Iptv video program recommendation method and device, electronic equipment and storage medium

Abstract

The present application relates to the technical field of film and television big data analysis, and particularly relates to an IPTV film and television program recommendation method and device, electronic equipment and a storage medium. The method comprises the following steps: firstly, obtaining a plurality of viewing ranking data sets and a plurality of freshness scores; then, determining a plurality of heat scores representing the heat of a plurality of database film and television programs according to the plurality of viewing ranking data sets and the source channels of the plurality of viewing ranking data sets; next, scoring the plurality of database film and television programs according to the plurality of freshness scores and the plurality of heat scores; and finally, placing the plurality of film and television programs in a plurality of first recommendation positions according to the scores of the plurality of database film and television programs. According to the source channels of the plurality of viewing ranking data sets, different weights are given to the plurality of viewing ranking data sets, and the database film and television programs are scored in combination with the freshness of the film and television programs, so that the film and television program scores are more in line with the viewing needs of IPTV users, and the efficiency of the users in searching for programs is improved.

Description

Technical Field

[0001] This invention relates to the field of film and television big data analysis technology, and in particular to an IPTV film and television program recommendation method, device, electronic device and storage medium. Background Technology

[0002] The development of the internet has given rise to online video and promoted the dissemination of film and television programs. Compared with the internet, IPTV has the advantages of real-time performance and simple operation, and its target audience differs somewhat from that of the internet.

[0003] To make it easier for users to watch more exciting movies and TV shows, IPTV is gradually developing film and television program rating and recommendation services. However, traditional film and television recommendation methods are based solely on overall online popularity, without considering the release time of the content on the platform or the target audience. Recommendations based on this alone do not meet the viewing needs of IPTV users, resulting in low efficiency for users searching for programs.

[0004] Therefore, it is necessary to develop and design an IPTV movie and TV program recommendation method. Summary of the Invention

[0005] The present invention provides an IPTV movie and TV program recommendation method, apparatus, electronic device and storage medium to solve the problem of low efficiency for IPTV users when searching for programs in the prior art.

[0006] In a first aspect, embodiments of the present invention provide an IPTV movie and TV program recommendation method, comprising:

[0007] Multiple viewership ranking datasets and multiple freshness scores are obtained. The viewership ranking datasets represent the ranking of the film and television programs in the database, and the freshness scores represent the duration of the film and television programs in the database. The film and television programs in the database are the film and television programs owned by the film and television program database.

[0008] Based on the multiple viewership ranking datasets and the source channels of the multiple viewership ranking datasets, multiple popularity scores representing the popularity of film and television programs in multiple databases are determined;

[0009] The multiple database film and television programs are scored based on the multiple freshness scores and the multiple popularity scores;

[0010] Based on the ratings of the multiple film and television programs in the database, the multiple film and television programs are placed in multiple first recommendation positions, among which the first recommendation position has the largest traffic data on its respective recommendation page.

[0011] In one possible implementation, determining multiple popularity scores characterizing the popularity of film and television programs in multiple databases based on the multiple viewership ranking datasets and the source channels of the multiple viewership ranking datasets includes:

[0012] Based on the source channels of the multiple viewership ranking datasets, each of the multiple viewership ranking datasets is assigned a popularity evaluation weight;

[0013] Based on the first formula, the multiple viewership ranking datasets, and the multiple popularity evaluation weights, the multiple popularity scores are determined, wherein the first formula is:

[0014]

[0015] In the formula, For the first A database of film and television program popularity scores. For the first The popularity evaluation weights of each dataset For the first The database of film and television programs is in the first Data from one dataset, For the number of datasets, The number of film and television programs in the database.

