A system for predicting rating values of digital contents

Abstract

The present invention relates to a system (1) which correlates with the rating value in traditional media, can be placed in a range between a certain upper and lower value, and enables the content to find a digital rating value equivalent through the daily average value of the number of individual views, the number of viewing traffic in certain time intervals, and future episodes to be predicted through this metric.

Description

[0001] A SYSTEM FOR PREDICTING RATING VALUES OF DIGITAL CONTENTS

[0002] Technical Field

[0003] The present invention relates to a system which correlates with the rating value in traditional media, can be placed in a range between a certain upper and lower value, and enables the content to find a digital rating value equivalent through the daily average value of the number of individual views, the number of viewing traffic in certain time intervals, and future episodes to be predicted through this metric.

[0004] Background of the Invention

[0005] Today, with the rapid increase in digitalisation, machine learning and autonomous systems are gradually increasing their impact in the broadcasting sector in the age of artificial intelligence. In competitive systems, predicting or simulating expected situations as closely as possible to reality forms the basis of strategic and budgetary planning. In this process, it is important to evaluate alternative scenarios and reach the most appropriate conclusion. Furthermore, action plans in which the benefits and damages in case of their actualisation are also taken into consideration are prepared. Recently, the broadcasting sector continues its activities in two separate branches, namely traditional and digital media. The contents published in both fields are evaluated within the framework of measurement systems called rating metrics specific to their respective fields. In traditional media, the share that a broadcast content receives from measurement devices distributed randomly and secretly during the broadcast and at the time of measurement is called the rating value. The ratio of the said measurement devices only per television switched on is called the TVR value, and the share it receives from the TVR value is called the share value. The rating, which is considered as a success metric, is examined not on its own, but in relation to TVR and share values. It also has sub-divisions within itself at different socio-economic levels. On the other hand, there is no measurement system or metric similar to rating for the broadcast contents of digital media platforms, which have increased their influence in recent years and attracted intense interest. Generally, traffic data expressed by the number of individual viewers, i.e. the number of views, is based on. However, the fact that there is no information calculated under certain norms within a certain period of time, such as the rating values in traditional media, and its constant variability creates the need for a digital rating concept in digital media.

[0006] For this reason, considering the studies and deficiencies included in the current technique, it is understood that there is a need for a system which enables a more accurate, scalable and predictable metric to be developed, data sources to be expanded, new attributes and factors to be included in the model, more suitable machine learning models to be selected and used, and thus more accurate and reliable digital rating predictions to be made.

[0007] The United States patent document no. US2014289752A1, an application included in the state of the art, discloses a system and method for temporal rating and analysis of digital content in a digital content environment. In the said invention, one or more content service providers and a rating analytics server are communicatively connected via a communication network. A rating capture module is also included. Digital contents are sent to the end points by the content service providers. The temporal rating, inputs and / or reactions of consumers are dynamically captured by the rating capture module while viewing and / or listening to digital content on the end points. The captured temporal ratings, inputs and / or reactions are sent to the rating analytics server by the rating capture module. The received temporal rating, inputs and / or reactions are analysed and sent to the content service providers by the rating analytics server. Summary of the Invention

[0008] An object of the present invention is to realize a system which correlates with the rating value in traditional media, can be placed in a range between a certain upper and lower value, and developed with the aim of enabling the content to find a digital rating value equivalent through the daily average value of the number of individual views, the number of viewing traffic in certain time intervals, and future episodes to be predicted through this metric.

[0009] Another object of the present invention is to realize a system developed with the aim of enabling time-dependent changes of each actor, screenwriter, director or production company, each channel and content to be in an explanatory structure that increases the domain knowledge when the user is logging in with detailed images by performing a detailed analysis of the digital broadcasting sector, to be tested in live environments by being fed from a rich and large data set created with data obtained from a wide variety of sources, primarily from social media data; and obtaining consistent and comprehensive outputs consistent with the traditional media rating value by creating a unique digital rating metric.

[0010] Detailed Description of the Invention

[0011] “A System for Predicting Rating Values of Digital Contents” realized to fulfil the objectives of the present invention is shown in the figure attached, in which:

[0012] Figure l is a schematic view of the inventive system.

