wherein the analyzing the target data slice to obtain target information comprises:
Dividing the at least one user identifier according to a second preset rule to obtain at least one second user group, wherein the second preset rule is any one of a region to which the user identifier corresponds to a user, an age of the user identifier corresponds to the user and a gender of the user identifier corresponds to the user;
calculating the number of the user identifiers for watching the watching channels in the second user group at the first watching time aiming at each second user group in the at least one second user group to obtain the instantaneous audience rating of the second user group at the first watching time;
and obtaining the instantaneous audience distribution information of the second user group at the first audience moment according to the instantaneous audience quantity of each second user group.
12. An electronic device comprising a memory and a processor, the memory for storing a computer program; the processor is configured to execute the computer program to implement the method according to any one of claims 1-11.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310368527.9A CN116095409B (en) | 2023-04-07 | 2023-04-07 | Audience data analysis method and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310368527.9A CN116095409B (en) | 2023-04-07 | 2023-04-07 | Audience data analysis method and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116095409A true CN116095409A (en) | 2023-05-09 |
CN116095409B CN116095409B (en) | 2023-08-04 |
Family
ID=86187237
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310368527.9A Active CN116095409B (en) | 2023-04-07 | 2023-04-07 | Audience data analysis method and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116095409B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030023967A1 (en) * | 2001-07-25 | 2003-01-30 | Kim Sang-Soo | System and method for surveying broadcasting rating |
CN104270653A (en) * | 2014-09-30 | 2015-01-07 | 北京酷云互动科技有限公司 | Method, device and server for obtaining viewing information |
CN104902293A (en) * | 2015-06-08 | 2015-09-09 | 福州大学 | System for counting and managing audience rating of digital television and implement method thereof |
CN109600640A (en) * | 2017-09-30 | 2019-04-09 | 北京国双科技有限公司 | A kind of appraisal procedure and device of program audience competitiveness |
CN111246294A (en) * | 2020-01-06 | 2020-06-05 | 国家广播电视总局广播电视规划院 | Method, device, equipment and storage medium for processing audience rating index data |
CN111526394A (en) * | 2020-04-10 | 2020-08-11 | 国家广播电视总局广播电视规划院 | Method, device and equipment for processing audience behavior data and storage medium |
CN112235610A (en) * | 2020-10-14 | 2021-01-15 | 广州欢网科技有限责任公司 | Method, device and system for analyzing audience distribution of direct-request program |
CN115033735A (en) * | 2022-06-17 | 2022-09-09 | 北京视达科技有限公司 | Video recommendation method, device and equipment and readable storage medium |
-
2023
- 2023-04-07 CN CN202310368527.9A patent/CN116095409B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030023967A1 (en) * | 2001-07-25 | 2003-01-30 | Kim Sang-Soo | System and method for surveying broadcasting rating |
CN104270653A (en) * | 2014-09-30 | 2015-01-07 | 北京酷云互动科技有限公司 | Method, device and server for obtaining viewing information |
CN104902293A (en) * | 2015-06-08 | 2015-09-09 | 福州大学 | System for counting and managing audience rating of digital television and implement method thereof |
CN109600640A (en) * | 2017-09-30 | 2019-04-09 | 北京国双科技有限公司 | A kind of appraisal procedure and device of program audience competitiveness |
CN111246294A (en) * | 2020-01-06 | 2020-06-05 | 国家广播电视总局广播电视规划院 | Method, device, equipment and storage medium for processing audience rating index data |
CN111526394A (en) * | 2020-04-10 | 2020-08-11 | 国家广播电视总局广播电视规划院 | Method, device and equipment for processing audience behavior data and storage medium |
CN112235610A (en) * | 2020-10-14 | 2021-01-15 | 广州欢网科技有限责任公司 | Method, device and system for analyzing audience distribution of direct-request program |
CN115033735A (en) * | 2022-06-17 | 2022-09-09 | 北京视达科技有限公司 | Video recommendation method, device and equipment and readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN116095409B (en) | 2023-08-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108108821B (en) | Model training method and device | |
US9152691B2 (en) | System and method for performing set operations with defined sketch accuracy distribution | |
CN105930425A (en) | Personalized video recommendation method and apparatus | |
CN106469202A (en) | A kind of data analysing method of video display big data platform | |
CN104731585A (en) | Display method and device of vote page | |
CN111125344B (en) | Related word recommendation method and device | |
CN103763585A (en) | User characteristic information obtaining method and device and terminal device | |
CN111008707A (en) | Automatic modeling method and device and electronic equipment | |
CN110347781B (en) | Article reverse arrangement method, article recommendation method, device, equipment and storage medium | |
CN110555172A (en) | user relationship mining method and device, electronic equipment and storage medium | |
US20190050317A1 (en) | Systems and methods for determining event processing delays | |
CN114747227A (en) | Method, system, and apparatus for estimating census-level audience size and total impression duration across demographic groups | |
CN106303591B (en) | A kind of video recommendation method and device | |
CN113537685A (en) | Data processing method and device | |
CN116095409B (en) | Audience data analysis method and electronic equipment | |
CN104735117A (en) | Information processing method, device and system | |
CN106156123A (en) | Active value computational methods and device | |
CN112100177A (en) | Data storage method and device, computer equipment and storage medium | |
CN116881219A (en) | Database optimization processing method and device, electronic equipment and storage medium | |
US20190089659A1 (en) | Bursty detection for message streams | |
CN109413459B (en) | User recommendation method and related equipment in live broadcast platform | |
CN108733728A (en) | Time series data statistical method, device, computer equipment and readable storage medium storing program for executing | |
CN109460476B (en) | Method and device for generating mulberry basic diagram, storage medium and electronic equipment | |
CN109669779B (en) | Method and device for determining cleaning path of data and cleaning data | |
CN117290561B (en) | Service state information feedback method, device, equipment and computer readable 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 |