[0016] In one possible implementation, assigning popularity evaluation weights to the plurality of viewership ranking datasets based on their source channels includes:

[0017] Multiple historical rating datasets are obtained, wherein the historical rating datasets include a first array representing the ranking of the number of views within a historical period, a second array representing the ranking of the popularity scores of the multiple database film and television programs within the historical period, and a popularity evaluation weight array. The popularity evaluation weight array includes multiple popularity evaluation weights for the historical period, and the popularity scores of the multiple database film and television programs within the historical period are determined based on the multiple popularity evaluation weights for the historical period.

[0018] Based on the multiple historical rating datasets, multiple popularity evaluation residual arrays are constructed, wherein the popularity evaluation residual arrays represent the deviation between the first array and the second array of the historical rating datasets, and the multiple popularity evaluation residual arrays correspond to the multiple historical rating datasets;

[0019] Obtain the relationship model between the expression popularity evaluation weight array and the popularity evaluation residual array, wherein the relationship model includes multiple undetermined parameters;

[0020] Based on the popularity evaluation weight array and the popularity evaluation residual array of the multiple historical rating datasets, multiple undetermined parameters in the relational model are determined to establish the relational model;

[0021] Based on the relationship model, the popularity evaluation weights are assigned to the multiple datasets respectively.

[0022] In one possible implementation, the relational model is:

[0023]

[0024] In the formula, The first residual array for heat evaluation One element, For the first of multiple undetermined parameters One parameter.

[0025] In one possible implementation, assigning the popularity evaluation weights to the plurality of datasets according to the relational model includes:

[0026] Obtain the perturbation array and the input weight array, wherein the input weight array is the popularity evaluation weight array of the previous period;

[0027] The input weight array is input into the relation model, and the output of the relation model is used as the first residual output array;

[0028] Scrambling step: Superimpose the input weight array with the perturbation array to obtain a scrambled input weight array;

[0029] The scrambled input weight array is input into the relation model, and the output of the relation model is used as the second residual output array;

[0030] If the modulus of the second residual output array is less than the modulus threshold, then multiple elements of the scrambling input weight array are assigned to the multiple datasets;

[0031] Otherwise, the perturbation array is adjusted according to the third formula, the first residual output array, the second residual output array, the input weight array, and the scrambling input weight array, wherein the third formula is:

[0032]

[0033] In the formula, For the adjusted perturbation array One element, To adjust the coefficient, The first residual output array is the first One element, The second residual output array One element, The perturbation array before adjustment One element;

[0034] Use the second residual output array as the first residual output array, and proceed to the scrambling step.

[0035] In one possible implementation, the step of scoring the multiple database film and television programs based on the multiple freshness scores and the multiple popularity scores includes:

[0036] Assign freshness weights to the multiple freshness scores;

[0037] The multiple database film and television programs are scored according to the second formula, the freshness weight, the multiple freshness scores, and the multiple popularity scores, wherein the second formula is:

[0038]

[0039] In the formula, For the first The ratings of movies and TV shows in a database. As a weighting factor for freshness, For the first The freshness score of film and television programs in a database. For the first A database of film and television program popularity scores.

[0040] In one possible implementation, placing multiple film and television programs in multiple first recommendation positions based on their ratings from the multiple databases includes:

[0041] Obtain multiple film and television program recommendations and multiple first recommendation positions obtained by the IPTV film and television program recommendation method described in the first aspect or any possible implementation of the first aspect, wherein the first recommendation position has the largest traffic data in the recommendation page to which it belongs;

[0042] Based on the attributes of multiple recommendation pages, multiple target film and television programs are selected from the multiple film and television program ratings, wherein the target film and television program is the film and television program with the highest rating among the film and television programs that match the attributes of the recommendation pages.

[0043] Based on the attributes of the multiple target film and television programs, the multiple target film and television programs are placed in the multiple first recommendation positions.

[0044] Secondly, embodiments of the present invention provide a film and television program recommendation device for implementing the IPTV film and television program recommendation method as described in the first aspect or any possible implementation thereof, the film and television program recommendation device comprising:

[0045] The data acquisition module is used to acquire multiple viewership ranking datasets and multiple freshness scores. The viewership ranking datasets represent the ranking of film and television programs in the database, and the freshness scores represent the online duration of film and television programs in the database. The film and television programs in the database are the film and television programs owned by the film and television program database.

