Server, media resource aggregation method and medium

Abstract

The present disclosure relates to a server, a media aggregation method and a medium, which determines multiple judgment texts based on a search text, and obtains a first similarity between the search text and each judgment text respectively; determines a target candidate text set from the multiple judgment texts based on the first similarity between the search text and each judgment text; obtains a second similarity between a first picture set related to the search text and a second picture set related to each target candidate text in the target candidate text set; obtains a target similarity between the search text and each target candidate text based on the first similarity and the second similarity; and sends media data corresponding to the target candidate text having a target similarity greater than a preset threshold to a terminal device based on the target similarity between the search text and each target candidate text, so that the terminal device displays the media data, thereby improving the accuracy of the displayed media data.

Description

Technical Field

[0001] The present disclosure relates to the field of computer processing technology, and in particular to a server, a media resource aggregation method, and a medium. Background Art

[0002] Currently, terminal devices such as smart TVs can display media data related to the user's search information based on the user's search information. For example, for a certain film or television work, the user can be shown related information such as the application that plays the film or television work, the director of the film or television work, the introduction, the poster, etc.

[0003] In the existing technology, media data is provided to users by providers in different countries. However, the media data provided by multiple providers may contain the same content. Therefore, in order to enable users to obtain valid media data, the media data provided by multiple providers need to be aggregated to remove the same content in the media data provided by multiple providers. However, because the media data provided by providers in different countries correspond to different languages, based on this, it is first necessary to unify the media data provided by multiple providers into the same standard language, and then aggregate the media data provided by multiple providers based on the same standard language to remove the same content.

[0004] However, using existing technologies, in the process of translating media data provided by multiple providers, it may not be possible to accurately translate between different languages, resulting in low accuracy of the media data displayed to users, affecting the user experience. Summary of the Invention

[0005] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a server, a media aggregation method and a medium. By calculating the similarity between a search text and multiple judgment texts in different languages ​​determined based on the search text, a target candidate text set with a higher similarity to the search text is preferentially determined without translation, thereby solving the problem in the prior art that translation between different languages ​​cannot be achieved more accurately. Furthermore, a second similarity between a first image set related to the search text and a second image set related to each target candidate text is obtained, and a target similarity is determined by combining the first similarity and the second similarity. The media data displayed to the user is determined based on the target similarity, thereby improving the accuracy of the media data displayed to the user.

[0006] In a first aspect, the present disclosure provides a server, comprising:

[0007] The controller is configured as:

[0008] Determining a plurality of determination texts according to the search text, and respectively obtaining a first similarity between the search text and each of the determination texts, wherein the determination texts are respectively texts in different languages;

[0009] Determining a target candidate text set from a plurality of the determination texts according to a first similarity between the search text and each of the determination texts;

[0010] For the first picture set related to the search text and the second picture set related to each target candidate text in the target candidate text set, respectively obtain a second similarity between the first picture set and each second picture set;

[0011] Obtaining target similarities between the search text and each of the target candidate texts based on the first similarity and the second similarity;

[0012] According to the target similarity between the search text and each target candidate text, the media asset data corresponding to the target candidate text having the target similarity greater than a preset threshold is sent to the terminal device, so that the terminal device displays the media asset data.

[0013] As an optional implementation of the embodiment of the present disclosure, the plurality of determination texts include: at least one first determination text;

[0014] The controller is specifically configured to:

[0015] For each of the first determination texts, determining a first text set corresponding to the first determination text;

[0016] A first similarity between the search text and each of the first determination texts is determined based on multiple preset information associated with the first determination text and multiple preset information associated with each of the first texts in each of the first text sets.

[0017] As an optional implementation of the embodiment of the present disclosure, the plurality of determination texts further include: at least one second determination text;

[0018] The controller is further configured to:

[0019] For each first text included in each first text set corresponding to each first determination text, obtaining at least one second determination text corresponding to each first text;

[0020] For each of the first texts and each of the second determination texts corresponding to each of the first texts, obtaining a third similarity between the first text and each of the second determination texts;

[0021] The product of the first similarity between the first determination text and each of the first texts and the third similarity between the first text and the second determination text is calculated to obtain the first similarity between the search text and each of the second determination texts.

[0022] As an optional implementation of the embodiment of the present disclosure, the controller is specifically configured as follows:

[0023] Determining a first candidate text set from the plurality of first determination texts based on a first similarity between the search text and each first determination text;

[0024] determining a second candidate text set from the plurality of second determination texts based on a first similarity between the search text and each of the second determination texts;

[0025] The target candidate text set is determined according to the first candidate text set and the second candidate text set.

[0026] As an optional implementation of the embodiment of the present disclosure, the controller is specifically configured as follows:

[0027] Obtaining, based on a size ratio between a length and a width of each first picture included in the first picture set, a size ratio between a length and a width of each second picture included in the second picture set, and at least one preset mapping relationship, a second similarity between the first picture set and each second picture set;

[0028] The preset mapping relationship includes a corresponding relationship between the size ratio and a preset standard resolution.

[0029] As an optional implementation of the embodiment of the present disclosure, the controller is further configured to:

[0030] performing resolution conversion on the first pictures of various size ratios in the first picture set and the second pictures of the same size ratio in the second picture set according to the preset mapping relationship, to obtain a third picture set corresponding to the first picture set and a fourth picture set corresponding to the second picture set;

[0031] Obtaining fourth similarities between the third picture set and the fourth picture set at respective preset standard resolutions;

[0032] An average calculation is performed on the fourth similarities corresponding to multiple preset standard resolutions to obtain a second similarity between the first picture set and each of the second picture sets.

[0033] As an optional implementation of the embodiment of the present disclosure, the controller is specifically configured as follows:

[0034] According to the target similarity between the search text and each of the target candidate texts, a plurality of the target candidate texts whose target similarity is greater than a preset threshold are sorted, and the media asset data is sent to the terminal device according to the sorting result.

