Media information-based processing method and apparatus, device, storage medium, and product

Abstract

The present disclosure provides a processing method and device based on media information, equipment, storage medium and product, which relates to the technical field of computer. The method comprises: aggregating the media information based on the similarity of the preset content attribute dimension to obtain a plurality of first media information sets, the media information in the same first media information set corresponding to the same at least one associated object, screening the first media information set whose content meets the preset requirement from the first media information set to obtain a second media information set, determining the theme information of the second media information set according to the associated information of the media information, determining the sorting of the theme information based on the heat information of the second media information set, and determining the target theme information according to the sorting result, wherein the target theme information is used for display in the preset theme set page. By adopting the above technical scheme, the display effect of the theme information can be improved, and the content quality of the media information set associated with the theme information can be ensured.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more particularly to methods, apparatus, devices, storage media, and products for processing media information. Background Technology

[0002] With the continuous development of internet technology, users can browse a wide variety of media information, such as videos or text and images, and can also share their own works by publishing media information.

[0003] To help users quickly find information, trending information, such as popular events or topics, can be identified based on its popularity and other relevant attributes. This trending information can then be displayed on pages like trending topics lists for easy browsing. However, currently, it's typically displayed as a text list, which is monotonous and doesn't provide an ideal viewing experience. Summary of the Invention

[0004] This disclosure provides methods, apparatus, devices, storage media, and products for processing media information, which can optimize existing media information processing solutions.

[0005] In a first aspect, embodiments of this disclosure provide a processing method based on media information, including:

[0006] Media information is aggregated based on the similarity of preset content attribute dimensions to obtain multiple first media information sets, wherein the media information in the same first media information set corresponds to the same at least one associated object;

[0007] The first media information set whose content meets the preset requirements is selected from the first media information set to obtain the second media information set;

[0008] Based on the association information of at least one media information in the second media information set, determine the theme information corresponding to the second media information set;

[0009] Based on the popularity information of the second media information set, the ranking of the topic information corresponding to the multiple second media information sets is determined, and the ranking result is obtained;

[0010] The target topic information is determined based on the sorting result, wherein the target topic information is at least one of the topic information, and the target topic information is used to be displayed on the preset topic collection page.

[0011] Secondly, embodiments of this disclosure also provide a processing apparatus based on media information, including:

[0012] The aggregation module is used to aggregate media information based on the similarity of preset content attribute dimensions to obtain multiple first media information sets, wherein the media information in the same first media information set corresponds to the same at least one associated object;

[0013] The set filtering module is used to filter out the first media information set whose content meets the preset requirements from the first media information set, and obtain the second media information set;

[0014] The topic determination module is used to determine the topic information corresponding to the second media information set based on the association information of at least one media information in the second media information set;

[0015] The sorting module is used to determine the sorting of the topic information corresponding to the multiple second media information sets based on the popularity information of the second media information sets, and to obtain the sorting result;

[0016] The target topic determination module is used to determine target topic information based on the sorting result, wherein the target topic information is at least one of the topic information, and the target topic information is used to be displayed on a preset topic collection page.

[0017] Thirdly, embodiments of this disclosure also provide an electronic device, the electronic device comprising:

[0018] One or more processors;

[0019] Storage device for storing one or more programs.

[0020] When the one or more programs are executed by the one or more processors, the one or more processors implement the media information-based processing method provided in the embodiments of this disclosure.

[0021] Fourthly, embodiments of this disclosure also provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the media information-based processing method provided in embodiments of this disclosure.

[0022] Fifthly, embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements the media information processing method provided in embodiments of this disclosure.

[0023] The media information processing scheme provided in this disclosure aggregates media information based on the similarity of preset content attribute dimensions to obtain multiple first media information sets. Media information within the same first media information set corresponds to at least one associated object. A second media information set is obtained by filtering out first media information sets whose content meets preset requirements. The theme information corresponding to the second media information set is determined based on the association information of at least one media information in the second media information set. The ranking of the theme information corresponding to the multiple second media information sets is determined based on the popularity information of the second media information sets, resulting in a ranking result. Target theme information is determined based on the ranking result, and this target theme information is used for display on a preset theme set page. By adopting the above technical solution, media information with similar content in the same area is aggregated. Before ranking based on popularity information, media information sets that meet the requirements are filtered out, ensuring content quality. The target theme information determined based on the ranking result is used for associated display with the corresponding media information set and associated object on the preset theme set page, thereby improving the display effect of theme information. Attached Figure Description

[0024] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0025] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0026] Figure 2 This is a schematic flowchart illustrating a media information processing method provided in an embodiment of this disclosure.