[0013] The components illustrated in the figure are individually numbered, where the numbers refer to the following:

[0014] 1. System 2. Electronic Device

[0015] 3. Interface

[0016] 4. Server

[0017] 5. Processor

[0018] The inventive system (1) developed with the aim of enabling the development of a model for predicting the ratings of digital media contents comprises: at least one electronic device (2) which is configured to exchange data by using any remote communication protocol and to run at least one application thereon; at least one interface (3) which is configured to be run on the electronic device (2), to run machine learning models thereon and to enable updated data to be automatically transferred to a dashboard; at least one server (4) which is configured to establish connection with the electronic device (2) and to establish communication with the interface (3) run on the electronic device (2) through this established connection by using any communication protocol, to access data sources in the form of digital media viewer numbers, social media interactions and trends and to transmit these data to the electronic device (2); at least one processor (5) which is configured to be run on the electronic device (2); to enable the necessary actions to be taken by predicting the next two episodes of the content in the digital broadcasting sector with the machine learning model; the rising or falling trends of the content to be captured; the value of the characteristic feature of the content in terms of rating to be created based on the viewer habits; and the rating value of the same content episodes belonging to the side channels of the same channel, if any, to be predicted individually; the impact of external factors such as weather, match information, special day or calendar data that will affect the rating value and internal factors such as channel, time and genre information of the content on the predicted rating values to be delivered to the end user with a machine learning model. The electronic device (2) included in the inventive system (1) is configured to exchange data by using any remote communication protocol and to run at least one application thereon. The electronic device (2) is a device in the form of a desktop computer and / or a portable computer. The electronic device (2) is configured to run the interface (3) and the processor (5) thereon. The electronic device (2) is configured to establish connection with the server (4) by using any remote communication protocol included in the state of art.

[0019] The interface (3) included in the inventive system (1) is configured to be run on the electronic device (2). The interface (3) is configured to run machine learning models thereon and to enable updated data to be automatically transferred to a dashboard and to be easily accessed by users.

[0020] The server (4) included in the inventive system (1) is configured to establish connection with the electronic device (2) and to establish communication with the interface (3) run on the electronic device (2) through this established connection by using any communication protocol included in the state of art. The server (4) is configured to access data sources in the form of digital media viewer numbers, social media interactions and trends, to collect these data and to transmit them to the electronic device (2).

[0021] The processor (5) included in the inventive system (1) is configured to be run on the electronic device (2). The processor (5) is configured to analyse data sources in the form of digital media viewer numbers, social media interactions and trends, and to identify deficiencies. The processor (5) is configured to perform a detailed analysis that includes the identification of factors affecting digital media content and how they can be used in the rating prediction in order to identify and integrate new data sources. The processor (5) is configured to create a digital rating metric with the corresponding values by normalising the values, obtained by calculating the daily average traffic data of each content based on 10-15 minute traffic views, between 1-10 across the entire data set. The processor (5) is configured to enable the amount of deviation or error to be reduced by recalculating the daily average traffic data with new data every week and normalisation process to be performed in order for the values to be maintained. The processor (5) is configured to apply statistical time series methods in order to capture seasonal effects of content such as broadcast season, viewer profile behaviours and habits, and relationships and effects with competing content. The processor (5) is configured to analyse different machine learning models that can be used for the creation and prediction of digital ratings. The processor (5) is configured to enable attribute engineering to be performed on the selected machine learning model in order to improve the success of the model, new statistical data to be included in the model and attributes to be improved. The processor (5) is configured to apply regression metrics in order to evaluate the success of the machine learning model and to analyse customer feedback. The processor (5) is configured to enable the necessary actions to be taken by predicting the next two episodes of the content in the digital broadcasting sector with the machine learning model; the rising or falling trends of the content to be captured; the value of the characteristic feature of the content in terms of rating to be created based on the viewer habits; and the rating value of the same content episodes belonging to the side channels of the same channel, if any, to be predicted individually. The processor (5) is configured to enable the impact of external factors such as weather, match information, special day or calendar data that will affect the rating value and internal factors such as channel, time and genre information of the content on the predicted rating values to be delivered to the end user with a machine learning model. The processor (5) is configured to update the collected and configured data at regular intervals, such as weekly and daily.

[0022] Industrial Application of the Invention

[0023] In the inventive system (1), time-dependent changes of each actor, screenwriter, director or production company, each channel and content are enabled to be in an explanatory structure that increases the domain knowledge when the user is logging in with detailed images by performing a detailed analysis of the digital broadcasting sector, and to be tested in live environments by being fed from a rich and large data set created with data obtained from a wide variety of sources, primarily from social media data; and consistent and comprehensive outputs consistent with the traditional media rating value to be obtained by creating a unique digital rating metric.

[0024] Within these basic concepts; it is possible to develop various embodiments of the inventive “A System (1) for Predicting Rating Values of Digital Contents”; the invention cannot be limited to examples disclosed herein and it is essentially according to claims.