[0035] In a second aspect, the present disclosure provides a media asset aggregation method, comprising:

[0036] Determining a plurality of determination texts according to the search text, and respectively obtaining a first similarity between the search text and each of the determination texts, wherein the determination texts are respectively texts in different languages;

[0037] Determining a target candidate text set from a plurality of the determination texts according to a first similarity between the search text and each of the determination texts;

[0038] For the first picture set related to the search text and the second picture set related to each target candidate text in the target candidate text set, respectively obtain a second similarity between the first picture set and each second picture set;

[0039] Obtaining target similarities between the search text and each of the target candidate texts based on the first similarity and the second similarity;

[0040] According to the target similarity between the search text and each target candidate text, the media asset data corresponding to the target candidate text having the target similarity greater than a preset threshold is sent to the terminal device, so that the terminal device displays the media asset data.

[0041] As an optional implementation of the embodiment of the present disclosure, the multiple judgment texts include: at least one first judgment text; including:

[0042] For each of the first determination texts, determining a first text set corresponding to the first determination text;

[0043] A first similarity between the search text and each of the first determination texts is determined based on multiple preset information associated with the first determination text and multiple preset information associated with each of the first texts in each of the first text sets.

[0044] In a third aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the second aspect.

[0045] The technical solution provided by the embodiments of the present disclosure has the following advantages over the prior art:

[0046] In the technical solution provided by the embodiment of the present disclosure, the controller of the server determines multiple judgment texts based on the search text, and obtains the first similarity between the search text and each judgment text respectively, wherein the judgment texts are texts in different languages; based on the first similarity between the search text and each judgment text, a target candidate text set is determined in the multiple judgment texts; for a first picture set related to the search text and a second picture set related to each target candidate text in the target candidate text set, a second similarity between the first picture set and each second picture set is obtained respectively; based on the first similarity and the second similarity, a target similarity between the search text and each target candidate text is obtained; for the target similarity between the search text and each target candidate text, the media data corresponding to the target candidate text with a target similarity greater than a preset threshold is sent to the terminal device, so that the terminal device displays the media data. In the above technical solution, by calculating the similarity between the search text and multiple judgment texts in different languages ​​determined based on the search text, the target candidate text set with a higher similarity to the search text is preferentially determined without translation, thereby solving the problem in the prior art that translation between different languages ​​cannot be achieved more accurately. Furthermore, the second similarity between the first picture set related to the search text and the second picture set related to each target candidate text is obtained, and the target similarity is determined by combining the first similarity and the second similarity. The media data displayed to the user is determined based on the target similarity, thereby improving the accuracy of the media data displayed to the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0048] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0049] Figure 1 A schematic diagram of a scenario architecture of a media resource aggregation method provided in an embodiment of the present disclosure;

[0050] Figure 2 A hardware configuration block diagram of a server according to one or more embodiments of the present disclosure;

[0051] Figure 3 A system framework diagram of a method for media resource aggregation according to one or more embodiments of the present disclosure;

[0052] Figure 4 A flowchart of a media resource aggregation method provided in an embodiment of the present disclosure;

[0053] Figure 5 A flowchart of another media resource aggregation method provided by an embodiment of the present disclosure;

[0054] Figure 6 A flowchart of another media resource aggregation method provided in an embodiment of the present disclosure;

[0055] Figure 7 A flowchart of another media resource aggregation method provided in an embodiment of the present disclosure;

[0056] Figure 8 A schematic diagram of a first image provided in an embodiment of the present disclosure;

[0057] Figure 9 A flowchart of another media resource aggregation method provided in an embodiment of the present disclosure;

[0058] Figure 10 A flowchart of another media resource aggregation method provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0059] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features therein can be combined with each other in the absence of conflict.

[0060] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0061] The terms "first" and "second" in this disclosure are used to distinguish different objects rather than to describe a specific order of objects. For example, a first processing result and a second processing result are used to distinguish different processing results rather than to describe a specific order of processing results.

[0062] Figure 1The following is a schematic diagram of a scenario architecture for the media aggregation method provided in an embodiment of the present disclosure. The scenario architecture provided in an embodiment of the present disclosure includes: a server 100, a terminal device 200, and a control device 300. The terminal device 200 can have various implementation forms, for example, a smart TV, a smart phone, a personal computer, a display, etc. Exemplarily, upon receiving a user's search information, the terminal device 200 displays information related to the search information to the user based on media data provided by providers in different countries. For example, a user enters the search information "Who is he?" in the search interface of a video playback application XX on a terminal device 200, such as a smart TV. In response to the search information "Who is he?", the terminal device 200 displays media data related to the search information "Who is he?" to the user, such as the film or television work, the director of the film or television work, an introduction, a poster, etc., or other video playback applications that play the film or television work.

[0063] However, the above-mentioned media data provided by providers from different countries may contain the same content. Therefore, in order to ensure that valid media data can be displayed to users, the media data provided by multiple providers need to be further aggregated to remove the same content. However, since the media data provided by providers from different countries correspond to different languages, the media data provided by providers from different countries need to be unified into the same standard language before aggregation. However, in the process of translating the media data provided by each provider into different languages, there is a problem that the translation between different languages ​​cannot be achieved more accurately, resulting in low accuracy of the media data displayed to users, affecting the user experience.

[0064] In order to solve the above problems, an embodiment of the present disclosure proposes a media aggregation method, including: a controller of a server determines multiple judgment texts based on a search text, and obtains a first similarity between the search text and each judgment text, respectively, wherein the judgment texts are texts in different languages; based on the first similarity between the search text and each judgment text, a target candidate text set is determined from the multiple judgment texts; for a first picture set related to the search text and a second picture set related to each target candidate text in the target candidate text set, a second similarity between the first picture set and each second picture set is obtained; based on the first similarity and the second similarity, a target similarity between the search text and each target candidate text is obtained; for the target similarity between the search text and each target candidate text, the media data corresponding to the target candidate text with a target similarity greater than a preset threshold is sent to a terminal device, so that the terminal device displays the media data. In the above technical solution, by calculating the similarity between the search text and multiple judgment texts in different languages ​​determined based on the search text, the target candidate text set with a higher similarity to the search text is preferentially determined without translation, thereby solving the problem in the prior art that translation between different languages ​​cannot be achieved more accurately. Furthermore, the second similarity between the first picture set related to the search text and the second picture set related to each target candidate text is obtained, and the target similarity is determined by combining the first similarity and the second similarity. The media data displayed to the user is determined based on the target similarity, thereby improving the accuracy of the media data displayed to the user.