[0027] Figure 3 A schematic flowchart illustrating another media information processing method provided in this embodiment of the present disclosure;

[0028] Figure 4 This is a schematic diagram of the structure of a media information processing device provided in an embodiment of the present disclosure;

[0029] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0030] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0031] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0032] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0033] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0034] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0035] In related technologies, displaying trending information in text form on pages such as trending topics lists results in monotonous content and unsatisfactory display effects. In this embodiment, the topic information, the corresponding media information set, and the corresponding associated objects can be displayed together on the page, improving the display effect. Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of the present disclosure, such as... Figure 1As shown, in the preset theme collection page 101 (e.g., the display page of the popular topics list of new hot spots in City X), theme information 102 (which can be the theme of a popular topic in the list), media information collection 103 corresponding to theme information 102, and associated objects 104 corresponding to theme information 102 can be displayed in association. The specific display format and style are not limited. For example, theme information 102 can be displayed in text form (e.g., "Come and enjoy the ginkgo trees in autumn"), media information collection 103 can be displayed as image information of at least one of the media information (e.g., the video cover of a video related to ginkgo trees filmed in XX Park), and associated objects 104 can be displayed as the corresponding area information (e.g., XX Park). Among them, media information collection 103 can be triggered to display the details of the media information it contains, such as playing a video in a video collection; associated objects 104 can be triggered to display the area details information of the associated objects.

[0036] Figure 2 This is a flowchart illustrating a media information processing method provided in an embodiment of the present disclosure. This embodiment is applicable to situations where media information, topic information, and associated objects are determined for association and display on a page. The method can be executed by a media information processing device, which can be implemented in software and / or hardware, or optionally, by an electronic device, such as a personal computer (PC) or a server.

[0037] like Figure 2 As shown, the method includes:

[0038] Step 201: Aggregate media information based on the similarity of preset content attribute dimensions to obtain multiple first media information sets, wherein the media information in the same first media information set corresponds to at least one associated object.

[0039] The media information in this embodiment may include media content such as images, text, and videos. For example, the media information to be aggregated may be media information in a preset media information pool. The media information in the preset media information pool is aggregated based on the similarity of preset content attribute dimensions. The preset media information pool may be all or part of the media information in a media information publishing platform. For partial media information, it may be obtained by filtering according to a preset filtering method, such as filtering media information published in the last 3 months, and / or media information with a cumulative display count greater than a preset threshold, thus obtaining the preset media information pool.

[0040] Optionally, the preset content attribute dimensions include at least one of the following: preset topic dimension, preset area dimension, text content dimension, image content dimension, and audio content dimension. The preset topic can be a topic set by the media information publisher for the media information. The preset topic is displayed when the media information is shown, helping users intuitively determine the topic to which the currently viewed media information belongs. The preset area dimension can be a region set by the media information publisher for the media information. For example, if the publisher filmed a video in XX Park, the area of ​​the filmed video can be set as XX Park, helping users intuitively determine the filming location of the currently viewed media information. Text content can include the media information's title, description, subtitles, audio content, and comments. The title, description, and subtitles can be set by the publisher. Subtitles can be included in the media information's images and can be obtained using text recognition algorithms such as Optical Character Recognition (OCR). Audio content can be obtained using speech recognition algorithms such as Automatic Speech Recognition (ASR). Comments can include the content of comments posted by users. Image content can include the content of images or video frames in the media information. Audio content can include audio content from media information, including voice and background music.

[0041] For example, attribute information of preset content attribute dimensions of media information can be obtained. Based on the obtained attribute information, corresponding feature vectors can be constructed. The similarity of the preset content attribute dimensions of the media information is determined by calculating the similarity of the feature vectors. Clustering is performed based on this similarity, ensuring that the media information in each clustered media information set (denoted as the first media information set) corresponds to the same associated object. For example, the media information in the first media information set A corresponds to associated object a, and the media information in the first media information set B corresponds to associated object b. Optionally, the associated object can be at least one of associated region, associated topic, and event. The associated region can be a geographical location or location range related to the media information, such as XX Park. The associated topic can be a topic related to the media information. The associated event can be an event related to the media information.

[0042] Optionally, media information is aggregated based on a preset region dimension to obtain a first information set; media information is also aggregated based on the similarity of a first target content attribute dimension to obtain a second information set, wherein the first target content attribute dimension is at least one of the preset content attribute dimensions and is different from the preset region dimension; media information in the first information set and media information in the second information set are aggregated based on the similarity of the second target content attribute dimension to obtain multiple first media information sets, wherein the second target content attribute dimension is at least one of the preset content attribute dimensions and is different from the preset region dimension. This allows for the rapid and accurate aggregation of similar media information associated with the same region, preventing the omission of media information due to the media publisher not actively adding preset regions.

[0043] For example, taking the aforementioned XX Park as an example, some publishers set a preset area as XX Park when publishing media information, while others do not set a preset area, but the content of their media information is indeed related to XX Park. In order to comprehensively find media information related to XX Park, we can first identify the media information with the preset area of ​​XX Park to obtain the corresponding first information set. Then, by using the similarity of the second target content attribute dimension, we can find the second information set with similar content to the media information in the first information set corresponding to XX Park and aggregate them to obtain one or more media information sets (first media information sets) that are similar in content dimension to the same XX Park. For example, a video set about appreciating ginkgo trees in XX Park, or a video set about hiking in XX Park.

[0044] Step 202: Select a first media information set whose content meets the preset requirements from the first media information set to obtain a second media information set.

[0045] In this embodiment of the disclosure, while displaying theme information on the preset theme collection page, the corresponding media information collection is also displayed in association. In order to ensure the content quality of the displayed media information collection, the content is first filtered to obtain media information collections with content that meets expectations for display.