[0046] The popularity score determination module is used to determine multiple popularity scores that characterize the popularity of film and television programs in multiple databases based on the multiple viewership ranking datasets and the source channels of the multiple viewership ranking datasets.

[0047] The scoring module is used to score the multiple database film and television programs based on the multiple freshness scores and the multiple popularity scores;

[0048] as well as,

[0049] The film and television program recommendation module is used to place multiple film and television programs in multiple first recommendation positions based on the ratings of film and television programs in the multiple databases. Among them, the first recommendation position has the largest traffic data on its respective recommendation page.

[0050] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor executes the computer program to implement the steps of the method as described in the first aspect or any possible implementation of the first aspect.

[0051] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method as described in the first aspect or any possible implementation thereof.

[0052] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows:

[0053] This invention discloses an IPTV movie and TV program recommendation method. First, it acquires multiple viewership ranking datasets and multiple freshness scores. The viewership ranking datasets represent the ranking of movies and TV programs in a database, and the freshness scores represent the online duration of the programs. The database consists of movies and TV programs owned by a movie and TV program database. Then, based on the multiple viewership ranking datasets and their source channels, multiple popularity scores representing the popularity of the movies and TV programs in the database are determined. Next, the multiple freshness scores and popularity scores are used to rate the movies and TV programs in the database. Finally, based on the ratings of the multiple movies and TV programs in the database, the programs are placed in multiple first recommendation positions, where the first recommendation position receives the most traffic on its respective recommendation page. This invention assigns different weights to multiple viewership ranking datasets based on their source channels and combines this with the freshness of the movies and TV programs to rate them. By incorporating the number of views by IPTV users when assigning weights to the viewership ranking datasets, the ratings of the movies and TV programs better match the viewing needs of IPTV users, improving the efficiency of users finding programs. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 This is a flowchart of the IPTV movie and TV program recommendation method provided in the embodiments of the present invention;

[0056] Figure 2 This is a schematic diagram of the recommendation page provided by an embodiment of the present invention;

[0057] Figure 3 This is a functional block diagram of the film and television program recommendation device provided in the embodiments of the present invention;

[0058] Figure 4 This is a functional block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0059] In the following description, specific details such as particular system structures and techniques are set forth for illustrative purposes and not for limitation, so as to provide a thorough understanding of embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0060] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments will be described below in conjunction with the accompanying drawings.

[0061] The embodiments of the present invention will be described in detail below. This example is implemented based on the technical solution of the present invention, and provides detailed implementation methods and specific operation processes. However, the protection scope of the present invention is not limited to the following embodiments.

[0062] Figure 1 A flowchart illustrating the IPTV movie and TV program recommendation method provided in an embodiment of the present invention.

[0063] like Figure 1 As shown, a flowchart illustrating the implementation of the IPTV movie and TV program recommendation method provided by an embodiment of the present invention is presented, and is described in detail below:

[0064] In step 101, multiple viewership ranking datasets and multiple freshness scores are obtained. The viewership ranking datasets represent the ranking of the film and television programs in the database, and the freshness scores represent the duration of the film and television programs in the database. The film and television programs in the database are the film and television programs owned by the film and television program database.

[0065] In some implementations, the process may also include filtering invalid data from the plurality of viewership ranking datasets so that the data in the plurality of viewership ranking datasets corresponds to the film and television programs in the database.

[0066] For example, as mentioned earlier, the internet has extensive reach in recommending and ranking film and television programs, and ratings for these programs are relatively easy to obtain. For IPTV, this data can serve as a basis for recommending film and television programs, thereby constructing a viewership ranking dataset. In this embodiment of the invention, the viewership ranking dataset is divided according to the source channels of the ratings and ranking data. For example, ranking data from website A is processed to obtain a first viewership ranking dataset, and ranking data from website B is processed to obtain a second viewership ranking dataset. Freshness is data set based on the time a film or television program is available on IPTV. For example, the time a film or television program is uploaded to a broadcast television platform is obtained, and a freshness score is assigned based on the upload time: 10 points for within three days, 7 points for within one week, 5 points for within one month, 3 points for within three months, 2 points for within six months, 1 point for within one year, and no score for more than one year.

[0067] Some of the movie and TV program rankings obtained from websites are not available on IPTV. In this case, we need to filter the data and only keep the rankings of movies and TV programs that exist in the database.

[0068] In step 102, based on the multiple viewership ranking datasets and the source channels of the multiple viewership ranking datasets, multiple popularity scores representing the popularity of film and television programs in multiple databases are determined.

[0069] In some embodiments, step 102 includes:

[0070] Based on the source channels of the multiple viewership ranking datasets, each of the multiple viewership ranking datasets is assigned a popularity evaluation weight;

[0071] Based on the first formula, the multiple viewership ranking datasets, and the multiple popularity evaluation weights, the multiple popularity scores are determined, wherein the first formula is:

[0072]

[0073] In the formula, For the first A database of film and television program popularity scores. For the first The popularity evaluation weights of each dataset For the first The database of film and television programs is in the first Data from one dataset, For the number of datasets, The number of film and television programs in the database.

[0074] In some implementations, assigning popularity evaluation weights to the plurality of viewership ranking datasets based on their source channels includes:

[0075] Multiple historical rating datasets are obtained, wherein the historical rating datasets include a first array representing the ranking of the number of views within a historical period, a second array representing the ranking of the popularity scores of the multiple database film and television programs within the historical period, and a popularity evaluation weight array. The popularity evaluation weight array includes multiple popularity evaluation weights for the historical period, and the popularity scores of the multiple database film and television programs within the historical period are determined based on the multiple popularity evaluation weights for the historical period.

[0076] Based on the multiple historical rating datasets, multiple popularity evaluation residual arrays are constructed, wherein the popularity evaluation residual arrays represent the deviation between the first array and the second array of the historical rating datasets, and the multiple popularity evaluation residual arrays correspond to the multiple historical rating datasets;

[0077] Obtain the relationship model between the expression popularity evaluation weight array and the popularity evaluation residual array, wherein the relationship model includes multiple undetermined parameters;

[0078] Based on the popularity evaluation weight array and the popularity evaluation residual array of the multiple historical rating datasets, multiple undetermined parameters in the relational model are determined to establish the relational model;

[0079] Based on the relationship model, the popularity evaluation weights are assigned to the multiple datasets respectively.

[0080] In some implementations, the relational model is as follows:

[0081]

[0082] In the formula, The first residual array for heat evaluation One element, For the first of multiple undetermined parameters One parameter.

[0083] In some implementations, assigning popularity evaluation weights to the plurality of datasets according to the relational model includes:

[0084] Obtain the perturbation array and the input weight array, wherein the input weight array is the popularity evaluation weight array of the previous period;

[0085] The input weight array is input into the relation model, and the output of the relation model is used as the first residual output array;

[0086] Scrambling step: Superimpose the input weight array with the perturbation array to obtain a scrambled input weight array;

[0087] The scrambled input weight array is input into the relation model, and the output of the relation model is used as the second residual output array;

[0088] If the modulus of the second residual output array is less than the modulus threshold, then multiple elements of the scrambling input weight array are assigned to the multiple datasets;

[0089] Otherwise, the perturbation array is adjusted according to the third formula, the first residual output array, the second residual output array, the input weight array, and the scrambling input weight array, wherein the third formula is:

[0090]

[0091] In the formula, For the adjusted perturbation array One element, To adjust the coefficient, The first residual output array is the first One element, The second residual output array One element, The perturbation array before adjustment One element;

[0092] Use the second residual output array as the first residual output array, and proceed to the scrambling step.

[0093] For example, popularity represents the degree to which a film or television program is popular with users. This embodiment of the invention determines popularity based on the aforementioned viewership ranking datasets from different sources. Specifically, the datasets are weighted according to their respective sources, and then, based on the ranking data and weights of the film or television program in different datasets, a popularity score is determined. This embodiment of the invention provides a formula for calculating the popularity score:

[0094]

[0095] In the formula, For the first A database of film and television program popularity scores. For the first The popularity evaluation weights of each dataset For the first The database of film and television programs is in the first Data from one dataset, For the number of datasets, The number of film and television programs in the database.

[0096] The formula above calculates the popularity score, which actually reflects the popularity of film and television programs on broadcast television platforms. Its accuracy is affected not only by the source of the dataset but also by the weighting.

[0097] One way to verify the accuracy of popularity scores is to compare the difference between popularity score rankings and view count rankings. Therefore, this invention adjusts the popularity evaluation weights by comparing the differences between the two.

[0098] Specifically, this invention provides a model that expresses the weighting of popularity evaluation and the ranking residual (ranking difference). By analyzing the differences between historical popularity score rankings and view count rankings, as well as the weights from each ranking, multiple parameters of the model are determined, thus completing the model construction. Finally, this relational model is used to adjust the current weights, thereby obtaining the popularity evaluation weights.

[0099] In one application scenario, this relational model is as follows:

[0100]

[0101] In the formula, The first residual array for heat evaluation One element, For the first of multiple undetermined parameters One parameter.

[0102] We can see that this model has There are several parameters, therefore, at least [number] are required. Data from several historical periods are used to solve for multiple undetermined parameters.

[0103] Once the parameters are determined, the model is complete.

[0104] Regarding the determination of popularity evaluation weights, in this embodiment of the invention, the current multiple popularity evaluation weights are used as an input weight array and input into the relational model. The output of the relational model at this time is used as the first residual output array.

[0105] Then, the input weight array is perturbed, and the perturbed input weight array is input into the model again. The resulting output is used as the second residual output array.

[0106] If the magnitude of the second residual output array is less than the threshold (the residual is less than expected), it means that the weight array with added perturbation can make the popularity score ranking more consistent with the number of views ranking. Multiple elements in the weight array with added perturbation can be used as multiple new popularity evaluation weights.

[0107] Otherwise, adjust the perturbation array using the third formula:

[0108]

[0109] In the formula, For the adjusted perturbation array One element, To adjust the coefficient, The first residual output array is the first One element, The second residual output array One element, The perturbation array before adjustment Each element.

[0110] After adjusting the perturbation array, the second residual output array is used as the first residual output array, and the process jumps back to the scrambling step. This process is repeated until the popularity score ranking and the number of views ranking converge to a relatively consistent level.

[0111] In step 103, the multiple database film and television programs are scored based on the multiple freshness scores and the multiple popularity scores.

[0112] In some embodiments, step 103 includes:

[0113] Assign freshness weights to the multiple freshness scores;

[0114] The multiple database film and television programs are scored according to the second formula, the freshness weight, the multiple freshness scores, and the multiple popularity scores, wherein the second formula is:

[0115]

[0116] In the formula, For the first The ratings of movies and TV shows in a database. As a weighting factor for freshness, For the first The freshness score of film and television programs in a database. For the first A database of film and television program popularity scores.

[0117] For example, the final rating of a film or television program is determined based on its freshness score and the popularity score obtained in the above steps. In this embodiment of the invention, the freshness score is assigned a weight, and the rating of the film or television program is determined based on the weight of the freshness score, the freshness score, and the popularity score. The formula for calculating the rating is as follows:

[0118]

[0119] In the formula, For the first The ratings of movies and TV shows in a database. As a weighting factor for freshness, For the first The freshness score of film and television programs in a database. For the first A database of film and television program popularity scores.

[0120] In step 104, based on the ratings of the multiple database film and television programs, the multiple film and television programs are placed in multiple first recommendation positions, where the first recommendation position has the largest traffic data on its respective recommendation page.

[0121] In some embodiments, step 104 includes:

[0122] Obtain the plurality of first recommendation positions, wherein the first recommendation position has the largest traffic data on its respective recommendation page;

[0123] Based on the attributes of multiple recommendation pages, multiple target film and television programs are selected from the multiple film and television program ratings, wherein the target film and television program is the film and television program with the highest rating among the film and television programs that match the attributes of the recommendation pages.

[0124] Based on the attributes of the multiple target film and television programs, the multiple target film and television programs are placed in the multiple first recommendation positions.

[0125] For example, such as Figure 2 As shown in the diagram, this illustrates a schematic of a recommendation page 201. In some application scenarios, recommendation pages 201 are divided into multiple parts, such as a homepage recommendation page, a children's recommendation page, a movie recommendation page, etc. Each recommendation page 201 has multiple recommendation slots 202. Obviously, these recommendation slots 202 have different traffic data (different click volumes). The recommendation slot 202 with the highest traffic data in each recommendation page 201 is selected as the first recommendation slot, thus obtaining multiple first recommendation slots for the corresponding multiple recommendation pages 201.

[0126] Since each recommendation page 201 has different attributes, the film and television program ratings obtained from the first aspect are categorized according to the attributes of the recommendation page 201 (for example, the ratings are divided into general, children's, and movies), and the film and television programs with the highest ratings after these categories are placed in the first recommendation position of the corresponding recommendation page 201.

[0127] This invention discloses an IPTV movie and TV program recommendation method. First, it acquires multiple viewership ranking datasets and multiple freshness scores. The viewership ranking datasets represent the ranking of movies and TV programs in a database, and the freshness scores represent the duration of their online availability. The database consists of movies and TV programs owned by a movie and TV program database. Then, based on the multiple viewership ranking datasets and their source channels, multiple popularity scores representing the popularity of the movies and TV programs in the database are determined. Next, the multiple freshness scores and popularity scores are used to rate the movies and TV programs in the database. Finally, based on the ratings of the multiple movies and TV programs in the database, the programs are placed in multiple first recommendation positions, where the first recommendation position receives the highest traffic on its respective recommendation page. This invention assigns different weights to multiple viewership ranking datasets based on their source channels and combines this with the freshness of the movies and TV programs to rate them. By incorporating the number of views by IPTV users when assigning weights to the viewership ranking datasets, the ratings of the movies and TV programs better match the viewing needs of IPTV users, improving the efficiency of users finding programs.

[0128] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0129] The following are embodiments of the apparatus of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0130] Figure 3 This is a functional block diagram of the film and television program recommendation device provided in the embodiments of the present invention, with reference to... Figure 3 The film and television program recommendation device includes: a data acquisition module 301, a popularity score determination module 302, a rating module 303, and a film and television program recommendation module 304, wherein:

[0131] The data acquisition module 301 is used to acquire multiple viewership ranking datasets and multiple freshness scores. The viewership ranking datasets represent the ranking of film and television programs in the database, and the freshness scores represent the online duration of film and television programs in the database. The film and television programs in the database are the film and television programs owned by the film and television program database.

[0132] The popularity score determination module 302 is used to determine multiple popularity scores that characterize the popularity of film and television programs in multiple databases based on the multiple viewership ranking datasets and the source channels of the multiple viewership ranking datasets.

[0133] The scoring module 303 is used to score the multiple database film and television programs based on the multiple freshness scores and the multiple popularity scores;

[0134] The film and television program recommendation module 304 is used to place multiple film and television programs in multiple first recommendation positions based on the ratings of film and television programs in the multiple databases, wherein the first recommendation position has the largest traffic data on its respective recommendation page.

[0135] Figure 4 This is a functional block diagram of the electronic device provided in an embodiment of the present invention. For example... Figure 4 As shown, the electronic device 4 of this embodiment includes a processor 400 and a memory 401, wherein the memory 401 stores a computer program 402 that can run on the processor 400. When the processor 400 executes the computer program 402, it implements the steps of the various IPTV film and television program recommendation methods and embodiments described above, for example... Figure 1 Steps 101 to 104 are shown.

[0136] For example, the computer program 402 may be divided into one or more modules / units, which are stored in the memory 401 and executed by the processor 400 to complete the present invention.

[0137] The electronic device 4 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. The electronic device 4 may include, but is not limited to, a processor 400 and a memory 401. Those skilled in the art will understand that... Figure 4 This is merely an example of electronic device 4 and does not constitute a limitation on electronic device 4. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device 4 may also include input / output devices, network access devices, buses, etc.

[0138] The processor 400 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0139] The memory 401 can be an internal storage unit of the electronic device 4, such as a hard disk or memory. The memory 401 can also be an external storage device of the electronic device 4, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 401 can include both internal and external storage units of the electronic device 4. The memory 401 is used to store the computer program 402 and other programs and data required by the electronic device 4. The memory 401 can also be used to temporarily store data that has been output or will be output.

[0140] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the aforementioned method embodiments, and will not be repeated here.

[0141] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0142] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0143] In the embodiments provided by this invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0144] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0145] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0146] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above-described embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various methods and apparatus embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0147] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. An IPTV program recommendation method, characterized in that, The method comprises the following steps: obtaining a plurality of rating data sets and a plurality of freshness scores, wherein the rating data set represents the ranking of a database movie and television program, and the freshness score represents the time length of the online database movie and television program, and the database movie and television program is a movie and television program owned by a database movie and television program; determining a plurality of heat scores representing the heat of a plurality of database movie and television programs according to the plurality of rating data sets and the source channels of the plurality of rating data sets; scoring the plurality of database movie and television programs according to the plurality of freshness scores and the plurality of heat scores; placing a plurality of movie and television programs in a plurality of first recommended positions according to the scores of the plurality of database movie and television programs, wherein the first recommended position has the maximum traffic data in the recommended page; wherein the determination of the plurality of heat scores representing the heat of the plurality of database movie and television programs according to the plurality of rating data sets and the source channels of the plurality of rating data sets comprises: assigning heat evaluation weights to the plurality of rating data sets according to the source channels of the plurality of rating data sets; determining the plurality of heat scores according to a first formula, the plurality of rating data sets and the plurality of heat evaluation weights, wherein the first formula is: In the formula, is the number of the database, is the number of the database, is the number of the database, is the number of the database, is the number of the database, is the number of the database, is the number of the database, is the number of the database, is the number of the database. the assigning of the heat evaluation weights to the plurality of rating data sets according to the source channels of the plurality of rating data sets comprises: obtaining a plurality of scoring history data sets, wherein the scoring history data set comprises a first array representing the viewing frequency ranking in a historical period, a second array representing the heat score ranking of the plurality of database movie and television programs in the historical period, and a heat evaluation weight array comprising a plurality of heat evaluation weights of the historical period, and the heat scores of the plurality of database movie and television programs in the historical period are determined according to the plurality of heat evaluation weights of the historical period; constructing a plurality of heat evaluation residual arrays according to the plurality of scoring history data sets, wherein the heat evaluation residual array represents the deviation between the first array of the scoring history data set and the second array of the scoring history data set, and the plurality of heat evaluation residual arrays correspond to the plurality of scoring history data sets; obtaining a relationship model expressing the relationship between the heat evaluation weight array and the heat evaluation residual array, wherein the relationship model comprises a plurality of undetermined parameters; determining the plurality of undetermined parameters in the relationship model according to the heat evaluation weight array of the plurality of scoring history data sets and the plurality of heat evaluation residual arrays, so as to establish the relationship model; assigning the heat evaluation weights to the plurality of data sets according to the relationship model.