[0065] In some embodiments, the terminal device 200 may receive a user instruction input by the user through the control device 300, and after receiving the user instruction, may communicate data with the server 100. The terminal device 200 may be allowed to communicate with the server 100 via a local area network (LAN) or a wireless local area network (WLAN).

[0066] The server 100 can be a server that provides various services, such as supporting media data collected by the terminal device 200. The server can analyze and process the received media data and feed back the processing results (e.g., endpoint information) to the terminal device. The server 100 can be a single server cluster or multiple server clusters, and can include one or more types of servers.

[0067] The multi-scenario and multi-task content recommendation method provided by the embodiments of the present disclosure can be implemented based on a server, or a functional module or functional entity in the server.

[0068] For example, Figure 2 FIG. 1 is a hardware configuration block diagram of a server according to one or more embodiments of the present disclosure. Figure 2As shown, the server includes at least one of a tuner and demodulator 210, a communicator 220, a memory 230, a display interface 240, a controller 250, and a power supply 260. Controller 250 includes a central processing unit (CPU), a video processor, an audio processor, a graphics processor, RAM, ROM, and first to nth interfaces for input / output. Display interface 240 can be a VGA (Video Graphics Array). Generally, server graphics cards have low requirements, so server graphics card interfaces are typically VGA, typically used for installing server operating systems or routine debugging. Tuner and demodulator 210 receives broadcast television signals via wired or wireless reception, and demodulates audio and video signals, such as EPG audio and video data signals, from multiple wireless or wired broadcast television signals. Communicator 220 is a component used to communicate with external devices according to various communication protocols. For example, the communicator can include at least one of a Wi-Fi module, a Bluetooth module, a wired Ethernet module, or other network communication protocol chips or near-field communication protocol chips, as well as an infrared receiver. The server can establish a communication channel for sending and receiving control signals and data signals with the terminal device 200 or the local control device via the communicator 220. The controller 250 and the tuner 210 can be located in different separate devices, that is, the tuner 210 can also be located in an external device of the main device where the controller 250 is located, such as an external set-top box.

[0069] In some embodiments, controller 250 controls the operation of the server and responds to user operations through various software control programs stored in memory. Controller 250 controls the overall operation of the server. A user can enter user commands through a graphical user interface (GUI) displayed on display interface 240, and the user input interface receives user input commands through the graphical user interface (GUI).

[0070] In some embodiments, the server includes:

[0071] The controller 250 is configured to:

[0072] Determining a plurality of determination texts according to the search text, and respectively obtaining a first similarity between the search text and each of the determination texts, wherein the determination texts are respectively texts in different languages;

[0073] Determining a target candidate text set from a plurality of the determination texts according to a first similarity between the search text and each of the determination texts;

[0074] For the first picture set related to the search text and the second picture set related to each target candidate text in the target candidate text set, respectively obtain a second similarity between the first picture set and each second picture set;

[0075] Obtaining target similarities between the search text and each of the target candidate texts based on the first similarity and the second similarity;

[0076] According to the target similarity between the search text and each target candidate text, the media asset data corresponding to the target candidate text having the target similarity greater than a preset threshold is sent to the terminal device, so that the terminal device displays the media asset data.

[0077] In some embodiments, the plurality of determination texts include: at least one first determination text; the controller 250 is specifically configured to:

[0078] For each of the first determination texts, determining a first text set corresponding to the first determination text;

[0079] A first similarity between the search text and each of the first determination texts is determined based on multiple preset information associated with the first determination text and multiple preset information associated with each of the first texts in each of the first text sets.

[0080] In some embodiments, the plurality of determination texts further include: at least one second determination text; the controller 250 is further configured to:

[0081] For each first text included in each first text set corresponding to each first determination text, obtaining at least one second determination text corresponding to each first text;

[0082] For each of the first texts and each of the second determination texts corresponding to each of the first texts, obtaining a third similarity between the first text and each of the second determination texts;

[0083] The product of the first similarity between the first determination text and each of the first texts and the third similarity between the first text and the second determination text is calculated to obtain the first similarity between the search text and each of the second determination texts.

[0084] In some embodiments, the controller 250 is specifically configured to:

[0085] Determining a first candidate text set from the plurality of first determination texts based on a first similarity between the search text and each first determination text;

[0086] determining a second candidate text set from the plurality of second determination texts based on a first similarity between the search text and each of the second determination texts;

[0087] The target candidate text set is determined according to the first candidate text set and the second candidate text set.

[0088] In some embodiments, the controller 250 is specifically configured to:

[0089] Obtaining, based on a size ratio between a length and a width of each first picture included in the first picture set, a size ratio between a length and a width of each second picture included in the second picture set, and at least one preset mapping relationship, a second similarity between the first picture set and each second picture set;

[0090] The preset mapping relationship includes a corresponding relationship between the size ratio and a preset standard resolution.

[0091] In some embodiments, the controller 250 is further configured to:

[0092] performing resolution conversion on the first pictures of various size ratios in the first picture set and the second pictures of the same size ratio in the second picture set according to the preset mapping relationship, to obtain a third picture set corresponding to the first picture set and a fourth picture set corresponding to the second picture set;

[0093] Obtaining fourth similarities between the third picture set and the fourth picture set at respective preset standard resolutions;

[0094] An average calculation is performed on the fourth similarities corresponding to multiple preset standard resolutions to obtain a second similarity between the first picture set and each of the second picture sets.

[0095] In some embodiments, the controller 250 is specifically configured to:

[0096] According to the target similarity between the search text and each of the target candidate texts, a plurality of the target candidate texts whose target similarity is greater than a preset threshold are sorted, and the media asset data is sent to the terminal device according to the sorting result.