[0046] Optionally, the preset requirements include at least one of the following: the content of the included media information belongs to a preset content type; the content of the included media information has a higher level of attention in the target region than a preset level of attention; the content of the included media information has a higher degree of correlation with the target time entity than a preset correlation, wherein the target time entity includes time entities whose time difference with the current time is greater than a preset time difference; and the content of the included media information has a lower degree of similarity than the content of historical media information corresponding to historical topic information than a preset similarity threshold. This allows for more reasonable content filtering.

[0047] For example, the content of media information (such as the text content in the media information) can be understood based on a large language model, and then a judgment result on whether it meets the preset requirements can be output.

[0048] For example, the preset content categories can be set according to actual needs, such as life services, food, attractions, or performances. Optionally, a first prompt message can be pre-written, and the text content of the first prompt message and media information can be input into the large language model, which will then output a determination result as to whether the media information belongs to the preset content type.

[0049] For example, the same region can include multiple areas; a city may include areas such as parks, museums, and scenic spots. The target region can be a region pre-set or dynamically determined according to actual needs, such as one actively input by the user. The attention level in the target region can be used to characterize the popularity of the media information content in the target region. Optionally, a second prompt message is pre-written, and the text content of the second prompt message and the media information is input into a large language model. The large language model outputs a judgment result on whether the attention level of the media information in the target region is greater than the preset attention level.

[0050] For example, time entities may include seasons and holidays. If the time difference between the target time entity and the current time is greater than a preset time difference, media information with poor timeliness can be filtered out. The preset time difference could be, for example, one month or ten days, and the current time is used to determine whether the preset requirements are met. For example, if the current time is January 1st, and the target time entity is holiday A, with holiday A's date being June 5th, then content highly related to holiday A does not meet the preset requirements and needs to be filtered out. Optionally, a third prompt message can be pre-written. The text content of the third prompt message and the media information is input into a large language model. The large language model outputs the time entities involved in the media information and their relevance to those time entities, thereby determining whether the preset requirements are met.

[0051] For example, historical topic information can be topic information displayed during a preset historical period, such as the most recent week or yesterday. If the content of the current media information has a high similarity to the historical media information corresponding to the historical topic information, it indicates that a similar topic has been displayed in the past. To improve the freshness and diversity of the topic information displayed on the page, deduplication can be performed. The method of determining similarity is not limited. For example, a text vector can be determined based on the text content of the media information. A first similarity (the similarity between the text vector of the current media information and the text vector of the historical media information) can be determined based on the similarity of the text vectors. If the first similarity is less than a first similarity threshold, a multimodal vector can be determined based on the image content and text content. A second similarity (the similarity between the multimodal vector of the current media information and the multimodal vector of the historical media information) can be determined based on the similarity of the multimodal vectors. If the second similarity is less than a second similarity threshold, then the preset requirements can be met. Thus, deduplication can be performed more accurately.

[0052] Step 203: Determine the theme information corresponding to the second media information set based on the association information of at least one media information in the second media information set.

[0053] For example, at least one piece of media information can be a preset number of media information, such as 10. Associated information can include information related to the text content of the media information, such as title information or description information. Title information or description information can more accurately express the core content of the media information, thereby allowing for quick and accurate determination of the corresponding topic information. Optionally, the associated information of at least one piece of media information is input into a preset topic determination model, and the topic information corresponding to the second set of media information is determined based on the output of the preset topic determination model. The preset topic determination model can be a large language model, for example, a large language model obtained by fine-tuning a general large language model based on manually annotated sample media information.

[0054] Step 204: Based on the popularity information of the second media information set, determine the ranking of the topic information corresponding to the multiple second media information sets respectively, and obtain the ranking result.

[0055] For example, the popularity information in this embodiment of the disclosure can be information used to characterize the overall popularity of media information in the second media information set. The popularity information of the second media information set can also be used to characterize the popularity of the corresponding topic information. Therefore, the ranking result of the topic information corresponding to each second media information set can be determined based on the popularity information of the second media information set. The specific ranking method can be to sort in descending order according to the popularity of the popularity information.

[0056] Step 205: Determine the target theme information based on the sorting results, wherein the target theme information is at least one of the theme information, and the target theme information is used to associate and display with the corresponding second media information set and the corresponding associated object in the preset theme set page.

[0057] For example, the topic information with a high number of popular targets in the sorting results can be identified as the target topic information. This allows for the association and display of the highly popular topic information, its corresponding second media information set, and its associated objects on a preset topic collection page. Optionally, the target topic information is used to sort and display the topics according to the sorting results on the preset topic collection page.

[0058] like Figure 1 As shown in the figure, two target topic information are displayed. More can exist, but are not shown in the figure. Taking the first target topic information as an example, the first target topic information is associated with the image information (such as video cover) of the target media information in the corresponding second media information set and the area information of the corresponding associated object and displayed.