2. The IPTV video program recommendation method of claim 1, wherein, The relationship model is: In the formula, is the first element of the residual array evaluated for hotness, is the first element of the residual array evaluated for hotness, is the first element of the residual array evaluated for hotness, is the first element of the residual array evaluated for hotness.

3. The IPTV video program recommendation method of claim 1, wherein, the assigning of the heat evaluation weights to the plurality of data sets according to the relationship model comprises: obtaining a perturbation array and an input weight array, wherein the input weight array is a heat evaluation weight array of a previous period; inputting the input weight array into the relationship model, and taking the output of the relationship model as a first residual output array; a scrambling step of superimposing the input weight array and the perturbation array to obtain a scrambled input weight array; inputting the scrambled input weight array into the relational model, and taking an output of the relational model as a second residual output array; if a modulus of the second residual output array is less than a modulus threshold, assigning multiple elements of the scrambled input weight array to the multiple data sets; otherwise, adjusting the perturbation array according to a third formula, the first residual output array, the second residual output array, the input weight array, and the scrambled input weight array, wherein the third formula is: wherein is the i-th element of the adjusted perturbation array, is the i-th element of the adjusted perturbation array, is the adjustment coefficient, is the i-th element of the first residual output array, is the i-th element of the first residual output array, is the i-th element of the second residual output array, is the i-th element of the second residual output array, is the i-th element of the perturbation array before adjustment, and is the i-th element of the perturbation array before adjustment. taking the second residual output array as the first residual output array, and jumping to the scrambling step.

4. The IPTV video program recommendation method of claim 1, wherein, The scoring the multiple database video programs according to the multiple freshness scores and the multiple heat scores includes: assigning a freshness weight to the multiple freshness scores; scoring the multiple database video programs according to a second formula, the freshness weight, the multiple freshness scores, and the multiple heat scores, wherein the second formula is: In the formula, is the score of the th database video program, is the freshness weight, is the freshness score of the th database video program, is the heat score of the th database video program.

5. The IPTV video program recommendation method according to any one of claims 1-4, characterized in that, The placing multiple video programs into multiple first recommendation positions according to the scores of the multiple database video programs includes: obtaining the multiple first recommendation positions; selecting multiple target video programs from the multiple video program scores according to attributes of multiple recommendation pages, wherein a target video program is a video program with the highest score among the video programs that meet the attributes of the recommendation pages; placing the multiple target video programs into the multiple first recommendation positions according to attributes of the multiple target video programs.

6. A video program recommendation apparatus characterized by comprising: The video program recommendation device for implementing the IPTV video program recommendation method according to any one of claims 1-5 includes: a data obtaining module, configured to obtain multiple viewing ranking data sets and multiple freshness scores, wherein a viewing ranking data set represents a ranking of a database video program, and a freshness score represents a time length of online of a database video program, the database video program being a video program owned by a video program database; a heat score determining module, configured to determine multiple heat scores representing heat of multiple database video programs according to the multiple viewing ranking data sets and source channels of the multiple viewing ranking data sets; a scoring module, configured to score the multiple database video programs according to the multiple freshness scores and the multiple heat scores; and a video program recommendation module, configured to place multiple video programs into multiple first recommendation positions according to scores of the multiple database video programs, wherein a first recommendation position has the maximum traffic data in a recommendation page to which the first recommendation position belongs.

7. An electronic device comprising a memory and a processor, said memory having stored therein a computer program operable on said processor, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1-5.

8. A computer-readable storage medium storing a computer program, the computer-readable storage medium comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 7. The computer program is executed by the processor to implement the steps of the method according to any one of claims 1-5.

Images