[0097] In summary, the present disclosure executes the above-mentioned media aggregation method on a server, including: the controller of the server determines multiple judgment texts based on the search text, and obtains the first similarity between the search text and each judgment text respectively, wherein the judgment texts are texts in different languages; based on the first similarity between the search text and each judgment text, determines a target candidate text set from the multiple judgment texts; for a first picture set related to the search text and a second picture set related to each target candidate text in the target candidate text set, obtains the second similarity between the first picture set and each second picture set respectively; based on the first similarity and the second similarity, obtains the target similarity between the search text and each target candidate text; for the target similarity between the search text and each target candidate text, sends the media data corresponding to the target candidate text with a target similarity greater than a preset threshold to the terminal device, so that the terminal device displays the media data. In the above technical solution, by calculating the similarity between the search text and multiple judgment texts in different languages ​​determined based on the search text, the target candidate text set with a higher similarity to the search text is preferentially determined without translation, thereby solving the problem in the prior art that translation between different languages ​​cannot be achieved more accurately. Furthermore, the second similarity between the first picture set related to the search text and the second picture set related to each target candidate text is obtained, and the target similarity is determined by combining the first similarity and the second similarity. The media data displayed to the user is determined based on the target similarity, thereby improving the accuracy of the media data displayed to the user.

[0098] Figure 3 A system framework diagram of a method for media aggregation according to one or more embodiments of the present disclosure is shown in FIG. Figure 3As shown, the system may include a first similarity acquisition module 401 , a target candidate text set determination module 402 , a second similarity acquisition module 403 , a target similarity acquisition module 404 and an output module 405 . Among them, the first similarity acquisition module 401 is used to determine multiple judgment texts based on the search text, and respectively obtain the first similarity between the search text and each judgment text, wherein the judgment texts are texts in different languages; the target candidate text set determination module 402 is used to determine the target candidate text set in multiple judgment texts based on the first similarity between the search text and each judgment text; the second similarity acquisition module 403 is used to obtain the second similarity between the first picture set related to the search text and the second picture set related to each target candidate text in the target candidate text set; the target similarity acquisition module 404 is used to obtain the target similarity between the search text and each target candidate text based on the first similarity and the second similarity; the output module 405 is used to send the media data corresponding to the target candidate text whose target similarity is greater than a preset threshold to the terminal device based on the target similarity between the search text and each target candidate text, so that the terminal device displays the media data. In the above technical solution, by calculating the similarity between the search text and multiple judgment texts in different languages ​​determined based on the search text, the target candidate text set with a higher similarity to the search text is preferentially determined without translation, thereby solving the problem in the prior art that translation between different languages ​​cannot be achieved more accurately. Furthermore, the second similarity between the first picture set related to the search text and the second picture set related to each target candidate text is obtained, and the target similarity is determined by combining the first similarity and the second similarity. The media data displayed to the user is determined based on the target similarity, thereby improving the accuracy of the media data displayed to the user.

[0099] In order to explain this solution in more detail, the following will be combined with the following examples. Figure 5 To explain, it is understandable that Figure 4 The steps involved may include more steps or fewer steps in actual implementation, and the order of these steps may also be different, so long as the media resource aggregation method provided in the embodiment of the present disclosure can be implemented. The embodiment of the present disclosure does not limit this.

[0100] Figure 4 This is a flow chart of a media aggregation method provided by an embodiment of the present disclosure. This embodiment is applied to a server, such as Figure 4 As shown, the media resource aggregation method specifically includes the following steps:

[0101] S51 : determining a plurality of determination texts according to the search text, and respectively obtaining a first similarity between the search text and each determination text.

[0102] Among them, the search text refers to the text used to determine the media data requested by the user. The search text can be, for example, the title of a film or TV work, or the director corresponding to a film or TV work, or part of the content in the introduction, but is not limited to this. This disclosure does not specifically limit it, and technical personnel in this field can set it according to actual conditions.

[0103] The above determination texts are texts in different languages. The determination text refers to a text in the same language as the search text, or in a different language, and representing the same meaning, but is not limited thereto. This disclosure does not specifically limit this, and those skilled in the art can set it according to actual circumstances.

[0104] The first similarity is used to determine the similarity between each determination text and the search text, that is, a text having a high similarity to the search text can be determined from a plurality of determination texts based on the first similarity.

[0105] Specifically, the controller of the server determines a plurality of determination texts in different languages ​​according to the search text, and after determining the plurality of determination texts in different languages, obtains a first similarity between the search text and each determination text.

[0106] For example, for a search text such as "XXX" in Chinese, multiple judgment text examples in different languages ​​are determined, such as other languages ​​corresponding to "XXX" such as English, Japanese, French, etc., but not limited to this. The present disclosure does not specifically limit it, and those skilled in the art can set it according to actual conditions.

[0107] Optionally, the controller of the server may perform a traversal search in a preset database based on the search text to determine the judgment texts in multiple different languages, but is not limited thereto.

[0108] S52: Determine a target candidate text set from the plurality of determination texts according to the first similarity between the search text and each determination text.

[0109] Specifically, after determining the first similarity between the search text and each decision text, the server controller further screens multiple decision texts based on the first similarity between the search text and each decision text to determine a set of target candidate texts with a high similarity to the search text.

[0110] S53 , for the first picture set related to the search text and the second picture set related to each target candidate text in the target candidate text set, respectively obtain a second similarity between the first picture set and each second picture set.

[0111] Among them, the first picture set refers to posters, stills and other pictures related to the search text. For example, if the search text is the name "XXX" corresponding to the film and television work "XXX", then the first picture set is posters, stills and other pictures related to the search text "XXX", and the second picture set is posters, stills and other pictures related to each target candidate text. To obtain the first picture set related to the search text and the second picture set related to each target candidate text in the target candidate text set, it can be searched in a preset database based on the search text and each target candidate text, but is not limited to this. This disclosure does not specifically limit it, and those skilled in the art can set it according to actual conditions.