[0059] The media information processing method provided in this disclosure aggregates media information based on the similarity of preset content attribute dimensions to obtain multiple first media information sets. Media information within the same first media information set corresponds to the same associated object. A second media information set is obtained by filtering out first media information sets whose content meets preset requirements. The theme information corresponding to the second media information set is determined based on the association information of at least one media information in the second media information set. The ranking of the theme information corresponding to the multiple second media information sets is determined based on the popularity information of the second media information sets, resulting in a ranking result. Target theme information is determined based on the ranking result, and this target theme information is used for display on a preset theme set page. By adopting the above technical solution, media information with similar content in the same area is aggregated. Before ranking based on popularity information, media information sets that meet the requirements are filtered out, ensuring content quality. The target theme information determined based on the ranking result is used for associated display with the corresponding media information set and associated object on the preset theme set page, thereby improving the display effect of theme information.

[0060] In some embodiments, optionally, the preset content attribute dimension includes a first preset content attribute dimension and a second preset content attribute dimension, wherein the number of dimensions of the second preset content attribute dimension is less than or equal to the number of dimensions of the first preset content attribute dimension; wherein, the similarity of the preset content attribute dimensions is used to aggregate media information to obtain multiple first media information sets, including: aggregating media information based on the similarity of the first preset content attribute dimensions to obtain multiple initial media information sets, wherein media information in the same initial media information set corresponds to the same associated object; and aggregating the multiple initial media information sets based on the similarity of the second preset content attribute dimensions to obtain multiple first media information sets. Thus, associated objects can be further aggregated, allowing the same topic information to be associated with multiple associated objects for display, improving the flexibility and display effect of topic information display, and facilitating users to centrally view multiple associated objects and corresponding media information associated with a specific topic information.

[0061] For example, the first preset content attribute dimension includes the preset topic dimension, preset area dimension, text content dimension, and image content dimension; the second preset content attribute dimension includes the text content dimension and the image content dimension.

[0062] For example, as mentioned earlier, XX University might also have a collection of videos about appreciating ginkgo trees (the initial media information collection). This collection shares high content similarity with the collection of videos about appreciating ginkgo trees at XX Park (also the initial media information collection). These can be further aggregated into a first media information collection. The media information in this first media information collection corresponds to the same two related objects. After content filtering, this is called the second media information collection. Then, based on the related information of the media information in the second media information collection, the corresponding theme information is determined, such as "Recommended Ginkgo Viewing Locations." Figure 1 As shown, the target topic information ranked second is displayed in association with its corresponding second media information set and two associated areas. Each associated area can be displayed in a one-to-one correspondence with its corresponding initial media information set.

[0063] Optionally, the first preset content attribute dimension includes a preset region dimension, a first target content attribute dimension, and a similarity between the second target content attribute dimension; wherein, based on the similarity of the second target content attribute dimension, media information in the first information set and media information in the second information set are aggregated to obtain multiple first media information sets, including: based on the similarity of the second target content attribute dimension, media information in the first information set and media information in the second information set are aggregated to obtain multiple initial media information sets, wherein media information in the same initial media information set corresponds to the same associated object.

[0064] In some embodiments, the method further includes: acquiring display count data, publication count data, and publication duration data of media information in the second media information set within the most recent preset time period; and determining the popularity information of the second media information set based on the change information of the display count data, the change information of the publication count data, and the publication duration data. Therefore, by comprehensively determining popularity information from multiple perspectives, the popularity information of the second media information set can be determined more accurately, thereby improving the accuracy of subsequent ranking results.

[0065] The recent preset time period can be set according to actual needs, such as the last two weeks or the last month. Display frequency data can include the number of new displays per unit time (e.g., daily views). Publish quantity data includes the number of new publishes per unit time (e.g., daily submissions). Publish duration data can be the difference between the current time and the publication time of the media information. For cases where there are multiple media information items in the second media information set, the display frequency data, publish quantity data, and publish duration data can each be a statistical value corresponding to multiple media information items. The calculation method for these statistical values ​​is not limited; for example, it can be the average or median. For example, if there are M media information items in the second media information set, the display frequency data can be the average daily views of the M media information items per unit time.

[0066] Figure 3 This is a flowchart illustrating another media information processing method provided by an embodiment of the present disclosure. The embodiments of the present disclosure are optimized based on the various optional solutions in the above embodiments. Specifically, the method includes the following steps:

[0067] Step 301: Aggregate media information based on the similarity of preset content attribute dimensions to obtain multiple first media information sets, wherein the media information in the same first media information set corresponds to at least one associated object.

[0068] Among them, the preset content attribute dimensions may include preset topic dimensions, preset region dimensions, text content dimensions, and image content dimensions, so as to more accurately measure the content similarity of media information from multiple dimensions and obtain more accurate aggregation results.

[0069] Step 302: Select the first media information set whose content meets the preset requirements from the first media information set to obtain the second media information set.

[0070] The preset requirements may include: the media information content belonging to a preset content type; the media information content having a higher than preset level of attention in the target region; the media information content having a higher than preset level of correlation with a target time entity, where the target time entity includes time entities whose time difference from the current time is greater than a preset time difference; and the media information content having a lower than preset similarity threshold compared to the content of historical media information corresponding to historical topic information. This allows for more accurate pre-screening of suitable media information for display and reduces the computational workload of subsequent topic and popularity determination, thus improving the efficiency of target topic information identification.