Claims

CLAIMS1. A system (1) developed with the aim of enabling the development of a model for predicting the ratings of digital media contents; comprising at least one electronic device (2) which is configured to exchange data by using any remote communication protocol and to run at least one application thereon; at least one interface (3) which is configured to be run on the electronic device (2), to run machine learning models thereon and to enable updated data to be automatically transferred to a dashboard; at least one server (4) which is configured to establish connection with the electronic device (2) and to establish communication with the interface (3) run on the electronic device (2) through this established connection by using any communication protocol, to access data sources in the form of digital media viewer numbers, social media interactions and trends and to transmit these data to the electronic device (2); and characterized by at least one processor (5) which is configured to be run on the electronic device (2); to enable the necessary actions to be taken by predicting the next two episodes of the content in the digital broadcasting sector with the machine learning model; the rising or falling trends of the content to be captured; the value of the characteristic feature of the content in terms of rating to be created based on the viewer habits; and the rating value of the same content episodes belonging to the side channels of the same channel, if any, to be predicted individually; the impact of external factors such as weather, match information, special day or calendar data that will affect the rating value and internal factors such as channel, time and genre information of the content on the predicted rating values to be delivered to the end user with a machine learning model.

2. A system (1) according to Claim 1; characterized by the electronic device (2) which is a device in the form of a desktop computer and / or a portable computer configured to exchange data by using any remote communication protocol and to run at least one application thereon.

3. A system (1) according to Claim 1 or 2; characterized by the electronic device (2) which is configured to run the interface (3) and the processor (5) thereon.

4. A system (1) according to Claim 3; characterized by the electronic device (2) which is configured to establish connection with the server (4) by using any remote communication protocol.

5. A system (1) according to any one of the preceding claims; characterized by the interface (3) which is configured to be run on the electronic device (2).

6. A system (1) according to any one of the preceding claims; characterized by the interface (3) which is configured to run machine learning models thereon and to enable updated data to be automatically transferred to a dashboard and to be easily accessed by users.

7. A system (1) according to any one of the preceding claims; characterized by the server (4) which is configured to establish connection with the electronic device (2) and to establish communication with the interface (3) run on the electronic device (2) through this established connection by using any communication protocol included in the state of art.

8. A system (1) according to any one of the preceding claims; characterized by the server (4) which is configured to access data sources in the form of digital media viewer numbers, social media interactions and trends, to collect these data and to transmit them to the electronic device (2).

9. A system (1) according to any one of the preceding claims; characterized by the processor (5) which is configured to be run on the electronic device (2).

10. A system (1) according to any one of the preceding claims; characterized by the processor (5) which is configured to analyse data sources in the form of digital media viewer numbers, social media interactions and trends, and to identify deficiencies.

11. A system (1) according to any one of the preceding claims; characterized by the processor (5) which is configured to perform a detailed analysis that includes the identification of factors affecting digital media content and how they can be used in the rating prediction in order to identify and integrate new data sources.

12. A system (1) according to any one of the preceding claims; characterized by the processor (5) which is configured to create a digital rating metric with the corresponding values by normalising the values, obtained by calculating the daily average traffic data of each content based on 10-15 minute traffic views, between 1-10 across the entire data set.

13. A system (1) according to any one of the preceding claims; characterized by the processor (5) which is configured to enable the amount of deviation or error to be reduced by recalculating the daily average traffic data with new data every week and normalisation process to be performed in order for the values to be maintained.

14. A system (1) according to any one of the preceding claims; characterized by the processor (5) which is configured to apply statistical time series methods in order to capture seasonal effects of contents such as broadcast season, viewer profile behaviours and habits, and relationships and effects with competing content.

15. A system (1) according to any one of the preceding claims; characterized by the processor (5) which is configured to analyse different machine learning models that can be used for the creation and prediction of digital ratings.

16. A system (1) according to any one of the preceding claims; characterized by the processor (5) which is configured to enable attribute engineering to be performed on the selected machine learning model in order to improve the success of the model, new statistical data to be included in the model and attributes to be improved.

17. A system (1) according to any one of the preceding claims; characterized by the processor (5) which is configured to apply regression metrics in order to evaluate the success of the machine learning model and to analyse customer feedback.

18. A system (1) according to any one of the preceding claims; characterized by the processor (5) which is configured to enable the necessary actions to be taken by predicting the next two episodes of the content in the digital broadcasting sector with the machine learning model; the rising or falling trends of the content to be captured; the value of the characteristic feature of the content in terms of rating to be created based on the viewer habits; and the rating value of the same content episodes belonging to the side channels of the same channel, if any, to be predicted individually.

19. A system (1) according to any one of the preceding claims; characterized by the processor (5) which is configured to enable the impact of external factors such as weather, match information, special day or calendar data that will affect the rating value and internal factors such as channel, time and genre information of the content on the predicted rating values to be delivered to the end user with a machine learning model.

20. A system (1) according to any one of the preceding claims; characterized by the processor (5) which is configured to update the collected and configured data at regular intervals, such as weekly and daily.

Images