[0112] Specifically, the controller of the server obtains a first picture set related to the search text and a second picture set related to each target candidate text in the target candidate text set. After obtaining the first picture set and the second picture set related to each target candidate text, the controller obtains a second similarity between the first picture set and the second picture set related to each target candidate text.

[0113] S54 : Obtain target similarities between the search text and each target candidate text according to the first similarity and the second similarity.

[0114] Specifically, the controller of the server determines the target similarity between the search text and each target candidate text based on the first similarity between the search text and each target candidate text, and the second similarity between the first picture set related to the search text and the second picture set related to each target candidate text.

[0115] Optionally, based on the above embodiment, in some embodiments of the present disclosure, one implementation method for obtaining the target similarity between the search text and each target candidate text according to the first similarity and the second similarity may be:

[0116] The first similarity and the second similarity are weightedly summed to obtain the target similarity between the search text and each target candidate text.

[0117] Exemplarily, the first similarity is set to S1 and the second similarity is set to S2, and the first similarity S1 and the first similarity S2 are weighted and summed to obtain the target similarity S = a*S1+b*S2, wherein a represents the weight of the first similarity and b represents the weight of the second similarity. The values ​​of a and b are determined according to actual conditions and are not specifically limited in this disclosure.

[0118] S55 , based on the target similarity between the search text and each target candidate text, sending the media asset data corresponding to the target candidate text whose target similarity is greater than a preset threshold to the terminal device, so that the terminal device displays the media asset data.

[0119] Among them, the preset threshold is a parameter set to determine the target candidate text with a higher similarity to the search text among multiple target candidate texts. The preset threshold can be 0.7, for example, but is not limited to this. This disclosure does not specifically limit it, and those skilled in the art can set it according to actual conditions.

[0120] The above-mentioned media data refers to data information associated with the target candidate text. Because the target candidate text is similar to the search text, the media data is data information associated with the search text. For example, it can be the director, introduction, actors, ranking, and related video playback programs of film and television works, but is not limited to this. This disclosure does not specifically limit it, and those skilled in the art can set it according to actual conditions.

[0121] Specifically, after obtaining the target similarity between the search text and each target candidate text, the server controller compares each target similarity with a preset threshold in turn. When it is determined that the target similarity is greater than the preset threshold, the media data corresponding to the target candidate text whose current target similarity is greater than the preset threshold is sent to the terminal device so that the terminal device displays the media data.

[0122] In the technical solution provided by the embodiment of the present disclosure, the controller of the server determines multiple judgment texts based on the search text, and obtains the first similarity between the search text and each judgment text respectively, wherein the judgment texts are texts in different languages; based on the first similarity between the search text and each judgment text, a target candidate text set is determined in the multiple judgment texts; for a first picture set related to the search text and a second picture set related to each target candidate text in the target candidate text set, a second similarity between the first picture set and each second picture set is obtained respectively; based on the first similarity and the second similarity, a target similarity between the search text and each target candidate text is obtained; for the target similarity between the search text and each target candidate text, the media data corresponding to the target candidate text with a target similarity greater than a preset threshold is sent to the terminal device, so that the terminal device displays the media data. In the above technical solution, by calculating the similarity between the search text and multiple judgment texts in different languages ​​determined based on the search text, the target candidate text set with a higher similarity to the search text is preferentially determined without translation, thereby solving the problem in the prior art that translation between different languages ​​cannot be achieved more accurately. Furthermore, the second similarity between the first picture set related to the search text and the second picture set related to each target candidate text is obtained, and the target similarity is determined by combining the first similarity and the second similarity. The media data displayed to the user is determined based on the target similarity, thereby improving the accuracy of the media data displayed to the user.

[0123] Figure 5Schematic flowchart of another media asset aggregation method provided by an embodiment of the present disclosure Figure 5 Based on the embodiment shown in Figure 4 Furthermore, since multiple determination texts include: at least one first determination text and at least one second determination text, where the first determination text is determined by directly searching in a preset database according to the search text, and the second determination text is determined by indirectly searching in the preset database for each first text in the first text set corresponding to each first determination text. Based on this, for each first determination text and each second determination text, the ways of obtaining the first similarity with the search text are different. As shown in Figure 5 For each first determination text, one implementation of determining the first similarity between the search text and each first determination text can be:

[0124] S62. For each first determination text, determine the first text set corresponding to the first determination text.

[0125] The first text set refers to texts with the same language as each first determination text and the same text content. Exemplarily, for the first determination text "Hero X Color", each first text in the first text set is "Hero X Color". It should be noted that each first text in the first text set may come from the same film and television work or different film and television works. The present disclosure does not specifically limit this, and those skilled in the art can set it according to actual situations.

[0126] Specifically, for each first determination text, the controller of the server searches in the preset data according to each first determination text to determine the first text set corresponding to the first determination text.

[0127] S63. According to multiple preset information associated with the first determination text and multiple preset information associated with each first text in each first text set, determine the first similarity between the search text and each first determination text.

[0128] The preset information refers to information related to the first determination text and information that can describe the work related to the first determination text. For example, for film and television work 1, the preset information can be, for example, the director, introduction, actor names, etc. of the film and television work 1, but is not limited thereto. The present disclosure does not specifically limit this, and those skilled in the art can set it according to actual situations.

[0129] Specifically, the controller of the server obtains multiple preset information associated with the first determination text and multiple preset information associated with each first text, and determines the first similarity between the search text and each first determination text according to the multiple preset information associated with the first determination text and the multiple preset information associated with each first text.

[0130] Optionally, based on the above embodiment, in some embodiments of the present disclosure, one implementation method for determining the first similarity between the search text and each first determination text based on multiple preset information associated with the first determination text and multiple preset information associated with each first text in each first text set may be:

[0131] The similarities between the first judgment text and each first text under each preset information are calculated respectively. The similarities between the first judgment text and each first text under multiple preset information are weighted summed to obtain the first similarities between the search text and each first judgment text.

