CN109561350B - User interest degree evaluation method and system - Google Patents
User interest degree evaluation method and system Download PDFInfo
- Publication number
- CN109561350B CN109561350B CN201710888524.2A CN201710888524A CN109561350B CN 109561350 B CN109561350 B CN 109561350B CN 201710888524 A CN201710888524 A CN 201710888524A CN 109561350 B CN109561350 B CN 109561350B
- Authority
- CN
- China
- Prior art keywords
- program
- label
- user
- under
- current
- 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
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
- H04N21/45—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
- H04N21/4662—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms
-
- 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
- H04N21/4508—Management of client data or end-user data
- H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a system for evaluating user interest degree, wherein an interest label library is established and comprises program labels and program parameters under the program labels; calculating program index parameters of the user on each program label based on the program labels; normalizing the relative values of the program index parameters of the current user under each program label, which are not relative to all users, to obtain normalized values corresponding to the program index parameters; and weighting and calculating the normalization value corresponding to each program index parameter under each program label corresponding to the current user to obtain the interest degree of the current user to the program corresponding to each program label. By the method, the interest degree is calculated based on the program index parameters on the pre-established program label, and the process is simple. Therefore, the user interest degree evaluation method disclosed by the invention can quickly and accurately obtain the interest degree of the user on each program label.
Description
Technical Field
The invention relates to the technical field of new media, in particular to a method and a system for evaluating user interestingness.
Background
With the rapid development of new media industry, it has become one of its important services to push different user portraits differently. The user's viewing preferences are an important component in the process of user portrayal. The viewing preferences of a user are primarily measured by user interestingness. The user interest level refers to the degree of interest of the user in each interest tag.
For the calculation of the user interest degree, in the prior art, the probability values of the viewing interest preferences of different users in different time periods are calculated mainly based on a topic model. The topic model mainly realizes the calculation of the user interestingness in a training mode. However, when the user interest degree is calculated by the topic model, the complexity is high, the universality is poor, the topic trained by the topic model is abstract, the interpretability is not strong, and certain differences exist among different topic models. Therefore, obtaining user interest based on the prior art is not only a complex process, but also inaccurate.
Disclosure of Invention
In view of this, the present application provides a method and a system for evaluating user interest, so as to achieve the purpose of quickly obtaining accurate user interest.
In order to achieve the above object, the following solutions are proposed:
the invention discloses a method for evaluating user interestingness in a first aspect, which comprises the following steps:
establishing an interest tag library, wherein the interest tag library comprises program tags and program parameters under the program tags, and the program tags comprise categories to which programs belong;
calculating program index parameters of the user on each program label based on the program labels;
normalizing the relative values of the program index parameters of the current user under each program label relative to all users to obtain normalized values corresponding to the program index parameters;
and weighting and calculating the normalization value corresponding to each program index parameter under each program label corresponding to the current user to obtain the interest degree of the current user to the program corresponding to each program label.
Preferably, the program parameters at least include: the program name and the duration of the program itself;
the categories to which the programs belong at least include: the categories divided according to the content and/or the categories divided according to the program subjects include: a drama, comedy, or reality show, the categories classified by program material include: a television show, a movie or a variety.
Preferably, the program index parameters include: viewing duration, viewing completion rate, number of programs, and number of viewing days.
Preferably, if the program index parameter includes a viewing duration, calculating the program index parameter of the user on each program label based on the program label, including:
determining each program label;
acquiring the time length of the user watching the program under each program label
Wherein, tiShowing the time length of the user watching the program under the current program label each time, i and n showing the number of times the user watches under a certain label, iGreater than or equal to 1, n is greater than i.
Preferably, if the program index parameter includes: and calculating a program index parameter used for each program label based on the program label, wherein the program index parameter comprises the following steps:
determining each program label;
acquiring the times of watching each program by the user under the program label, the watching time length of each time and the original time length of each program to obtain the watching completion rate
Wherein, tiThe time length of the user watching the program under the current program label each time is represented, i and n represent the number of times the user watches under a certain label, i is more than or equal to 1, n is more than i, piAnd the preview playing time length of the program under the current program label is shown for each time the user watches the program.
Preferably, the normalization processing is performed on the relative value of the program index parameter of each program label of the current user with respect to all users to obtain a corresponding normalization value, and includes:
acquiring the number of all users corresponding to programs watched under each program label and program index parameters corresponding to all the users under each program label;
determining the relative value of the program index parameter of the current user at each program label relative to all users;
based on the maximum and minimum normalization calculation method and the program index parameters corresponding to the users, obtaining the relative values of the watching days of the program index parameters of the current user on each program label relative to all the users, and taking the obtained relative values as the normalization values of the program index parameters under the corresponding program labels.