[0071] Step 303: Determine the theme information corresponding to the second media information set based on the association information of at least one media information in the second media information set.

[0072] Optionally, the associated information includes title information. Optionally, this step may include: sorting the media information in the second media information set in descending order based on the attribute values ​​of a preset popularity attribute; obtaining the title information of the top N media information; inputting the obtained title information into a preset topic determination model; and determining the topic information corresponding to the second media information set based on the output of the preset topic determination model. This allows for more accurate determination of topic information.

[0073] For example, N could be 10. Preset popularity attributes could be, for example, cumulative impressions, such as the cumulative number of video views. Title information can concisely express the core content of the media information, improving the computational efficiency of the preset topic determination model and the accuracy of the output topic information, and can also match the wording style of the media information publisher.

[0074] Step 304: Obtain the display count, publication count, and publication duration data of the media information in the second media information set within the most recent preset time period.

[0075] For example, the number of impressions data includes the number of new impressions per unit of time, and the number of posts data includes the number of posts per unit of time.

[0076] Step 305: Determine the first popularity value based on the weighted sum of the changes in display frequency data and the changes in posting quantity data.

[0077] For example, for each second media information set in the second media information set, the first popularity value corresponding to the current second media information set is determined by the weighted sum of the change information of the display count data and the change information of the publication count data corresponding to the current second media information set.

[0078] Optionally, the change information includes change trends and change indices.

[0079] This step may include: determining a first value based on the weighted sum of the changing trends of the display frequency data and the publishing quantity data; determining a second value based on the weighted sum of the changing indices of the display frequency data and the publishing quantity data; and determining a first popularity value based on the weighted sum of the first value and the second value.

[0080] The trend is determined as follows: New data within a unit of time is sorted according to chronological order to obtain a new data sequence, where the new data refers to the number of new displays or the number of new releases; for each pair of adjacent new data in the new data sequence, if the new data from more recent times is greater than the new data from more distant times, then the current data pair is determined as the target data pair; the trend is determined based on the quotient of the number of target data pairs and the total number of data pairs.

[0081] The trend of the number of impressions is determined as follows: the number of new impressions within a unit of time is sorted according to time sequence to obtain the sequence of new impressions; for each pair of new impressions in the sequence, if the number of new impressions from more recent times is greater than the number of new impressions from more distant times, then the current data pair is determined as the target data pair; the trend is determined based on the quotient of the number of target data pairs and the total number of data pairs.

[0082] The trend of the number of releases is determined as follows: the number of new releases within a unit time period is sorted according to time sequence to obtain a sequence of new releases; for each pair of new releases in the sequence, if the number of new releases from more recent times is greater than the number of new releases from more distant times, the current data pair is determined as the target data pair; the trend is determined based on the quotient of the number of target data pairs and the total number of data pairs.

[0083] For ease of explanation, let's take the trend of display count data as an example. Assume the most recent preset time period is the last 7 days, with a unit time of 1 day. The number of new displays per day, from oldest to newest, are 10,000, 20,000, 10,000, 30,000, 40,000, 50,000, and 60,000, which can form 6 data pairs: (10,000, 20,000), (20,000, 10,000), (10,000, 30,000), (30,000, 40,000), (40,000, 50,000), and (50,000, 60,000). In each data pair, the first is the new data from an older time period, and the second is the new data from a more recent time period. Then, the number of target data pairs is 5, and the total number of data pairs is 6. Therefore, the trend is 5 / 6.

[0084] Optionally, the change index is determined by: determining a first normalized value of the new data corresponding to the last unit of time; determining a second normalized value of the rate of change of the new data corresponding to the last unit of time relative to the new data corresponding to the first unit of time; and determining the change index based on the product of the first normalized value and the second normalized value.

[0085] The change index for the number of impressions is determined as follows: the first normalized value of the number of new impressions corresponding to the last unit of time is determined; the second normalized value of the rate of change of the number of new impressions corresponding to the last unit of time relative to the number of new impressions corresponding to the first unit of time is determined; and the change index is determined by multiplying the first normalized value and the second normalized value.

[0086] The change index for the number of releases is determined as follows: a first normalized value is determined for the number of new releases corresponding to the last unit of time; a second normalized value is determined for the rate of change of the number of new releases corresponding to the last unit of time relative to the number of new releases corresponding to the first unit of time; and the change index is determined by multiplying the first normalized value and the second normalized value.

[0087] For ease of explanation, let's take the change index of display count data as an example. As mentioned above, the new data corresponding to the last unit of time is 60,000, and the new data corresponding to the first unit of time is 10,000. The change rate of the new data corresponding to the last unit of time relative to the new data corresponding to the first unit of time is 5 / 6. Calculate the product of the normalized value of 60,000 (first normalized value) and the normalized value of 5 / 6 (second normalized value) to obtain the change index of display count data.

[0088] Optionally, the first heat value can be determined by the following expression:

[0089] First popularity value = X * (Trend of display frequency * Y + Trend of posting quantity * (1-Y)) + (1-X) * (Z * Index of display frequency + (1-Z) * Index of posting quantity). Where X, Y, and Z are weighting coefficients that can be preset according to actual needs.