[0132] For example, when multiple preset information are director and introduction, when the preset information is director, determine the director list 1 of the film and television work 1 to which the first judgment text belongs, and the director list 2 of the film and television work 2 to which the first text belongs. Based on the director list 1 and the director list 2, determine the total number of directors A of the film and television work 1 and the film and television work 2, and the number of directors B shared by the film and television work 1 and the film and television work 2. Calculate the ratio of the number of directors B to the number of directors A to obtain the similarity S between the first judgment text and the first text when the preset information is director. d＝ B / A. When the preset information is an introduction, for introduction 1 of the film and television work 1 to which the first judgment text belongs, by performing word segmentation processing on introduction 1, obtain keyword set 1 corresponding to introduction 1. For introduction 2 of the film and television work 2 to which the first text belongs, by performing word segmentation processing on introduction 2, obtain keyword set 2 corresponding to introduction 2. The number of keywords C and the number of keywords D corresponding to keyword set 1 and keyword set 2 are obtained respectively, as well as the number of keywords E shared by keyword set 1 and keyword set 2. Then, based on the number of keywords C, the number of keywords D, and the number of keywords E, calculate the similarity between the first judgment text and the first text when the preset information is an introduction. Furthermore, the similarity between the first judgment text with the preset information of director and introduction and the first text is weighted summed to obtain the first similarity S between the search text and the first judgment text. 1＝ d*S d +s*S s , where d represents the weight of the similarity between the first judgment text and the first text when the preset information is director, and s represents the weight of the similarity between the first judgment text and the first text when the preset information is introduction. The values ​​of d and s are determined according to actual conditions and are not specifically limited in this disclosure.

[0133] In the technical solution provided by the embodiments of the present disclosure, in the above process, according to multiple preset information associated with the first determination text and multiple preset information associated with each first text, the first similarity between the search text and each first determination text is calculated from a multi-dimensional perspective, thereby improving the accuracy of calculating the first similarity between the search text and each first determination text.

[0134] Optionally, continue to refer to Figure 5 As shown, for each second determination text, an implementation manner for determining the first similarity between the search text and each second determination text may be:

[0135] S64. For each first text included in each first text set corresponding to each first determination text, obtain at least one second determination text corresponding to each first text.

[0136] Wherein, the second determination text is a text in a different language from each first text and has the same meaning as each first text. Exemplarily, if the first text is the Chinese "Hero X Color", then the second determination text is the text corresponding to the other language of "Hero X Color". However, this is not limited thereto, and the present disclosure does not specifically limit it, and those skilled in the art can set it according to actual situations.

[0137] Specifically, for each first text included in each first text set corresponding to each first determination text, the controller of the server searches in the preset database according to each first text and obtains one or more second determination texts corresponding to each first text.

[0138] It should be noted that after obtaining one or more second determination texts corresponding to each first text, when it is determined that there is a text in the same language as the first determination text among the one or more second determination texts, then the second determination text is filtered.

[0139] S65. For each first text and each second determination text corresponding to each first text, obtain the third similarity between the first text and each second determination text.

[0140] Specifically, for each first text and each second determination text corresponding to each first text, the controller of the server obtains the third similarity between the first text and each second determination text.

[0141] Optionally, the third similarity between the first text and each second determination text can be obtained by calculating the similarity between the first text and each second determination text under multiple preset information and performing weighted summation on the similarity under the multiple preset information. However, this is not limited thereto, and the present disclosure does not specifically limit it.

[0142] S66 , calculating the product of the first similarity between the first determination text and each first text and the third similarity between the first text and the second determination text to obtain the first similarity between the search text and each second determination text.

[0143] Specifically, the controller of the server performs a product operation on the first similarities between the first determination text and each first text, and the third similarities between the first text and the second determination text, thereby obtaining the first similarities between the search text and each second determination text.

[0144] It should be noted that, when it is determined that the third similarity between the first text and each second determination text is less than the preset similarity, there is no need to calculate the first similarity between the current second determination text and the search text.

[0145] In the technical solution provided by the embodiment of the present disclosure, in the above process, after determining the first text set corresponding to the first judgment text, the second judgment text corresponding to the search text is obtained based on the various first texts included in the first text set, which can avoid omitting media data with high similarity to the search text, thereby fully displaying media data related to the search information to the user.

[0146] Figure 6 A flowchart of another media resource aggregation method provided by an embodiment of the present disclosure is shown below. Figure 6 is Figure 5 On the basis of the illustrated embodiment, further, one implementation method for determining a target candidate text set from a plurality of determination texts based on the first similarity between the search text and each determination text may be:

[0147] S71 : determining a first candidate text set from a plurality of first determination texts based on a first similarity between the search text and each first determination text.

[0148] Specifically, the controller of the server compares the first similarities between the search text and each first determination text according to the sizes of the multiple first similarities, and determines a first candidate text set from the multiple first determination texts.

[0149] For example, for multiple first similarities S1, S2, S3, S4, S5...Sn, the first candidate text may be determined by determining the first judgment text with the maximum first similarity among S1, S2, S3, S4, S5...Sn. Alternatively, the first candidate text set may be determined based on the sorting results of the multiple first similarities S1, S2, S3, S4, S5...Sn. However, this is not intended to limit the present disclosure, and those skilled in the art may determine the first candidate text set based on actual circumstances.

[0150] S72 : determining a second candidate text set from the plurality of second determination texts based on the first similarities between the search text and each second determination text.

[0151] Specifically, the controller of the server compares the first similarities between the search text and each second determination text according to the sizes of the multiple first similarities, and determines a first candidate text set from the multiple second determination texts.

[0152] S73: Determine a target candidate text set according to the first candidate text set and the second candidate text set.

[0153] Specifically, the controller of the server combines the first candidate text set and the second candidate text set to determine a target candidate text set corresponding to the search text.

[0154] In the technical solution provided by the embodiment of the present disclosure, in the above process, the first candidate text set and the second candidate text set can be combined to determine the target candidate text set corresponding to the search text, thereby avoiding omitting media data with high similarity to the search text, so that media data related to the search information can be fully displayed to the user.