Preferably, if the program index parameter includes: viewing duration, viewing completion rate, program number and viewing days; then, the weighting calculates a normalization value corresponding to each program index parameter under each program label corresponding to the current user, to obtain the interest level of the current user in the program corresponding to each program label, including:
acquiring each viewing time length, the viewing completion rate, the program number and a normalization value corresponding to the viewing days under each program label corresponding to the current user;
and for each program label, obtaining the interest degree H of the current user to the program corresponding to each program label based on H ═ aT '+ bP' + cR '+ dD', wherein T 'is a normalized value corresponding to the viewing duration under the current program label, P' is a normalized value corresponding to the number of programs under the current program label, R 'is a normalized value corresponding to the viewing completion rate under the current program label, D' is a normalized value corresponding to the number of viewing days under the current program label, a, b, c, D are pre-assigned weight values, and a + b + c + D is 1.
The second aspect of the present invention discloses a system for evaluating user interest, comprising:
the system comprises a preprocessing unit, a storage unit and a processing unit, wherein the preprocessing unit is used for establishing an interest tag library, the interest tag library comprises program tags and program parameters under the program tags, and the program tags comprise categories to which programs belong;
the index calculation unit is used for calculating program index parameters of the user on each program label based on the program labels;
the normalization processing unit is used for normalizing the relative values of the program index parameters of the current user under each program label relative to all users to obtain the normalization values corresponding to the program index parameters;
and the interest degree calculation unit is used for weighting and calculating the normalization value corresponding to each program index parameter under each program label corresponding to the current user to obtain the interest degree of the current user on the program corresponding to each program label.
In a third aspect, the present invention discloses a storage medium, which includes a stored program, wherein, when the program runs, a device in which the storage medium is located is controlled to execute the method for evaluating user interest degree disclosed in the first aspect of the present invention.
In a fourth aspect of the present invention, a processor is disclosed, the processor is configured to run a program, wherein the program executes the method for evaluating the user interest level disclosed in the first aspect of the present invention.
According to the technical scheme, the invention discloses a method and a system for evaluating the user interest degree, wherein an interest label library is established and comprises program labels and program parameters under the program labels, and the program labels comprise the categories of the programs; calculating program index parameters of the user on each program label based on the program labels; normalizing the relative values of the program index parameters of the current user under each program label, which are not relative to all users, to obtain normalized values corresponding to the program index parameters; and weighting and calculating the normalization value corresponding to each program index parameter under each program label corresponding to the current user to obtain the interest degree of the current user to the program corresponding to each program label. By the disclosed user interest evaluation method, the obtained interest approximately follows Gaussian distribution on the number of users, the obtained interest can truly reflect the interest of the user in the program under the program label, the calculation is obtained based on the program index parameters on the program label established in advance, and the process is simple. Therefore, the user interest degree evaluation method disclosed by the invention can quickly and accurately obtain the interest degree of the user on each program label.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for evaluating user interestingness disclosed in the embodiment of the present invention;
FIG. 2 is a schematic flowchart of a normalization process according to an embodiment of the disclosure;
FIG. 3 is a schematic structural diagram of a system for evaluating user interestingness disclosed in the embodiments of the present invention;
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As can be seen from the background art, in the prior art, probability values of viewing interest preferences of different users in different time periods are calculated based on a topic model. However, when the user interest is calculated by the topic model, the complexity is high, the universality is poor, the topic trained by the topic model is abstract, the interpretability is not strong, and different topic models have certain difference, so that the process for obtaining the user interest is complex and inaccurate. Therefore, the invention discloses a method for evaluating the user interest degree, which aims to achieve the aim of quickly obtaining the accurate user interest degree.
Fig. 1 is a schematic flow chart of a method for evaluating user interest level according to an embodiment of the present invention.
Step S101: establishing an interest tag library, wherein the interest tag library comprises program tags and program parameters under the program tags, and the program tags comprise categories to which programs belong.
In the process of establishing the interest tag library in step S101, the programs are classified according to the categories to which the programs belong, and corresponding program tags are established. And the divided program labels contain the program parameters.
It should be noted that the category to which the program belongs refers to a category divided according to the content and/or a category divided according to the program material, and the category divided according to the content includes: a drama, comedy, or reality show, the categories classified by program material include: a television show, a movie or a variety. Of course, the embodiments of the present invention are not limited to the content included in the above categories, and the categories divided according to the content may also include parent categories, education categories, and the like. The categories divided by the program material may also include animation, music, and the like.
Further, the categories to which the program belongs in the embodiments of the present invention are not limited to the above categories, and may also include other categories, for example, the categories divided according to the program duration include: short video and long video.
It should be noted that the program parameters include the program name and the duration of the program itself. Further, the content of the watching time length, time period and the like of each time the user watches the program can be included.
Preferably, the interest tag library constructed based on the program tags may be constructed by mapping the tags of the existing programs into the constructed interest tag library.