[0090] Step 306: Determine the second popularity value based on the changes in display count data, publication duration data, and display count data.

[0091] This step may include: determining a third value based on the weighted sum of the changing trends of the publication duration data and the display frequency data; and determining a second popularity value based on the product of the display frequency data and the third value.

[0092] In determining the second popularity value, the sum of the number of new displays per unit time within the most recent preset time period can be calculated and recorded as the cumulative number of new displays. The second popularity value is determined by multiplying the cumulative number of new displays by the third value.

[0093] Optionally, the second heat value can be determined by the following expression:

[0094] Second popularity value = cumulative new impressions * (post duration * K + impression change trend * (1-K)). Where K is a weighting coefficient, which can be preset according to actual needs.

[0095] Step 307: Determine the popularity information of the second media information set based on the weighted sum of the first popularity value and the second popularity value.

[0096] For example, the popularity information can be recorded as a comprehensive popularity value, which is: Comprehensive Popularity Value = F * First Popularity Value + (1-F) * Second Popularity Value, where F is a weighting coefficient that can be preset according to actual needs.

[0097] Step 308: Based on the popularity information of the second media information set, determine the ranking of the topic information corresponding to the multiple second media information sets, and obtain the ranking result.

[0098] Step 309: Determine the target theme information based on the sorting results. The target theme information is used to associate and display the image information of at least one media information in the corresponding second media information set and the area information of the corresponding associated object in the preset theme set page according to the sorting results.

[0099] The media information processing method provided in this disclosure determines a first popularity value based on a weighted sum of changes in display frequency data and changes in publication quantity data before determining the order of each topic information. It then determines a second popularity value based on changes in display frequency data, publication duration data, and display frequency data. Finally, it determines the popularity information of a second media information set based on a weighted sum of the first and second popularity values. By comprehensively considering the influence of various factors on the popularity of the second media information set from multiple perspectives, the popularity information can be determined more accurately, thereby improving the accuracy of the topic information sorting results and further enhancing the information display effect within the preset topic information set page.

[0100] Figure 4 This is a schematic diagram of the structure of a media information processing device provided in an embodiment of the present disclosure, as shown below. Figure 4 As shown, the device includes:

[0101] The aggregation module 401 is used to aggregate media information based on the similarity of preset content attribute dimensions to obtain multiple first media information sets, wherein the media information in the same first media information set corresponds to the same at least one associated object;

[0102] The set filtering module 402 is used to filter out the first media information set whose content meets the preset requirements from the first media information set, and obtain the second media information set;

[0103] The topic determination module 403 is used to determine the topic information corresponding to the second media information set based on the association information of at least one media information in the second media information set;

[0104] The sorting module 404 is used to determine the sorting of the topic information corresponding to the multiple second media information sets based on the popularity information of the second media information set, and to obtain the sorting result;

[0105] The target topic determination module 405 is used to determine target topic information based on the sorting result, wherein the target topic information is at least one of the topic information, and the target topic information is used to be displayed on a preset topic collection page.

[0106] The media information processing apparatus provided in this embodiment aggregates media information with similar content in the same area. Before sorting based on popularity information, it filters out a set of media information that meets the requirements to ensure content quality. The target theme information determined according to the sorting results is used to display the corresponding media information set and related objects in a preset theme set page, which can improve the display effect of theme information.

[0107] Optionally, the preset requirements include at least one of the following:

[0108] The content of the included media information belongs to the preset content type;

[0109] The media information contained therein receives more attention in the target region than the preset attention level;

[0110] The content of the included media information has a higher correlation with the target time entity than a preset correlation, wherein the target time entity includes time entities whose corresponding time differs from the current time by a preset time difference; and

[0111] The similarity between the content of the included media information and the content of the historical media information corresponding to the historical theme information is less than the preset similarity threshold.

[0112] Optionally, the target topic information is used to sort and display the content in the preset topic collection page according to the sorting result.

[0113] Optionally, the associated object is at least one of associated region, associated topic, and associated event.

[0114] Optionally, the device may also include:

[0115] The data acquisition module is used to acquire the display count data, publication count data, and publication duration data of the media information in the second media information set within the most recent preset time period;

[0116] The popularity information determination module is used to determine the popularity information of the second media information set based on the change information of the display frequency data, the change information of the publication quantity data, and the publication duration data.

[0117] Optionally, the heat information determination module includes:

[0118] The first popularity value determination unit is used to determine the first popularity value based on the weighted sum of the change information of the display frequency data and the change information of the publication quantity data;

[0119] The second popularity value determination unit is used to determine the second popularity value based on the display count data, the publication duration data, and the change information of the display count data;

[0120] The popularity information determination unit is used to determine the popularity information of the second media information set based on the weighted sum of the first popularity value and the second popularity value.

[0121] Optionally, the change information includes change trend and change index;

[0122] The step of determining the first popularity value based on the weighted sum of the changes in the number of displays and the number of posts includes:

[0123] The first value is determined by a weighted sum of the trends in the number of impressions and the number of publications.