[0155] Figure 7 A flowchart of another media resource aggregation method provided by an embodiment of the present disclosure is shown below. Figure 7 is Figure 6 On the basis of the embodiment shown, after obtaining the target candidate text set corresponding to the search text, the accuracy of the media asset data displayed to the user is improved by combining the first image set related to the search text and the second image set related to each target candidate text on the basis of the first similarity. Figure 7 As shown, one implementation method of obtaining the second similarity between the first picture set and each second picture set may be:

[0156] S81, obtaining second similarities between the first picture set and each second picture set based on the size ratio corresponding to the length and width of each first picture included in the first picture set, the size ratio corresponding to the length and width of each second picture included in the second picture set, and at least one preset mapping relationship.

[0157] The size ratio is the ratio between the length and width of each first picture or each second picture, such as Figure 8 As shown, the size ratio of the first image 901 is the ratio between the length l and the width d, for example, it can be l:d=16:9, or it can be 4:3, 3:4, 2:3, 3:2, but it is not limited to this. The present disclosure does not specifically limit it, and those skilled in the art can set it according to actual conditions.

[0158] The above-mentioned preset mapping relationship includes a correspondence between a size ratio and a preset standard resolution. For example, following the above embodiment, for a size ratio of 16:9, the corresponding preset standard resolution is 480*270, correspondingly, for a size ratio of 4:3, the corresponding preset standard resolution is 480*360, for a size ratio of 3:4, the corresponding preset standard resolution is 360*480, for a size ratio of 2:3, the corresponding preset standard resolution is 320*480, and for a size ratio of 3:2, the corresponding preset standard resolution is 480*320, but the present disclosure is not limited thereto, and those skilled in the art may set it according to actual conditions.

[0159] Specifically, the controller of the server obtains the second similarity between the first picture set and each second picture set based on the size ratio corresponding to the length and width of each first picture included in the first picture set, the size ratio corresponding to the length and width of each second picture included in the second picture set, and one or more preset mapping relationships including the correspondence between the size ratio and the preset standard resolution.

[0160] Figure 9 A flowchart of another media resource aggregation method provided by an embodiment of the present disclosure is shown below. Figure 9 is Figure 7 On the basis of the embodiment shown, further, as Figure 9 As shown, one implementation of S81 may be:

[0161] S101 , performing resolution conversion on first pictures of various size ratios in a first picture set and second pictures of the same size ratios in a second picture set according to a preset mapping relationship to obtain a third picture set and a fourth picture set.

[0162] Specifically, the controller of the server determines the size ratio of each first picture included in the first picture set, and determines the size ratio of each second picture included in the second picture set. According to the preset mapping relationship, the first pictures of each size ratio in the first picture set and the second pictures of the same size ratio in the second picture set are converted into resolution, thereby obtaining a third picture set corresponding to the first picture set and a fourth picture set corresponding to the second picture set.

[0163] S102: Obtain fourth similarities between the third picture set and the fourth picture set at respective preset standard resolutions.

[0164] Specifically, the controller of the server obtains the fourth similarities corresponding to the third picture set and the fourth picture set at each preset standard resolution.

[0165] For example, for a first picture x with a size ratio of 16:9 included in the first picture set, determine the second pictures y and z with the same size ratio of 16:9 in the second picture set, perform resolution conversion on the first picture x, the second picture y, and the second picture z respectively, and obtain a third picture x1, a fourth picture y1, and a fourth picture z1 with a preset standard resolution of 480*270, and calculate the similarity S between the third picture x1 and the fourth picture y1 xy , the similarity S between the third image x1 and the fourth image z1 xz , by comparing S xy With S xz The size between them determines S xy With S xz The maximum value between them is the fourth similarity between the third picture set and the fourth picture set at the preset standard resolution of 480*270, but is not limited thereto. The present disclosure does not specifically limit this, and those skilled in the art can set it according to actual conditions.

[0166] Optionally, continuing with the above embodiment, the similarity S between the third image x1 and the fourth image y1 is calculated. xy The specific expression of is defined as follows:

[0167]

[0168] Among them, μ x represents the mean value of the pixel values ​​included in the third image x1, μ y represents the mean value of the pixel values ​​included in the fourth image y1, σ x represents the standard deviation of the pixel values ​​in the third image x1, σ y represents the standard deviation of the pixel values ​​in the fourth image y1, c1 and c2 represent stability constants, c1 = (k1*) 2 , c2=(k2*) 2 , where L represents the pixel value, and the values ​​of k1 and k2 are determined according to the pixel value L. For example, when L is 255, k1 is 0.01 and k2 is 0.03, but it is not limited to this. The present disclosure does not specifically limit it, and those skilled in the art can set it according to actual conditions.

[0169] Optionally, based on the above embodiments, in some embodiments of the present disclosure, when calculating the fourth similarity between the third picture and the fourth picture, the third picture and the fourth picture can be segmented to obtain the similarity between each image block in the third picture and the fourth picture, and further obtain the fourth similarity between the third picture and the fourth picture, so as to improve the accuracy of the fourth similarity.

[0170] S103 , performing average calculation on the fourth similarities corresponding to the plurality of preset standard resolutions to obtain second similarities between the first picture set and each second picture set.

[0171] Specifically, for the fourth similarities corresponding to the plurality of preset standard resolutions, the controller of the server averages the plurality of fourth similarities to obtain the second similarities between the first picture set and each of the second picture sets.

[0172] In the technical solution provided by the embodiments of the present disclosure, in the above process, by obtaining the fourth similarity between different preset standard resolutions corresponding to different size ratios, and further obtaining the second similarity between the first image set and each second image set based on multiple fourth similarities, the accuracy of the second similarity is improved.

[0173] Figure 10 A flowchart of another media resource aggregation method provided by an embodiment of the present disclosure is shown below. Figure 10 is Figure 9 On the basis of the embodiment shown, further, as Figure 10 As shown, one implementation method of sending the media asset data corresponding to the target candidate text whose target similarity is greater than a preset threshold to the terminal device may be:

[0174] S111 , according to the target similarity between the search text and each target candidate text, multiple target candidate texts having target similarity greater than a preset threshold are sorted, and media asset data is sent to the terminal device according to the sorting result.

[0175] Specifically, the server controller determines multiple target candidate texts whose target similarity is greater than a preset threshold based on the target similarity between the search text and each target candidate text, and sorts the multiple target candidate texts whose target similarity is greater than the preset threshold, and sends the media data corresponding to the target candidate text to the terminal device based on the sorting results.

[0176] In the technical solution provided by the embodiment of the present disclosure, in the above process, the target candidate texts can be sorted and processed, and media data can be sent to the terminal device based on the sorting results, so that the media data with a high similarity to the search text can be displayed to the user first, thereby improving the user experience.

[0177] The present disclosure provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the various processes of the above-described media aggregation method and achieves the same technical effects. To avoid repetition, the details are not described here. The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0178] The present disclosure provides a computer program product, including: when the computer program product is run on a computer, the computer is enabled to implement the above-mentioned media asset aggregation method.

[0179] For ease of explanation, the above description has been made in conjunction with specific embodiments. However, the above discussion of some embodiments is not intended to be exhaustive or to limit the embodiments to the specific forms disclosed above. Based on the above teachings, various modifications and variations can be obtained. The selection and description of the above embodiments are intended to better explain the principles and practical applications, so that those skilled in the art can better use the embodiments and various different variations of the embodiments suitable for specific use considerations.

Claims

1. A server, characterized in that: include: The controller is configured as: Determining a plurality of determination texts based on the search text, and obtaining first similarities between the search text and each of the determination texts, wherein the determination texts are texts in different languages; and the determination texts are texts having the same meaning as the search text; Determining a target candidate text set from a plurality of the determination texts according to a first similarity between the search text and each of the determination texts; For the first picture set related to the search text and the second picture set related to each target candidate text in the target candidate text set, respectively obtain a second similarity between the first picture set and each second picture set; Obtaining target similarities between the search text and each of the target candidate texts based on the first similarity and the second similarity; According to the target similarity between the search text and each target candidate text, the media asset data corresponding to the target candidate text having the target similarity greater than a preset threshold is sent to the terminal device, so that the terminal device displays the media asset data.

2. The server according to claim 1, wherein: The plurality of determination texts include: at least one first determination text; The controller is specifically configured to: For each of the first determination texts, determining a first text set corresponding to the first determination text, where the first text set refers to texts in the same language and with the same text content as the first determination texts; A first similarity between the search text and each of the first determination texts is determined based on multiple preset information associated with the first determination text and multiple preset information associated with each of the first texts in each of the first text sets.

3. The server according to claim 2, wherein: The plurality of determination texts further includes: at least one second determination text; The controller is further configured to: For each first text included in each first text set corresponding to each first determination text, obtaining at least one second determination text corresponding to each first text, where the second determination text is a text in a different language from the first text and has the same meaning as the first text; For each of the first texts and each of the second determination texts corresponding to each of the first texts, obtaining a third similarity between the first text and each of the second determination texts; The product of the first similarity between the first determination text and each of the first texts and the third similarity between the first text and the second determination text is calculated to obtain the first similarity between the search text and each of the second determination texts.

4. The server according to claim 3, wherein: The controller is specifically configured to: Determining a first candidate text set from the plurality of first determination texts based on a first similarity between the search text and each first determination text; determining a second candidate text set from the plurality of second determination texts based on a first similarity between the search text and each of the second determination texts; The target candidate text set is determined according to the first candidate text set and the second candidate text set.

5. The server according to claim 1, wherein: The controller is specifically configured to: Obtaining, based on a size ratio between a length and a width of each first picture included in the first picture set, a size ratio between a length and a width of each second picture included in the second picture set, and at least one preset mapping relationship, a second similarity between the first picture set and each second picture set; The preset mapping relationship includes a corresponding relationship between the size ratio and a preset standard resolution.

6. The server according to claim 5, wherein: The controller is further configured to: performing resolution conversion on the first pictures of various size ratios in the first picture set and the second pictures of the same size ratio in the second picture set according to the preset mapping relationship, to obtain a third picture set corresponding to the first picture set and a fourth picture set corresponding to the second picture set; Obtaining fourth similarities between the third picture set and the fourth picture set at respective preset standard resolutions; An average calculation is performed on the fourth similarities corresponding to multiple preset standard resolutions to obtain a second similarity between the first picture set and each of the second picture sets.

7. The server according to claim 1, wherein: The controller is specifically configured to: According to the target similarity between the search text and each of the target candidate texts, a plurality of the target candidate texts whose target similarity is greater than a preset threshold are sorted, and the media asset data is sent to the terminal device according to the sorting result.

8. A media resource aggregation method, characterized in that: include: Determining a plurality of determination texts based on the search text, and obtaining first similarities between the search text and each of the determination texts, wherein the determination texts are texts in different languages; and the determination texts are texts having the same meaning as the search text; Determining a target candidate text set from a plurality of the determination texts according to a first similarity between the search text and each of the determination texts; For the first picture set related to the search text and the second picture set related to each target candidate text in the target candidate text set, respectively obtain a second similarity between the first picture set and each second picture set; Obtaining target similarities between the search text and each of the target candidate texts based on the first similarity and the second similarity; According to the target similarity between the search text and each target candidate text, the media asset data corresponding to the target candidate text having the target similarity greater than a preset threshold is sent to the terminal device, so that the terminal device displays the media asset data.

9. The method according to claim 8, characterized in that The plurality of judgment texts include: at least one first judgment text; including: For each of the first determination texts, determining a first text set corresponding to the first determination text, where the first text set refers to texts in the same language and with the same text content as the first determination texts; A first similarity between the search text and each of the first determination texts is determined based on multiple preset information associated with the first determination text and multiple preset information associated with each of the first texts in each of the first text sets.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 8 to 9 are implemented.

Images