It should be noted that each program parameter may include a plurality of categories to which the program belongs, and a corresponding relationship in the constructed interest tag library, for example: nominal name of people: drama/drama; i is the singer: hedonic/talent show, etc.
Step S102: and calculating the program index parameters of the user on each program label based on the program labels.
When the step S102 is executed to calculate the program index parameter, the program index parameter that can be calculated in the embodiment of the present invention may be set in advance. The program index parameters include: viewing duration, viewing completion rate, program number, and viewing days, etc., but the embodiment of the present invention is not limited to have only the above four program index parameters.
It should be noted that, in the specific process of calculating the program index parameters, at least two program index parameters among the four program index parameters need to be calculated, but the upper limit is not set.
Step S103: and normalizing the relative value of the program index parameter of the current user under each program label relative to all users to obtain a normalized value corresponding to each program index parameter.
In the process of executing step S103, the relative situation of the program index parameter of the user under each program label with respect to the program index parameters of all users under each program label is calculated.
The specific process is shown in fig. 2, and includes:
step S201: and acquiring the number of all users corresponding to the program under each program label and the program index parameter corresponding to each user under each program label.
Step S202: and determining the relative value of the program index parameter of the current user at each program label relative to all users.
Step S203: based on the maximum and minimum normalization calculation method and the program index parameters corresponding to the users, obtaining the relative values of the watching days of the program index parameters of the current user on each program label relative to all the users, and taking the obtained relative values as the normalization values of the program index parameters under the corresponding program labels.
Based on the above specific implementation process, the following examples are given:
when the program label is a television play, the program index parameter is viewing duration, and the total number of users watching the television play is 5, including the users needing to be calculated currently. Respectively acquiring the watching time of watching TV plays by 5 users as follows: 20 minutes, 30 minutes, 45 minutes, 15 minutes, and 60 minutes. Then, normalizing the viewing time length of the user (first user) currently needing to be calculated, and obtaining a normalized value of the viewing time length as follows: (20-15)/(60-15) ═ 0.11.
The normalization of other program index parameters is also calculated by adopting the normalization mode of the maximum value and the minimum value. And normalizing the program index parameters to be within the [0,1] interval. And the subsequent interest evaluation is facilitated.
Step S104: and weighting and calculating the normalization value corresponding to each program index parameter under each program label corresponding to the current user to obtain the interest degree of the current user to the program corresponding to each program label.
In the process of executing step S104, the obtained normalization value corresponding to each program index parameter under each program label corresponding to the current user is subjected to weighted calculation. The weight added to the normalization value corresponding to each program index parameter can be adjusted according to the service type, and can also be preset. That is, different weights are assigned to the normalization values corresponding to different program index parameters according to actual conditions, but it is necessary to satisfy that the sum of the weights added to the normalization values corresponding to the program index parameters is 1.
Further, it should be noted that, in the process of performing the weighting calculation, the normalization values corresponding to the plurality of program index parameters may be deleted and selected for performing the weighting calculation, and not all of them are required.
The embodiment of the invention establishes an interest label library, wherein the interest label library comprises program labels and program parameters under the program labels, and the program labels comprise the categories of the programs; calculating program index parameters of the user on each program label based on the program labels; normalizing the relative values of the program index parameters of the current user under each program label, which are not relative to all users, to obtain normalized values corresponding to the program index parameters; and weighting and calculating the normalization value corresponding to each program index parameter under each program label corresponding to the current user to obtain the interest degree of the current user to the program corresponding to each program label. By the disclosed user interest evaluation method, the obtained interest approximately follows Gaussian distribution on the number of users, the obtained interest can truly reflect the interest of the user in the program under the program label, the calculation is obtained based on the program index parameters on the program label established in advance, and the process is simple. Therefore, the user interest degree evaluation method disclosed by the invention can quickly and accurately obtain the interest degree of the user on each program label.
Based on the method for evaluating user interest level disclosed in the embodiment of the present invention, in the process of calculating the program index parameters of the user on each program label in step S102, different program index parameters are calculated in different manners, which is exemplified here.
If the program index parameter includes the viewing duration, calculating the program index parameter of the user on each program label based on the program label, wherein the specific process comprises the following steps:
first, each program label is determined.
And then, acquiring the time length T of the user for watching the program under each program label.
Wherein, t in the formula (1)iThe time length of the user watching the program under the current program label each time is shown, i and n show the number of times the user watches under a certain label, i is more than or equal to 1, and n is more than i.
If the program index parameters include the number of programs, calculating the program index parameters of the user on each program label based on the program labels, wherein the specific process comprises the following steps:
first, each program label is determined.
Then, different programs watched by the user under each program label are determined, and the different programs can be determined by program names or program topics, wherein the number P of the programs having the same or similar program names or program topics is 1.