[0124] The second value is determined by a weighted sum of the change index of the display frequency data and the change index of the release quantity data;

[0125] The first heat value is determined by the weighted sum of the first value and the second value;

[0126] The determination of the second popularity value based on the display frequency data, the publication duration data, and the change information of the display frequency data includes:

[0127] The third value is determined by a weighted sum of the changing trends of the publication duration data and the display frequency data;

[0128] The second popularity value is determined by multiplying the number of times the image was displayed by the third value.

[0129] Optionally, the display count data includes the number of new displays per unit time, and the publication count data includes the number of publications per unit time.

[0130] The trend of change is determined in the following way:

[0131] The newly added data within a unit of time is sorted according to the chronological order to obtain a sequence of newly added data, wherein the newly added data is the number of newly displayed data or the number of newly published data.

[0132] For each pair of adjacent new data in the new data sequence, if the new data that is more recent is greater than the new data that is more distant, then the current data pair is determined to be the target data pair.

[0133] The trend of change is determined by the quotient of the number of target data pairs and the total number of data pairs;

[0134] The change index is determined in the following way:

[0135] Determine the first normalized value of the newly added data corresponding to the last unit of time;

[0136] Determine the second normalized value of the rate of change of the new data corresponding to the last unit of time relative to the new data corresponding to the first unit of time;

[0137] The change index is determined by multiplying the first normalized value and the second normalized value.

[0138] Optionally, the associated information includes title information; the topic determination module includes:

[0139] The sorting unit is used to sort the media information in the second media information set in descending order based on the attribute value of a preset popularity attribute.

[0140] The title information acquisition unit is used to acquire the title information of the top N media information;

[0141] The theme determination unit is used to input the acquired title information into a preset theme determination model, and determine the theme information corresponding to the second media information set based on the output of the preset theme determination model.

[0142] Optionally, the preset content attribute dimensions include at least one of the following: preset topic dimension, preset region dimension, text content dimension, image content dimension, and audio content dimension.

[0143] Optionally, the preset content attribute dimension includes a first preset content attribute dimension and a second preset content attribute dimension, wherein the number of dimensions of the second preset content attribute dimension is less than or equal to the number of dimensions of the first preset content attribute dimension.

[0144] The aggregation module includes:

[0145] The first aggregation unit is used to aggregate media information based on the similarity of the first preset content attribute dimension to obtain multiple initial media information sets, wherein the media information in the same initial media information set corresponds to the same associated object;

[0146] The second aggregation unit is used to aggregate the multiple initial media information sets based on the similarity of the second preset content attribute dimension to obtain multiple first media information sets.

[0147] The media information processing apparatus provided in this disclosure can execute the media information processing method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of executing the method.

[0148] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of this disclosure.

[0149] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Reference is made below. Figure 5 It illustrates an electronic device suitable for implementing embodiments of the present disclosure (e.g., Figure 5 The diagram below shows the structure of the terminal device or server 500. The terminal device in this embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and vehicle terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0150] like Figure 5As shown, electronic device 500 may include a processing unit (e.g., central processing unit, graphics processor, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from storage device 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of electronic device 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. An edit / output (I / O) interface 505 is also connected to bus 504.

[0151] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0152] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, it performs the functions defined in the methods of embodiments of this disclosure.

[0153] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0154] The electronic device provided in this embodiment and the media information processing method provided in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0155] This disclosure provides a computer storage medium storing a computer program that, when executed by a processor, implements the media information processing method provided in the above embodiments.

[0156] This disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the media information processing method provided in the above embodiments.

[0157] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0158] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0159] The aforementioned computer-readable medium carries one or more programs. When the aforementioned one or more programs are executed by the electronic device, the electronic device causes the following actions: It aggregates media information based on the similarity of preset content attribute dimensions to obtain multiple first media information sets, wherein media information in the same first media information set corresponds to at least one associated object; it filters out first media information sets whose content meets preset requirements from the first media information sets to obtain second media information sets; it determines the theme information corresponding to the second media information set based on the association information of at least one media information in the second media information set; it determines the ranking of the theme information corresponding to the multiple second media information sets based on the popularity information of the second media information set, obtaining a ranking result; and it determines target theme information based on the ranking result, wherein the target theme information is at least one of the theme information, and the target theme information is used to be displayed in association with the corresponding second media information set and the corresponding associated object on a preset theme set page.

[0160] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0161] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0162] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The name of a module does not necessarily limit the module itself; for example, a target topic determination module can also be described as "a module that determines target topic information based on the sorting results".

[0163] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0164] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0165] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0166] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0167] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A method for processing media information, characterized in that, include: Media information is aggregated based on the similarity of preset content attribute dimensions to obtain multiple first media information sets, wherein the media information in the same first media information set corresponds to the same at least one associated object; The first media information set whose content meets the preset requirements is selected from the first media information set to obtain the second media information set; Based on the association information of at least one media information in the second media information set, determine the theme information corresponding to the second media information set; Based on the popularity information of the second media information set, the ranking of the topic information corresponding to the multiple second media information sets is determined, and the ranking result is obtained; The target theme information is determined based on the sorting result, wherein the target theme information is at least one of the theme information, and the target theme information is used to associate and display with the corresponding second media information set and the corresponding associated object in the preset theme set page.