For example, determining that the program label is a variety, and the program watched by the user under the program label includes: which dad goes to 1 and dad goes to 2. Because the program names are similar, the number of programs watched by the user under the condition that the program label is the synthesis art is 1.
For example, determining that the program label is a variety, and the program watched by the user under the program label includes: dad goes to which 1, dad goes to which 2 and i is singer 3. And the program names of which 1 and 2 are similar to each other are recorded as 1 by dad. I are singers 3 and are individually noted as 1. Therefore, the number of programs watched by the user under the condition that the program label is the total art is 2.
If the program index parameters include: and calculating a program index parameter used for each program label based on the program label if the watching completion rate is reached, wherein the specific process comprises the following steps:
first, each program label is determined.
Then, the number of times that the user watches each program under the program label, the watching time length of each time and the original time length of each program are obtained, and the watching completion rate R is obtained.
Wherein t in the formula (2)iThe time length of each time the user watches the program under the current program label is shown, i and n show the number of times the user watches under a certain label, i is more than or equal to 1, n is more than i, piAnd the preview playing time length of the program under the current program label is shown for each time the user watches the program.
For example: it is determined that a program label is a drama and the user watches the name of people 3 times on the drama label. And the time for watching the nominal first set of people is 20 minutes, the time for watching the nominal second set of people is 40 minutes, and the time for watching the fifth set of army league is 20 minutes. Wherein the nominal total duration of people is 50 minutes and the total duration of the army union is 45 minutes. Based on the above formula (2), the completion rate of watching the program by the user under the program label can be obtained as follows: (20/50+40/50+20/45)/3 ═ 0.55.
If the program index parameters comprise watching days, calculating the program index parameters of the user on each program label based on the program labels, wherein the specific process comprises the following steps:
first, each program label is determined.
The number of days D that the user has watched under each program label is then determined.
For example, if the program label is a tv show and the user has watched the tv show for 3 days, the number of viewing days of the user on the tv show labeled by the program label is 3.
Further, based on the determined program label parameters, the normalization processing is performed to obtain a normalization value T 'corresponding to the viewing duration, a normalization value P' corresponding to the number of programs, a normalization value R 'corresponding to the viewing completion rate, and a normalization value D' corresponding to the number of viewing days.
Further, based on the normalized viewing duration, viewing completion rate, program number and viewing days, the weighting calculates the normalized value corresponding to each program index parameter under each program label corresponding to the current user, so as to obtain the interest level of the current user in the program corresponding to each program label, and the specific process includes:
firstly, acquiring each viewing time length, the viewing completion rate, the number of programs and a normalization value corresponding to the number of viewing days of each program label corresponding to the current user;
then, for each program label, performing weighting calculation based on formula (3) to obtain the interest level H of the current user in the program corresponding to each program label.
H＝aT′+bP′+cR′+dD′ (3)
Wherein, T 'is a normalized value corresponding to the viewing duration under the current program label, P' is a normalized value corresponding to the number of programs under the current program label, R 'is a normalized value corresponding to the viewing completion rate under the current program label, D' is a normalized value corresponding to the viewing days under the current program label, a, b, c, D are pre-assigned weighted values, and a + b + c + D is 1.
According to the embodiment of the invention, by the user interest evaluation method, the program index parameters of the user on the program labels are calculated based on the program labels which are established in advance according to the interest, the obtained program index parameters under each program label are respectively subjected to normalization processing, and finally the user interest of the user taking the weighted result of the program index parameters subjected to the normalization processing as the corresponding program label is obtained.
Based on the above-mentioned method for evaluating user interestingness disclosed in the embodiments of the present invention, the embodiments of the present invention also correspondingly disclose an evaluation system for user interestingness, as shown in fig. 3, the evaluation system 300 for user interestingness mainly includes:
the preprocessing unit 301 is configured to establish an interest tag library, where the interest tag library includes program tags and program parameters under the program tags, and the program tags include categories to which programs belong.
An index calculating unit 302, configured to calculate a program index parameter of the user on each program label based on the program label.
The normalization processing unit 303 is configured to normalize a relative value of the program index parameter of the current user under each program label with respect to all users, to obtain a normalization value corresponding to each program index parameter.
The interest-degree calculating unit 304 is configured to calculate, by weighting, a normalized value corresponding to each program index parameter under each program label corresponding to the current user, to obtain an interest degree of the current user in the program corresponding to each program label.
Further, the index calculation unit 302 includes:
the time length calculation module is used for determining each program label; acquiring the time length of the user watching the program under each program label
Wherein, tiThe time length of the user watching the program under the current program label each time is shown, i and n show the number of times the user watches under a certain label, i is more than or equal to 1, and n is more than i.
And/or the presence of a gas in the gas,
a watching completion rate calculation module for determining each program label; acquiring the times of watching each program by the user under the program label, the watching time length of each time and the original time length of each program to obtain the watching completion rate
Wherein, tiIndicates the duration of each time the user watches the program under the current program label, i andn represents the number of times that the user watches under a certain label, i is more than or equal to 1, n is more than i, piAnd the preview playing time length of the program under the current program label is shown for each time the user watches the program.
And/or the presence of a gas in the gas,
and the program number calculating module is used for determining the number of programs watched by the user under the sign of each program target, wherein the programs with the same program theme are marked as 1.
And/or the presence of a gas in the gas,
and the watching day calculating module is used for determining the number of days the user watches under each section of target sign.
Further, the interestingness calculating unit 304 includes:
an obtaining module, configured to obtain each viewing duration, the viewing completion rate, the number of programs, and a normalization value corresponding to the number of viewing days for each program tag corresponding to the current user;
an interest degree calculation module, configured to, for each of the program tags, calculate a degree of interest based on H ═ aT′+bP′And + cR '+ dD', obtaining the interest level H of the user in the program corresponding to each program label, where T 'is a normalized value corresponding to the viewing duration under the current program label, P' is a normalized value corresponding to the number of programs under the current program label, R 'is a normalized value corresponding to the viewing completion rate under the current program label, D' is a normalized value corresponding to the number of viewing days under the current program label, a, b, c, D are pre-assigned weight values, and a + b + c + D is 1.
The specific principle and the implementation process of each unit and module in the user interest level evaluation system disclosed in the embodiment of the present invention are the same as those of the user interest level evaluation method disclosed in the embodiment of the present invention, and reference may be made to corresponding parts in the user interest level evaluation method disclosed in the embodiment of the present invention, which are not described herein again.
Based on the user interest evaluation system disclosed in the embodiment of the present invention, the units and modules may be implemented by a hardware device including a processor and a memory. The method specifically comprises the following steps: the units and modules are stored in a memory as program units, and the program units stored in the memory are executed by a processor to realize the evaluation of the user interest degree.
The processor comprises a kernel, and the kernel calls a corresponding program unit from the memory. The kernel can be set to be one or more, and the evaluation on the user interestingness is realized by adjusting the kernel parameters.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
Further, an embodiment of the present invention provides a processor, where the processor is configured to execute a program, where the program executes the method for evaluating the user interest level when running.
Further, an embodiment of the present invention provides an apparatus, where the apparatus includes a processor, a memory, and a program stored in the memory and capable of running on the processor, and the processor implements the following steps when executing the program: establishing an interest tag library, wherein the interest tag library comprises program tags and program parameters under the program tags, and the program tags comprise categories to which programs belong; calculating program index parameters of the user on each program label based on the program labels; normalizing the relative values of the program index parameters of the current user under each program label relative to all users to obtain normalized values corresponding to the program index parameters; and weighting and calculating the normalization value corresponding to each program index parameter under each program label corresponding to the current user to obtain the interest degree of the current user to the program corresponding to each program label.
If the program index parameter includes the viewing duration, calculating the program index parameter of the user on each program label based on the program label, including: determining each program label; acquiring the time length of the user watching the program under each program label
Wherein, tiThe time length of the user watching the program under the current program label each time is shown, i and n show the number of times the user watches under a certain label, i is more than or equal to 1, and n is more than i.
If the program index parameters include: and calculating a program index parameter used for each program label based on the program label, wherein the program index parameter comprises the following steps: determining each program label; acquiring the times of watching each program under the program label, the watching time length of each time and the original time length of each program of a user to obtain the watching completion rate
Wherein, tiThe time length of each time the user watches the program under the current program label is shown, i and n show the number of times the user watches under a certain label, i is more than or equal to 1, n is more than i, piAnd the preview playing time length of the program under the current program label is shown for each time the user watches the program.
Normalizing the relative values of the program index parameters of the current user in each program label relative to all users to obtain corresponding normalized values, wherein the normalization comprises the following steps: acquiring the number of all users corresponding to the program under each program label and the program index parameter corresponding to each user under each program label; determining the relative value of the program index parameter of the current user at each program label relative to all users; based on the maximum and minimum normalization calculation method and the program index parameters corresponding to the users, the relative values of the watching days of the program index parameters of the current user on each program label relative to all the users are obtained, and the obtained relative values are used as the normalization values of the program index parameters under the corresponding program labels.
Wherein, if the program index parameter includes: viewing duration, viewing completion rate, program number and viewing days; the weighting calculates a normalization value corresponding to each program index parameter under each program label corresponding to the current user to obtain the interest degree of the current user in the program corresponding to each program label, including: acquiring each viewing time length, the viewing completion rate, the number of programs and a normalization value corresponding to the number of viewing days under each program label corresponding to the current user; and aiming aT each program label, obtaining the interest degree H of the current user to the program corresponding to each program label based on H ═ aT '+ bP' + cR '+ dD', wherein T 'is a normalized value corresponding to the viewing duration under the current program label, P' is a normalized value corresponding to the number of programs under the current program label, R 'is a normalized value corresponding to the viewing completion rate under the current program label, D' is a normalized value corresponding to the viewing days under the current program label, a, b, c and D are pre-assigned weight values, and a + b + c + D is 1.