2. The method according to claim 1, characterized in that, The preset requirements include at least one of the following: The content of the included media information belongs to the preset content type; The media information contained therein receives more attention in the target region than the preset attention level; The content of the included media information has a higher correlation with the target time entity than a preset correlation, wherein the target time entity includes time entities whose corresponding time differs from the current time by a preset time difference; and The similarity between the content of the included media information and the content of the historical media information corresponding to the historical theme information is less than the preset similarity threshold.

3. The method according to claim 1, characterized in that, The target topic information is used to sort and display the content in the preset topic collection page according to the sorting result; and / or, the associated object is at least one of associated area, associated topic and associated event.

4. The method according to claim 1, characterized in that, Also includes: Obtain the display count data, publication count data, and publication duration data of the media information in the second media information set within the most recent preset time period; The popularity information of the second media information set is determined based on the changes in the number of displays, the number of publications, and the publication duration.

5. The method according to claim 4, characterized in that, The step of determining the popularity information of the second media information set based on the changes in the display frequency data, the changes in the number of publications data, and the publication duration data includes: A first popularity value is determined by a weighted sum of the changes in the number of displays and the number of posts. The second popularity value is determined based on the display count data, the publication duration data, and the change information of the display count data; The popularity information of the second media information set is determined based on the weighted sum of the first popularity value and the second popularity value.

6. The method according to claim 5, characterized in that, The change information includes change trends and change indices; The step of determining the first popularity value based on the weighted sum of the changes in the number of displays and the number of posts includes: The first value is determined by a weighted sum of the trends in the number of impressions and the number of publications. The second value is determined by a weighted sum of the change index of the display frequency data and the change index of the release quantity data; The first heat value is determined by the weighted sum of the first value and the second value; The determination of the second popularity value based on the display frequency data, the publication duration data, and the change information of the display frequency data includes: The third value is determined by a weighted sum of the changing trends of the publication duration data and the display frequency data; The second popularity value is determined by multiplying the number of times the image was displayed by the third value.

7. The method according to claim 5, characterized in that, The display count data includes the number of new displays per unit time, and the publication count data includes the number of publications per unit time. The trend of change is determined in the following way: The newly added data within a unit of time is sorted according to the chronological order to obtain a sequence of newly added data, wherein the newly added data is the number of newly displayed data or the number of newly published data. For each pair of adjacent new data in the new data sequence, if the new data that is more recent is greater than the new data that is more distant, then the current data pair is determined to be the target data pair. The trend of change is determined by the quotient of the number of target data pairs and the total number of data pairs; The change index is determined in the following way: Determine the first normalized value of the newly added data corresponding to the last unit of time; Determine the second normalized value of the rate of change of the new data corresponding to the last unit of time relative to the new data corresponding to the first unit of time; The change index is determined by multiplying the first normalized value and the second normalized value.

8. The method according to claim 1, characterized in that, The associated information includes title information; based on the associated text information of at least one media information in the second media information set, the theme information corresponding to the second media information set is determined, including: The media information in the second media information set is sorted in descending order based on the attribute values ​​of the preset popularity attribute; Retrieve the title information of the top N media outlets; The acquired title information is input into the preset theme determination model, and the theme information corresponding to the second media information set is determined according to the output of the preset theme determination model.

9. The method according to claim 1, wherein the preset content attribute dimension includes at least one of the preset topic dimension, preset region dimension, text content dimension, image content dimension, and audio content dimension.

10. The method according to claim 1, wherein the preset content attribute dimension includes a first preset content attribute dimension and a second preset content attribute dimension, wherein the number of dimensions of the second preset content attribute dimension is less than or equal to the number of dimensions of the first preset content attribute dimension; in, The similarity of the preset content attribute dimensions is used to aggregate media information, resulting in multiple sets of first media information, including: Media information is aggregated based on the similarity of the first preset content attribute dimension to obtain multiple initial media information sets, wherein media information in the same initial media information set corresponds to the same associated object; Based on the similarity of the second preset content attribute dimension, the multiple initial media information sets are aggregated to obtain multiple first media information sets.

11. A media information processing device, characterized in that, include: The aggregation module is used to aggregate media information based on the similarity of a preset content attribute dimension to obtain multiple first media information sets. The preset content attribute dimension includes an associated object dimension, and the media information in the same first media information set corresponds to at least one of the same associated objects. The set filtering module is used to filter out the first media information set whose content meets the preset requirements from the first media information set, and obtain the second media information set; The topic determination module is used to determine the topic information corresponding to the second media information set based on the association information of at least one media information in the second media information set; The sorting module is used to determine the sorting of the topic information corresponding to the multiple second media information sets based on the popularity information of the second media information sets, and to obtain the sorting result; The target topic determination module is used to determine target topic information based on the sorting result, wherein the target topic information is at least one of the topic information, and the target topic information is used to be displayed on a preset topic collection page.

12. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the media information-based processing method as described in any one of claims 1-10.

13. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the media information-based processing method as described in any one of claims 1-10.

14. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the media information-based processing method as described in any one of claims 1-10.

Images