The equipment disclosed in the embodiment of the invention can be a server, a PC, a PAD, a mobile phone and the like.
Further, an embodiment of the present invention further provides a storage medium, on which a program is stored, and the program, when executed by a processor, implements the method for evaluating the user interest level.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device: establishing an interest tag library, wherein the interest tag library comprises program tags and program parameters under the program tags, and the program tags comprise categories to which programs belong; calculating program index parameters of the user on each program label based on the program labels; normalizing the relative values of the program index parameters of the current user under each program label relative to all users to obtain normalized values corresponding to the program index parameters; and weighting and calculating the normalization value corresponding to each program index parameter under each program label corresponding to the current user to obtain the interest degree of the current user to the program corresponding to each program label.
If the program index parameter includes the viewing duration, calculating the program index parameter of the user on each program label based on the program label, including: determining each program label; acquiring users to watch each of theDuration of program under program label
Wherein, tiThe time length of the user watching the program under the current program label each time is shown, i and n show the number of times the user watches under a certain label, i is more than or equal to 1, and n is more than i.
If the program index parameters include: and calculating a program index parameter used for each program label based on the program label, wherein the program index parameter comprises the following steps: determining each program label; acquiring the times of watching each program under the program label, the watching time length of each time and the original time length of each program of a user to obtain the watching completion rate
Wherein, tiThe time length of each time the user watches the program under the current program label is shown, i and n show the number of times the user watches under a certain label, i is more than or equal to 1, n is more than i, piAnd the preview playing time length of the program under the current program label is shown for each time the user watches the program.
Normalizing the relative values of the program index parameters of the current user in each program label relative to all users to obtain corresponding normalized values, wherein the normalization comprises the following steps: acquiring the number of all users corresponding to the program under each program label and the program index parameter corresponding to each user under each program label; determining the relative value of the program index parameter of the current user at each program label relative to all users; based on the maximum and minimum normalization calculation method and the program index parameters corresponding to the users, the relative values of the watching days of the program index parameters of the current user on each program label relative to all the users are obtained, and the obtained relative values are used as the normalization values of the program index parameters under the corresponding program labels.
Wherein, if the program index parameter includes: viewing duration, viewing completion rate, program number and viewing days; the weighting calculates a normalization value corresponding to each program index parameter under each program label corresponding to the current user to obtain the interest degree of the current user in the program corresponding to each program label, including: acquiring each viewing time length, the viewing completion rate, the number of programs and a normalization value corresponding to the number of viewing days under each program label corresponding to the current user; and aiming aT each program label, obtaining the interest degree H of the current user to the program corresponding to each program label based on H ═ aT '+ bP' + cR '+ dD', wherein T 'is a normalized value corresponding to the viewing duration under the current program label, P' is a normalized value corresponding to the number of programs under the current program label, R 'is a normalized value corresponding to the viewing completion rate under the current program label, D' is a normalized value corresponding to the viewing days under the current program label, a, b, c and D are pre-assigned weight values, and a + b + c + D is 1.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, 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 specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (7)
1. A method for evaluating user interestingness is characterized by comprising the following steps:
establishing an interest tag library, wherein the interest tag library comprises program tags and program parameters under the program object tags, the program tags comprise program categories, and the program parameters comprise program names and program self-duration;
calculating program index parameters of the user on each program label based on the program labels, wherein the program index parameters comprise viewing duration and viewing completion rate;
normalizing the relative value of the program index parameter of the current user under each program label relative to all users to obtain a normalized value corresponding to each program index parameter, wherein the normalized value comprises the following steps: acquiring the number of all users corresponding to programs watched under each program label and program index parameters corresponding to all the users under each program label; determining the relative value of the program index parameter of the current user at each program label relative to all users; based on a maximum value and minimum value normalization calculation method and program index parameters corresponding to each user, obtaining relative values of the program index parameters of the current user on each program label relative to all users, and taking the obtained relative values as normalization values of the program index parameters under the program labels corresponding to the user;
weighting and calculating a normalization value corresponding to each program index parameter under each program label corresponding to the current user to obtain the interest degree of the current user to the program corresponding to each program label;
if the program index parameter includes the viewing duration, calculating the program index parameter of the user on each program label based on the program label, including:
determining each program label;
acquiring the watching time length of the user watching the program under each program label
；
Wherein the content of the first and second substances,
the time length of the user watching the program under the current program label for the ith time is represented, n represents the total number of times of watching the user under the current program label, i represents the ith time of watching the user under the current program label, i is more than or equal to 1, and n is greater thanIs equal to i;
if the program index parameters include: and calculating a program index parameter used for each program label based on the program label, wherein the program index parameter comprises the following steps:
determining each program label;
acquiring the times of watching each program by the user under the program label, the watching time length of each time and the original time length of each program to obtain the watching completion rate
；
Wherein the content of the first and second substances,
the time length of the program under the current program label watched by the user for the ith time is represented, n represents the total number of times of watching under the current program label by the user, i represents the ith time of watching under the current program label by the user, i is more than or equal to 1, n is more than or equal to i,
indicating the original time length of each time the user watches the program under the current program label.
2. The method of claim 1, wherein the category to which the program belongs comprises at least: the categories divided according to the content and/or the categories divided according to the program subjects include: a drama, comedy, or reality show, the categories classified by program material include: a television show, a movie or a variety.
3. The method of claim 1, wherein the program indicator parameter further comprises: the number of programs and the number of viewing days.
4. The method of claim 3, wherein the program indicator parameter comprises: viewing duration, viewing completion rate, program number and viewing days; then, the weighting calculates a normalization value corresponding to each program index parameter under each program label corresponding to the current user, to obtain the interest level of the current user in the program corresponding to each program label, including:
acquiring each viewing time length, the viewing completion rate, the program number and a normalization value corresponding to the viewing days under each program label corresponding to the current user;
for each program label, based on the obtained interest level H of the current user to the program corresponding to each program label, wherein,
is a normalized value corresponding to the viewing duration under the current program label,
is a normalized value corresponding to the number of programs under the current program label,
the normalized value corresponding to the viewing completion rate under the current program label,
and a, b, c and d are weight values distributed in advance, and a + b + c + d = 1.
5. A system for evaluating a user's interest level, comprising:
the system comprises a preprocessing unit, a program searching unit and a program searching unit, wherein the preprocessing unit is used for establishing an interest tag library, the interest tag library comprises program tags and program parameters contained under the program object tags, the program tags comprise program categories, and the program parameters comprise program names and program self-time lengths;
the index calculation unit is used for calculating program index parameters of the user on each program label based on the program labels, wherein the program index parameters comprise viewing duration and viewing completion rate;
a normalization processing unit, configured to normalize a relative value of the program index parameter of the current user under each program label with respect to all users, to obtain a normalization value corresponding to each program index parameter, where the normalization processing unit is configured to: acquiring the number of all users corresponding to programs watched under each program label and program index parameters corresponding to all the users under each program label; determining the relative value of the program index parameter of the current user at each program label relative to all users; based on a maximum value and minimum value normalization calculation method and program index parameters corresponding to each user, obtaining relative values of the program index parameters of the current user on each program label relative to all users, and taking the obtained relative values as normalization values of the program index parameters under the program labels corresponding to the user;
the interest degree calculation unit is used for weighting and calculating a normalization value corresponding to each program index parameter under each program label corresponding to the current user to obtain the interest degree of the current user on the program corresponding to each program label;
wherein, if the program index parameter includes a viewing duration, the index calculating unit specifically includes:
determining each program label;
acquiring the watching time length of the user watching the program under each program label
；
Wherein the content of the first and second substances,
the time length of the program under the current program label watched by the user for the ith time is represented, n represents the total number of times of watching the program under the current program label watched by the user, i represents the time of watching the program under the current program label watched by the userI is more than or equal to 1 and n is more than or equal to i at the ith time;
if the program index parameter includes a viewing completion rate, the index calculation unit specifically includes:
determining each program label;
acquiring the times of watching each program by the user under the program label, the watching time length of each time and the original time length of each program to obtain the watching completion rate
；
Wherein the content of the first and second substances,
the time length of the program under the current program label watched by the user for the ith time is represented, n represents the total number of times of watching under the current program label by the user, i represents the ith time of watching under the current program label by the user, i is more than or equal to 1, n is more than or equal to i,
indicating the original time length of each time the user watches the program under the current program label.
6. A storage medium characterized by comprising a stored program, wherein the program, when executed by a processor, controls an apparatus in which the storage medium is located to perform the method of evaluating user interest level according to any one of claims 1 to 4.
7. An electronic device, comprising a processor, a memory, the memory storing a program executable on the processor, the processor being configured to execute the program, wherein the program when executed performs the method of evaluating user interest according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710888524.2A CN109561350B (en) | 2017-09-27 | 2017-09-27 | User interest degree evaluation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710888524.2A CN109561350B (en) | 2017-09-27 | 2017-09-27 | User interest degree evaluation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109561350A CN109561350A (en) | 2019-04-02 |
| CN109561350B true CN109561350B (en) | 2021-06-29 |
Family
ID=65863917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710888524.2A Active CN109561350B (en) | 2017-09-27 | 2017-09-27 | User interest degree evaluation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109561350B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111858564A (en) * | 2019-04-28 | 2020-10-30 | 腾讯科技（深圳）有限公司 | Data processing method, service processing method, device, terminal and storage medium |
| CN113590926A (en) * | 2020-04-30 | 2021-11-02 | 北京爱笔科技有限公司 | User interest identification method, device, equipment and computer readable medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102263992A (en) * | 2011-08-08 | 2011-11-30 | 上海文广互动电视有限公司 | Program recommendation degree estimation method based on user viewing record |
| CN103686236A (en) * | 2013-11-19 | 2014-03-26 | 乐视致新电子科技（天津）有限公司 | Method and system for recommending video resource |
| CN104935970A (en) * | 2015-07-09 | 2015-09-23 | 三星电子（中国）研发中心 | Method for recommending television content and television client |
| CN105095516A (en) * | 2015-09-16 | 2015-11-25 | 中国传媒大学 | Broadcast television subscriber grouping system and method based on spectral clustering integration |
| CN106802956A (en) * | 2017-01-19 | 2017-06-06 | 山东大学 | A kind of film based on weighting Heterogeneous Information network recommends method |
| CN107113466A (en) * | 2014-06-12 | 2017-08-29 | 慧与发展有限责任合伙企业 | To user's recommended project |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8249430B2 (en) * | 2007-04-18 | 2012-08-21 | Panasonic Corporation | Digital broadcast receiving apparatus and method for displaying images with programming information |
| US8510778B2 (en) * | 2008-06-27 | 2013-08-13 | Rovi Guides, Inc. | Systems and methods for ranking assets relative to a group of viewers |
-
2017
- 2017-09-27 CN CN201710888524.2A patent/CN109561350B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102263992A (en) * | 2011-08-08 | 2011-11-30 | 上海文广互动电视有限公司 | Program recommendation degree estimation method based on user viewing record |
| CN103686236A (en) * | 2013-11-19 | 2014-03-26 | 乐视致新电子科技（天津）有限公司 | Method and system for recommending video resource |
| CN107113466A (en) * | 2014-06-12 | 2017-08-29 | 慧与发展有限责任合伙企业 | To user's recommended project |
| CN104935970A (en) * | 2015-07-09 | 2015-09-23 | 三星电子（中国）研发中心 | Method for recommending television content and television client |
| CN105095516A (en) * | 2015-09-16 | 2015-11-25 | 中国传媒大学 | Broadcast television subscriber grouping system and method based on spectral clustering integration |
| CN106802956A (en) * | 2017-01-19 | 2017-06-06 | 山东大学 | A kind of film based on weighting Heterogeneous Information network recommends method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109561350A (en) | 2019-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106649316B (en) | Video pushing method and device | |
| CN110781321B (en) | Multimedia content recommendation method and device | |
| CN109600669B (en) | Object playing monitoring method and device, storage medium and processor | |
| US9032429B1 (en) | Determining importance of scenes based upon closed captioning data | |
| CN110149540B (en) | Recommendation processing method and device for multimedia resources, terminal and readable medium | |
| CN109255037B (en) | Method and apparatus for outputting information | |
| US11907817B2 (en) | System and methods for machine learning training data selection | |
| CN108614856B (en) | Video sequencing calibration method and device | |
| CN105308636A (en) | Apparatus and method for providing virtual advertisement | |
| CN108540860B (en) | Video recall method and device | |
| US20180130075A1 (en) | Analysis of media consumption for new media production | |
| CN109561350B (en) | User interest degree evaluation method and system | |
| CN111353071A (en) | Label generation method and device | |
| US11012744B2 (en) | Systems and methods for evaluating the engagement factor of videos | |
| CN110569429B (en) | Method, device and equipment for generating content selection model | |
| CN108881968B (en) | Network video advertisement putting method and system | |
| CN108764021B (en) | Cheating video identification method and device | |
| CN106658183B (en) | Pop up the method and device of video logon dialog frame | |
| CN109429104B (en) | Family member analysis method and related device | |
| CN111144702A (en) | Archive generation method, generation device, storage medium and processor | |
| CN109525864B (en) | Audience rating ranking method and device | |
| CN110648156A (en) | Advertisement processing method, device and equipment | |
| US11838600B2 (en) | System and method for modelling access requests to multi-channel content sharing platforms | |
| CN110245337B (en) | Method and device for generating trial finding sections in referee document | |
| CN113987034A (en) | Information display 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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100080 No. 401, 4th Floor, Haitai Building, 229 North Fourth Ring Road, Haidian District, Beijing Applicant after: Beijing Guoshuang Technology Co.,Ltd. Address before: 100086 Beijing city Haidian District Shuangyushu Area No. 76 Zhichun Road cuigongfandian 8 layer A Applicant before: Beijing Guoshuang Technology Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |