A method, apparatus, device, and computer-readable storage medium for determining media assets.

Abstract

This application discloses a media asset determination method, which includes: determining a first parameter corresponding to the media asset to be matched and a second parameter corresponding to each candidate media asset based on the tags of the media asset to be matched and the tags of each candidate media asset; wherein the first parameter represents the tag situation of the media asset to be matched; the second parameter represents the tag situation of the candidate media asset; acquiring historical behavior information of a target object towards the media asset to be matched, and determining a third parameter of the tags corresponding to the historical behavior information based on the historical behavior information; wherein the third parameter represents the preference of the target object; determining the correlation degree between the media asset to be matched and each candidate media asset based on the first parameter, the second parameter, and the third parameter; and determining the target media asset corresponding to the target object from multiple candidate media assets based on the correlation degree. This application also discloses a media asset determination device, equipment, and computer-readable storage medium.

Description

Technical Field

[0001] This application relates to the field of Internet technology, and in particular to a method, apparatus, device and computer-readable storage medium for determining media assets. Background Technology

[0002] Currently, driven by the surge in artificial intelligence and big data, recommendation systems are widely applied in user-facing service sectors, such as video services, news services, and e-commerce services. Typically, media asset recommendations are made by first identifying similar media assets with the same tags as the current media asset; then calculating the similarity between the current media asset and similar media assets; and finally ranking the similar media assets based on similarity or by combining similarity with popularity to recommend media assets to users. However, current technologies only consider the similarity between the current media asset and similar media assets when recommending media assets to users, without considering user behavior preferences. This results in low intelligence in media asset recommendations and a low match between recommended media assets and users. Summary of the Invention

[0003] To address the aforementioned technical problems, embodiments of this application aim to provide a media asset determination method, apparatus, device, and computer-readable storage medium, which can solve the problem of low intelligence in media asset recommendation in related technologies, improve the intelligence of media asset recommendation, and enhance the matching degree between recommended media assets and users.

[0004] The technical solution of this application is implemented as follows:

[0005] A method for determining media assets, the method comprising:

[0006] Based on the tags of the media asset to be matched and the tags of each candidate media asset, a first parameter corresponding to the media asset to be matched and a second parameter corresponding to each candidate media asset are determined; wherein, the first parameter represents the tag situation of the media asset to be matched; and the second parameter represents the tag situation of the candidate media asset.

[0007] The system obtains historical behavior information of the target object regarding the media asset to be matched, and determines a third parameter of the tag corresponding to the historical behavior information based on the historical behavior information; wherein the third parameter represents the target object's preference.

[0008] Based on the first parameter, the second parameter, and the third parameter, the correlation degree between the media asset to be matched and each candidate media asset is determined;

[0009] Based on the correlation, the target media asset corresponding to the target object is determined from a plurality of candidate media assets.

[0010] In the above scheme, determining the first parameter corresponding to the media asset to be matched and the second parameter corresponding to each media asset to be selected based on the tag of the media asset to be matched and the tag of each media asset to be selected includes:

[0011] The tags of the media assets to be matched and the tags of each media asset to be selected are deduplicated to obtain deduplicated tags;

[0012] The first parameter is determined based on the deduplication tag and the tag of the media asset to be matched;

[0013] Based on the deduplication tag and the tag of each candidate media asset, a plurality of the second parameters are determined.

[0014] In the above scheme, determining the first parameter based on the deduplication tag and the tag of the media asset to be matched includes:

[0015] Based on the number of deduplicated tags, a first initial vector corresponding to the tags of the media asset to be matched is generated; wherein, the values ​​of all elements in the first initial vector are the same;

[0016] The deduplicated tags are sorted using a target sorting method to obtain sorted deduplicated tags;

[0017] Determine the first order of the tags of the media asset to be matched in the sorted and deduplicated tags;

[0018] The values ​​of the elements in the first initial vector corresponding to the first arrangement order are modified to obtain the first target vector; wherein, the first parameter includes the first target vector;

[0019] In the above scheme, determining multiple second parameters based on the deduplication tag and the tag of each candidate media asset includes:

[0020] Based on the number of deduplication tags, a second initial vector is generated corresponding to the tag of each candidate media asset; wherein, the values ​​of the elements in the second initial vector are all the same, and the values ​​of the corresponding elements in the first initial vector and the second initial vector are the same;

[0021] Determine the second arrangement order of the tags for each candidate media asset in the sorted and deduplicated tags;

[0022] The values ​​of the elements in the second initial vector corresponding to the second arrangement order are modified to obtain the second target vector; wherein, the second parameter includes the second target vector.

[0023] In the above scheme, the third parameter for determining the tag corresponding to the historical behavior information based on the historical behavior information includes:

[0024] The historical behavior information is analyzed to determine the number of times each candidate media asset's tag has been manipulated;

[0025] Based on the number of operations and the number of deduplication tags, a third initial vector for the target object is generated;

[0026] Each element in the third initial vector is normalized to obtain the third target vector; wherein the third parameter includes the third target vector.

[0027] In the above scheme, the normalization process for each element in the third initial vector to obtain the third target vector includes:

[0028] Determine the target element; wherein, the target element is the element corresponding to the tag that is operated on most frequently among the tags of the candidate media assets;

[0029] Determine the number of first objects and the number of second objects that operate on the tag of each candidate media asset; wherein, the second object refers to an object registered in the application corresponding to the candidate media asset;

[0030] The third target vector is obtained by processing each element based on the target element, the number of the first object, and the number of the second object.

[0031] In the above scheme, determining the correlation between the media asset to be matched and each candidate media asset based on the first parameter, the second parameter, and the third parameter includes:

[0032] Based on the first target vector, the second target vector, and the third target vector, determine the first numerical value;

[0033] The first target vector is moduloed to obtain a first modulo value, and each second target vector is moduloed to obtain multiple second modulo values;

[0034] The first modulus value and the plurality of second modulus values ​​are used to calculate the second value, and the first value and the second value are used to calculate the correlation degree.

[0035] In the above scheme, determining the first value based on the first target vector, the second target vector, and the third target vector includes:

[0036] Calculate the corresponding elements in the first target vector, each of the second target vectors, and the third target vector to obtain multiple third values;

[0037] The first value is obtained by performing calculations on the plurality of third values.

[0038] In the above scheme, determining the target media asset corresponding to the target object from multiple candidate media assets based on the correlation degree includes:

[0039] The candidate media assets are sorted based on the correlation to obtain the sorted candidate media assets;

[0040] The target media asset is determined from the sorted candidate media assets.

[0041] A media asset determination device, the device comprising:

[0042] The first processing unit is configured to determine a first parameter corresponding to the media asset to be matched and a second parameter corresponding to each media asset to be selected, based on the tags of the media asset to be matched and the tags of each media asset to be selected; wherein, the first parameter represents the tag information of the media asset to be matched; and the second parameter represents the tag information of the media asset to be selected.

[0043] The second processing unit is used to acquire historical behavior information of the target object towards the media asset to be matched, and to determine a third parameter of the tag corresponding to the historical behavior information based on the historical behavior information; wherein the third parameter represents the preference of the target object;

[0044] The third processing unit is used to determine the correlation between the media asset to be matched and each candidate media asset based on the first parameter, the second parameter and the third parameter;

[0045] A determining unit is used to determine the target media asset corresponding to the target object from a plurality of candidate media assets based on the correlation degree.

[0046] A media asset determination device, the device comprising: a processor, a memory, and a communication bus;

[0047] The communication bus is used to realize the communication connection between the processor and the memory;

[0048] The processor is used to execute the media asset determination program stored in the memory to implement the steps of the media asset determination method described above.

[0049] A computer-readable storage medium storing one or more programs that can be executed by one or more processors to perform the steps of the media asset determination method described above.

[0050] The media asset determination method, apparatus, device, and computer-readable storage medium provided in this application first determine a first parameter representing the label of the media asset to be matched and a second parameter representing the label of the media asset to be matched, based on the label of the media asset to be matched and the label of each candidate media asset. Then, it obtains historical behavior information of the target object regarding the media asset to be matched and determines a third parameter representing the target object's preferences based on the historical behavior information. Next, it determines the correlation degree between the media asset to be matched and each candidate media asset based on the first, second, and third parameters. Finally, it determines the correlation degree based on the relevant parameters. The system identifies the target media asset from multiple candidate media assets. This takes into account the target object's historical behavior information regarding the media asset to be matched. Furthermore, it determines the similarity between the media asset to be matched and each candidate media asset based on a first parameter corresponding to the media asset to be matched, a second parameter corresponding to the candidate media asset, and a third parameter corresponding to the tags of the historical behavior information. This approach improves the intelligence of media asset recommendation and enhances the matching degree between the recommended media assets and the user. Attached Figure Description

[0051] Figure 1 A flowchart illustrating a media asset determination method provided in an embodiment of this application;

[0052] Figure 2 A flowchart illustrating another method for determining media assets provided in this application embodiment;

[0053] Figure 3 A flowchart illustrating personalized media asset recommendation in a media asset determination method provided in this application embodiment;

[0054] Figure 4 This is a schematic diagram of the structure of a media asset determination device provided in an embodiment of this application;

[0055] Figure 5 This is a schematic diagram of the structure of a media asset determination device provided in an embodiment of this application. Detailed Implementation

[0056] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0057] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0058] This application provides a method for determining media assets, which can be applied to a media asset determination device. (Refer to...) Figure 1As shown, the method includes the following steps:

[0059] Step 101: Based on the tags of the media assets to be matched and the tags of each candidate media asset, determine the first parameter corresponding to the media asset to be matched and the second parameter corresponding to each candidate media asset.

[0060] The first parameter represents the tag information of the media asset to be matched; the second parameter represents the tag information of the media asset to be selected.

[0061] In this embodiment of the application, a tag may refer to information used to identify the category or content of a media asset; a media asset to be matched may refer to a media asset for which a target media asset needs to be determined to match; a media asset to be selected may refer to multiple media assets in a media asset library for selection; it should be noted that a media asset to be matched may have multiple different tags, and each media asset to be selected may also have multiple different tags; the number of tags for each media asset to be selected may be different.

[0062] In this embodiment of the application, the tags of the media assets to be matched and the total tag of each candidate media asset can be determined first. Then, the first parameter corresponding to the media asset to be matched is obtained through the total tag and the tag of the media asset to be matched, and the second parameter corresponding to each candidate media asset is obtained through the total tag and the tag of each candidate media asset.

[0063] Step 102: Obtain the target object's historical behavior information for the media asset to be matched, and determine the third parameter of the tag corresponding to the historical behavior information based on the historical behavior information.

[0064] The third parameter represents the target object's preferences.

[0065] In this application embodiment, the target object may refer to the user who generates historical behavior information for the media asset to be matched, and the historical behavior information may refer to the operation information of the media asset to be matched generated after the target object operates on the media asset to be matched; in a feasible implementation, the historical behavior information may refer to the behavior of playing the media asset to be matched, collecting the media asset to be matched, and ordering the media asset to be matched; the historical behavior information of the target object for the media asset to be matched may refer to the target user playing the media asset to be matched, the target user collecting the media asset to be matched, and / or the target user ordering the media asset to be matched, etc.

[0066] In this embodiment of the application, the media asset determination device can periodically acquire historical behavior information of the target object for the media asset to be matched, then analyze the historical behavior information to obtain the tag corresponding to the historical behavior information, and then analyze the tag corresponding to the historical behavior information to obtain the third parameter of the tag corresponding to the historical behavior information.

[0067] Step 103: Based on the first parameter, the second parameter, and the third parameter, determine the correlation between the media asset to be matched and each candidate media asset.

[0068] Among them, the relevance represents the degree of similarity between the media asset to be matched and each candidate media asset.

[0069] In this embodiment of the application, the elements in the first parameter, each of the second parameters, and the third parameter can be calculated to obtain the similarity between the media asset to be matched and each candidate media asset; thus, taking into account the third parameter of the target object's preferences, the matching degree between the target media asset recommended for the media asset to be matched and the user is improved.

[0070] Step 104: Based on relevance, determine the target media asset corresponding to the target object from multiple candidate media assets.

[0071] The target media asset can refer to a media asset that has a high degree of relevance to the media asset to be matched; it should be noted that there can be multiple target media assets.

[0072] In this embodiment of the application, each correlation degree can be processed to obtain a processing result, and then multiple media assets can be determined from multiple candidate media assets as target media assets based on the processing result. The target media assets can be recommended to the target object, thus ensuring the quantity of target media assets.

[0073] The media asset determination method provided in this application takes into account the target object's historical behavior information regarding the media asset to be matched, and recommends target media assets based on the first parameter corresponding to the media asset to be matched, the second parameter corresponding to the media asset to be selected, and the third parameter of the tag corresponding to the historical behavior information, which together determine the similarity between the media asset to be matched and each media asset to be selected. This method does not simply recommend media assets based on the similarity between the media asset to be matched and each media asset to be selected, as determined by the first parameter corresponding to the media asset to be matched and the second parameter corresponding to the media asset to be selected. This improves the intelligence of media asset recommendation and enhances the matching degree between the recommended media assets and the user.

[0074] Based on the foregoing embodiments, this application provides a method for determining media assets, referring to... Figure 2 As shown, the method includes the following steps:

[0075] Step 201: The media asset determination device performs deduplication processing on the tags of the media assets to be matched and the tags of each candidate media asset to obtain deduplicated tags.

[0076] In this embodiment, the tags of the media asset to be matched and the tags of each candidate media asset can be analyzed to identify the identical tags among the tags of the media asset to be matched and the tags of each candidate media asset. Then, the identical tags among the tags of the media asset to be matched and the tags of each candidate media asset are deleted to obtain deduplicated tags. It should be noted that since the number of tags of the media asset to be matched and each candidate media asset is not fixed, this will affect the accuracy of the target media asset recommendation. Therefore, it is necessary to determine the total number of tags of the media asset to be matched and each candidate media asset, so as to generate a vector of fixed length with the same number of tags as the total number of tags, thereby improving the accuracy of the target media asset recommendation.

[0077] Step 202: The media asset determination device determines the first parameter based on the deduplication tag and the tag of the media asset to be matched.

[0078] In this embodiment of the application, the deduplication tags and the tags of the media assets to be matched can be analyzed to obtain the first parameter.

[0079] It should be noted that step 202 can be achieved in the following way:

[0080] Step 202a1: The media asset determination device generates a first initial vector corresponding to the tag of the media asset to be matched based on the number of deduplicated tags.

[0081] In this case, all elements in the first initial vector have the same value.

[0082] In this embodiment, the number of elements in the first initial vector is the same as the number of deduplication tags; the number of deduplication tags can refer to the total number of deduplication tags; in one feasible implementation, if the number of deduplication tags is M, each deduplication tag can be represented by tag1, tag2, tag3, ..., tagM, the value of the elements in the first initial vector is 0, and the first initial vector is denoted by x. i Let x be the initial vector. i =(0,0,0,......,0) 1×M , where i represents the i-th media asset to be matched.

[0083] Step 202a2: The media asset determination device uses the target sorting method to sort the deduplicated labels, and obtains the sorted deduplicated labels.

[0084] The target sorting method can refer to the sorting method according to the alphabetical order.

[0085] In one feasible implementation, the first letter of each tag in the deduplication tag can be determined, and the tags can be sorted according to the alphabetical order of their first letter to obtain the sorted deduplication tags.

[0086] Step 202a3: The media asset determination device determines the first order of the tags of the media asset to be matched in the sorted deduplication tags.

[0087] The first sorting order can refer to the order of the tags of the media assets to be matched in the sorted and deduplicated tags.

[0088] In this embodiment of the application, the tags of the media asset to be matched can be matched with each tag in the sorted deduplication tags. If the tag of the media asset to be matched matches a certain tag in the sorted deduplication tags, the arrangement order of that tag in the sorted deduplication tags is determined as the first arrangement order of the tags of the media asset to be matched in the sorted deduplication tags.

[0089] Step 203a4: The media determining device modifies the values ​​of the elements in the first initial vector that correspond to the first arrangement order to obtain the first target vector.

[0090] The first parameter includes the first target vector.

[0091] In this embodiment, the first target vector can be a vector obtained by modifying the values ​​of the elements corresponding to the first permutation order in the first initial vector; in one feasible implementation, the element corresponding to the first permutation order can be the third element, and the value of the third element in the first initial vector is modified to obtain the first target vector x′. i =(0,0,1,......,0) 1×M .

[0092] Step 203: The media asset determination device determines multiple second parameters based on the deduplication label and the label of each candidate media asset.

[0093] In this embodiment of the application, the deduplication tags and the tags of each candidate media asset can be analyzed to obtain multiple second parameters.

[0094] It should be noted that step 203 can be achieved in the following way:

[0095] Step 203b1: The media asset determination device generates a second initial vector corresponding to the tag of each candidate media asset based on the number of deduplicated tags.

[0096] In this case, the values ​​of all elements in the second initial vector are the same, and the values ​​of corresponding elements in the first and second initial vectors are the same.

[0097] In this embodiment, the number of elements in the second initial vector is the same as the number of deduplication tags; in one feasible implementation, if the number of deduplication tags is M, each deduplication tag can be represented by tag1, tag2, tag3, ..., tagM, and the value of each element in the second initial vector is 0. The second initial vector is denoted by y. i Let represent this, then, the second initial vector y i =(0,0,0,......,0) 1×M It should be noted that each candidate media asset will generate a second initial vector corresponding to the label of the candidate media asset.

[0098] Step 203b2: The media asset determination device determines the second order of the label of each candidate media asset in the sorted and deduplicated labels.

[0099] The second sorting order can refer to the order of the tags of each candidate media asset in the sorted and deduplicated tags.

[0100] In this embodiment of the application, for each candidate media asset, the tags of the candidate media asset can be matched with each tag in the sorted deduplication tags. If the tag of the candidate media asset matches a certain tag in the sorted deduplication tags, the arrangement order of that tag in the sorted deduplication tags is determined as the second arrangement order of the tags of the candidate media asset in the sorted deduplication tags.

[0101] Step 203b3: The media determining device modifies the values ​​of the elements in the second initial vector that correspond to the second permutation order to obtain the second target vector.

[0102] The second parameter includes the second target vector.

[0103] In this embodiment, the second target vector can refer to a vector obtained by modifying the values ​​of the elements corresponding to the second permutation order in the second initial vector; in one feasible implementation, the elements corresponding to the second permutation order can be the second element, and the value of the second element in the second initial vector is modified to obtain the second target vector y′. i =(0,1,0,......,0) 1×M .

[0104] Step 204: The media asset determination device analyzes historical behavior information to determine the number of times each candidate media asset's tag has been manipulated.

[0105] In this embodiment of the application, for each candidate media asset, if the historical behavior information refers to any one of playback, favorite, or order, then the number of operations performed on the tag of each candidate media asset refers to the number of playbacks, favorites, or orders; if the historical behavior information refers to at least two of playbacks, favorites, or orders, then the number of operations performed on the tag of each candidate media asset refers to the sum of at least two of the playbacks, favorites, and orders.

[0106] In one feasible implementation, if the historical behavior information is determined to be only playback, the number of playbacks is determined as the number of operations performed on the tags of the candidate media asset; if the historical behavior information is determined to be playback and favorites, the sum of the number of playbacks and favorites is determined as the number of operations performed on the tags of the candidate media asset; if the historical behavior information is determined to be playback, favorites and subscriptions, the sum of the number of playbacks, favorites and subscriptions is determined as the number of operations performed on the tags of the candidate media asset.

[0107] Step 205: The media asset determination device generates a third initial vector of the target object based on the number of operations and the number of deduplicated tags.

[0108] In this embodiment, the number of operations performed on the tags of each candidate media asset is determined as the value of an element corresponding to a bit in the third initial vector, and the number of deduplication tags is determined as the dimension of the third initial vector. Thus, the third initial vector can be composed of multiple elements, and the dimension of the third initial vector is the same as the number of deduplication tags. In one feasible implementation, the target object can refer to the target user, and the third initial vector can be represented by P. l =(P l1 ,P l2 ,P l3 ,......,P lM ) 1×M Let P represent the total number of users, where l∈[1,U], l represents the l-th user, U represents the total number of users, and P represents the total number of users. lM This represents the number of operations performed on the M-th label by the l-th user.

[0109] Step 206: The media determination device normalizes each element in the third initial vector to obtain the third target vector.

[0110] The third parameter includes the third target vector.

[0111] In this embodiment, the third target vector may refer to the vector obtained by normalizing each element of the third initial vector; the third target vector can be obtained by normalizing each element of the third initial vector using a target normalization method; in a feasible implementation, the target normalization method may be the Term Frequency–Inverse Document Frequency (TF-IDF) method.

[0112] It should be noted that step 206 can be achieved in the following way:

[0113] Step 206c1: Determine the target element using the media asset determination equipment.

[0114] The target element is the element corresponding to the tag that is most frequently manipulated among the tags of the media assets to be selected.

[0115] In this embodiment, the number of times each tag of the media asset to be selected is operated on can be compared to determine the element corresponding to the tag that is operated on the most times as the target element; it should be noted that the target element can be D lN Let represent , where l represents the l-th user and N represents the N-th element.

[0116] Step 206c2: The media asset determination device determines the number of first objects and the number of second objects of each candidate media asset's label.

[0117] The second object refers to the object registered in the application corresponding to the media asset to be selected.

[0118] In this embodiment, the first object can refer to an object that operates a tag of a candidate media asset; for each candidate media asset tag, the number of objects operating the tag of the candidate media asset can be counted to obtain the number of first objects operating the tag of the candidate media asset, and the number of objects registered in the application corresponding to the candidate media asset can be counted to obtain the number of second objects; it should be noted that the number of first objects can be expressed as df M The number of the second object can be represented by U; in one feasible implementation, the object can refer to the user.

[0119] Step 206c3: The media asset determination device processes each element based on the target element, the number of the first object, and the number of the second object to obtain the third target vector.

[0120] In this embodiment of the application, mathematical operations can be performed on the target element, the number of the first object, the number of the second object, and each element to obtain the third target vector.

[0121] In one feasible implementation, the third initial vector is P. l =(P l1 ,P l2 ,P l3 ,......,P lM ) 1×M In the case of representing, for the element P in the third initial vector lM Based on the target element, the number of the first object, and the number of the second object, P is evaluated. lM The processed element can be represented by P′ lM Let P′ represent this. lM It can be done through expression (1): The calculation yields the third target vector P′. For each element in the third initial vector, the processed element can be calculated using expression (1). l =(P′) l1 ,P′ l2 ,P′ l3 ,......,P′ lM ) 1×M .

[0122] Step 207: The media asset determination device determines the first value based on the first target vector, the second target vector, and the third target vector.

[0123] Here, the first value can refer to the value obtained after performing operations on the first target vector, the second target vector, and the third target vector.

[0124] In this embodiment of the application, for each second target vector, mathematical operations can be performed on the elements of each corresponding position in the first target vector, each second target vector, and the third target vector to obtain a first value. In this way, by combining user behavior records, a third target vector is added when calculating media asset similarity, so as to realize personalized recommendations of related media assets for each user's any media asset, thereby improving the recommendation effect.

[0125] It should be noted that step 207 can be achieved in the following way:

[0126] Step 207d1: The media determination device performs calculations on the corresponding elements of the first target vector, each second target vector, and the third target vector to obtain multiple third values.

[0127] The third value can refer to the value obtained by performing mathematical operations on the corresponding elements of each second target vector, first target vector, and third target vector.

[0128] In one feasible implementation, the first target vector x′ i=(x′1,x′2,x′3,...,x′ M ), the second target vector y′ i =(y′1,y′2,y′3,...,y′ M ), the third target vector P′ l =(P′) l1 ,P′ l2 ,P′ l3 ,......,P′ lM ) 1×M The third value can be calculated by using the expression Q = x′1·y′1·p′1 on the first element of the first target vector, the second target vector, and the third target vector; it should be noted that i represents the i-th media asset, and M represents the total number of tags.

[0129] Step 207d2: The media asset determination device performs calculations on multiple third values ​​to obtain the first value.

[0130] In this embodiment, multiple third values ​​can be summed to obtain a first value; in one feasible implementation, the first value can be expressed as R = x′1·y′1·p′1 + x′2·y′2·p′2 + ... + x′ M ·y′ M ·p′ M The calculation shows that the first value at this point is the value corresponding to R.

[0131] Step 208: The media asset determination device performs a modulo operation on the first target vector to obtain a first modulo value, and performs a modulo operation on each second target vector to obtain multiple second modulo values.

[0132] The first modulus value is the value obtained by taking the modulus of the first target vector, and the second modulus value is the value obtained by taking the modulus of the second target vector.

[0133] In this embodiment of the application, the first target vector is x′ i =(x′1,x′2,x′3,...,x′ M In the case of ||x′, the first modulus of the first target vector can be expressed as ||x′. i The symbol || can be used to represent this, and it can be expressed in an expression. The first modulus value is calculated; the second target vector is y′. i =(y′1,y′2,y′3,...,y′ M In the case of ||y′||, the second modulus of the second target vector can be expressed as ||y′||. i The symbol || can be used to represent this, and it can be expressed in an expression. The second modulus value is calculated.

[0134] Step 209: The media asset determination device calculates the first modulus value and multiple second modulus values ​​to obtain the second value, and calculates the correlation degree between the first value and the second value.

[0135] The second value is obtained by performing a modulo operation on the first target vector and a modulo operation on the second target vector.

[0136] In this embodiment, the first modulus value can be multiplied by each of the second modulus values ​​to obtain the second value, that is, the first modulus value of the first target vector is represented by ||x′. i || is used to represent the second modulus of the second target vector, and ||y′ is used to represent the second modulus of the second target vector. i When || is used to represent the expression, it can be expressed as G=||x′. i ||·||y′ i || We get the second value.

[0137] In this embodiment, the first value can be divided by each of the second values ​​to obtain the correlation between the media asset to be matched and each candidate media asset. The correlation between the media asset to be matched and each candidate media asset can be represented by sim(x′). i ,y′ i The first value is represented by R = x′1·y′1·p′1 + x′2·y′2·p′2 + ... + x′ M ·y′ M ·p′ M The second value is represented by G=||x′. i ||·||y′ i When expressed as ||, the degree of association can be expressed by an expression. Calculated.

[0138] Step 210: The media asset determination device sorts multiple candidate media assets based on their relevance to obtain the sorted candidate media assets.

[0139] In this embodiment of the application, multiple candidate media assets are sorted according to their relevance to obtain candidate media assets arranged from largest to smallest relevance, or candidate media assets arranged from smallest to largest relevance.

[0140] Step 211: The media asset determination device determines the target media asset from the sorted candidate media assets.

[0141] In this embodiment of the application, N media assets with high relevance can be identified from the sorted media assets and designated as target media assets. These target media assets can then be recommended to the user, thereby achieving the effect of personalized media asset recommendations for the user's requested media assets. It should be noted that N represents the number of media assets with high relevance to the media assets.

[0142] In other embodiments of this application, reference is made to Figure 3 As shown, when the number of candidate media assets in the media asset library is large, it can lead to significant pressure in real-time calculation of the similarity between the media asset to be matched and each candidate media asset. In such cases, similarity calculation can be used. Calculate the similarity between the media asset to be matched and each candidate media asset, where x i This refers to the first target vector corresponding to the tag of the media asset to be matched, y i This refers to the second target vector corresponding to the tag of each candidate media asset. N candidate media assets with high similarity to the media asset to be matched are selected as the recommended media asset candidate set. Then, user historical behavior information (i.e., playback, favorites, subscriptions) needs to be obtained to acquire user preference tags, and a third target vector p representing user preferences is generated based on the number of actions associated with those tags. i In this way, when a user requests recommendations for related media assets to be matched, the system can obtain the user's identifier and the identifier of the media asset to be matched, and then use the similarity calculation formula. The first target vector, the second target vector, and the third target vector are calculated to obtain the similarity between the media asset to be matched and each candidate media asset in the recommended media asset candidate set. Based on the similarity, the candidate media assets in the recommended media asset candidate set are sorted, and the N candidate media assets with the higher similarity are selected to generate a personalized recommendation list to recommend to the user, thereby providing the user with personalized related media asset recommendations for the media asset to be matched.

[0143] The media asset determination method provided in this application takes into account the target object's historical behavior information regarding the media asset to be matched, and recommends target media assets based on the first parameter corresponding to the media asset to be matched, the second parameter corresponding to the media asset to be selected, and the third parameter of the tag corresponding to the historical behavior information, which together determine the similarity between the media asset to be matched and each media asset to be selected. This method does not simply recommend media assets based on the similarity between the media asset to be matched and each media asset to be selected, as determined by the first parameter corresponding to the media asset to be matched and the second parameter corresponding to the media asset to be selected. This improves the intelligence of media asset recommendation and enhances the matching degree between the recommended media assets and the user.

[0144] Based on the foregoing embodiments, embodiments of this application provide a media asset determination device, which can be applied to... Figure 1 and 2 In the corresponding embodiment of the media asset determination method, refer to Figure 4 As shown, the device 3 may include: a first processing unit 31, a second processing unit 32, a third processing unit 33, and a determining unit 34, wherein:

[0145] The first processing unit 31 is used to determine a first parameter corresponding to the media asset to be matched and a second parameter corresponding to each media asset to be selected based on the tags of the media asset to be matched and the tags of each media asset to be selected; wherein, the first parameter represents the tag situation of the media asset to be matched; and the second parameter represents the tag situation of the media asset to be selected.

[0146] The second processing unit 32 is used to obtain historical behavior information of the target object for the media asset to be matched, and to determine the third parameter of the tag corresponding to the historical behavior information based on the historical behavior information; wherein, the third parameter represents the target object's preference;

[0147] The third processing unit 33 is used to determine the correlation between the media asset to be matched and each candidate media asset based on the first parameter, the second parameter and the third parameter;

[0148] The determination unit 34 is used to determine the target media asset corresponding to the target object from multiple candidate media assets based on the relevance.

[0149] In this embodiment of the application, the first processing unit 31 is further configured to perform the following steps:

[0150] The tags of the media assets to be matched and the tags of each candidate media asset are deduplicated to obtain deduplicated tags;

[0151] The first parameter is determined based on the deduplication tag and the tag of the media asset to be matched;

[0152] Based on the deduplication tags and the tags of each candidate media asset, multiple second parameters are determined.

[0153] In this embodiment of the application, the first processing unit 31 is further configured to perform the following steps:

[0154] Based on the number of duplicate tags, a first initial vector is generated corresponding to the tags of the media assets to be matched; wherein, the values ​​of all elements in the first initial vector are the same;

[0155] The deduplication tags are sorted using a target sorting method to obtain the sorted deduplication tags;

[0156] Determine the first order of the tags of the media asset to be matched in the sorted and deduplicated tags;

[0157] The values ​​of the elements corresponding to the first permutation order in the first initial vector are modified to obtain the first target vector; wherein, the first parameter includes the first target vector;

[0158] In this embodiment of the application, the first processing unit 31 is further configured to perform the following steps:

[0159] Based on the number of deduplicated tags, a second initial vector is generated corresponding to the tag of each candidate media asset; wherein, the values ​​of the elements in the second initial vector are all the same, and the values ​​of the corresponding elements in the first initial vector and the second initial vector are the same;

[0160] Determine the second order of the tags for each candidate media asset in the sorted, deduplicated tags;

[0161] The values ​​of the elements corresponding to the second permutation order in the second initial vector are modified to obtain the second target vector; wherein, the second parameter includes the second target vector.

[0162] In this embodiment of the application, the second processing unit 32 is further configured to perform the following steps:

[0163] Analyze historical behavior information to determine the number of times each candidate media asset's tag has been manipulated;

[0164] Based on the number of operations and the number of deduplicated tags, a third initial vector for the target object is generated.

[0165] Normalize each element in the third initial vector to obtain the third target vector; where the third parameter includes the third target vector.

[0166] In this embodiment of the application, the second processing unit 32 is further configured to perform the following steps:

[0167] Identify the target element; where the target element is the element corresponding to the tag that is operated on most frequently among the tags of the media assets to be selected;

[0168] Determine the number of first objects and second objects for each candidate media asset's tag; wherein, the second object refers to the object registered in the application corresponding to the candidate media asset;

[0169] Each element is processed based on the target element, the number of the first object, and the number of the second object to obtain the third target vector.

[0170] In this embodiment of the application, the third processing unit 33 is further configured to perform the following steps:

[0171] Based on the first target vector, the second target vector, and the third target vector, determine the first numerical value;

[0172] The first target vector is moduloed to obtain the first modulo value, and the second target vector is moduloed to obtain multiple second modulo values.

[0173] The second value is obtained by performing calculations on the first modulus and multiple second modulus values, and the correlation degree is obtained by performing calculations on the first value and the second value.

[0174] In this embodiment of the application, the third processing unit 33 is further configured to perform the following steps:

[0175] Perform operations on the corresponding elements of the first target vector, each second target vector, and the third target vector to obtain multiple third values;

[0176] The first value is obtained by performing calculations on multiple third values.

[0177] In this embodiment of the application, the determining unit 34 is further configured to perform the following steps:

[0178] Multiple candidate media assets are sorted based on their relevance to obtain the sorted candidate media assets;

[0179] Select target media assets from the sorted candidate media assets.

[0180] It should be noted that the specific implementation process of the steps performed by each unit in this embodiment can be referred to Figure 1 and 2 The implementation process of the media asset determination method provided in the corresponding embodiment will not be described in detail here.

[0181] The media asset determination device provided in this application takes into account the historical behavior information of the target object towards the media asset to be matched, and jointly determines the similarity between the media asset to be matched and each candidate media asset based on the first parameter corresponding to the media asset to be matched, the second parameter corresponding to the candidate media asset, and the third parameter of the tag corresponding to the historical behavior information, so as to recommend the target media asset. Instead of simply recommending media assets based on the similarity between the media asset to be matched and each candidate media asset determined by the first parameter corresponding to the media asset to be matched and the second parameter corresponding to the candidate media asset, the device improves the intelligence of media asset recommendation and enhances the matching degree between the recommended media assets and the user.

[0182] Based on the foregoing embodiments, embodiments of this application provide a media asset determination device, which can be applied to... Figure 1 and 2 The corresponding embodiment provides a method for determining media assets, referring to... Figure 5 As shown, the device 4 may include a processor 41, a memory 42, and a communication bus 43;

[0183] Communication bus 43 is used to realize the communication connection between processor 41 and memory 42;

[0184] The processor 41 is used to execute the media asset determination program stored in the memory 42 to perform the following steps:

[0185] Based on the tags of the media assets to be matched and the tags of each candidate media asset, a first parameter corresponding to the media asset to be matched and a second parameter corresponding to each candidate media asset are determined; wherein, the first parameter represents the tag situation of the media asset to be matched; and the second parameter represents the tag situation of the candidate media asset.

[0186] The system obtains historical behavior information of the target object towards the media asset to be matched, and determines the third parameter of the tag corresponding to the historical behavior information based on the historical behavior information; wherein, the third parameter represents the target object's preference.

[0187] Based on the first, second, and third parameters, the correlation between the media asset to be matched and each candidate media asset is determined;

[0188] Based on relevance, the target media asset corresponding to the target object is determined from multiple candidate media assets.

[0189] In other embodiments of this application, the processor 41 is configured to execute a media asset determination program in the memory 42, based on the tags of the media assets to be matched and the tags of each candidate media asset, to determine a first parameter corresponding to the media asset to be matched and a second parameter corresponding to each candidate media asset, in order to implement the following steps:

[0190] The tags of the media assets to be matched and the tags of each candidate media asset are deduplicated to obtain deduplicated tags;

[0191] The first parameter is determined based on the deduplication tag and the tag of the media asset to be matched;

[0192] Based on the deduplication tags and the tags of each candidate media asset, multiple second parameters are determined.

[0193] In other embodiments of this application, processor 41 is used to execute a media asset determination program in memory 42 to determine a first parameter based on deduplication tags and tags of the media asset to be matched, in order to implement the following steps:

[0194] Based on the number of duplicate tags, a first initial vector is generated corresponding to the tags of the media assets to be matched; wherein, the values ​​of all elements in the first initial vector are the same;

[0195] The deduplication tags are sorted using a target sorting method to obtain the sorted deduplication tags;

[0196] Determine the first order of the tags of the media asset to be matched in the sorted and deduplicated tags;

[0197] The values ​​of the elements corresponding to the first permutation order in the first initial vector are modified to obtain the first target vector; wherein, the first parameter includes the first target vector;

[0198] In other embodiments of this application, processor 41 is configured to execute a media asset determination program in memory 42 to determine a plurality of second parameters based on deduplication tags and tags of each candidate media asset, in order to perform the following steps:

[0199] Based on the number of deduplicated tags, a second initial vector is generated corresponding to the tag of each candidate media asset; wherein, the values ​​of the elements in the second initial vector are all the same, and the values ​​of the corresponding elements in the first initial vector and the second initial vector are the same;

[0200] Determine the second order of the tags for each candidate media asset in the sorted, deduplicated tags;

[0201] The values ​​of the elements corresponding to the second permutation order in the second initial vector are modified to obtain the second target vector; wherein, the second parameter includes the second target vector.

[0202] In other embodiments of this application, the processor 41 is used to execute the media asset determination program in the memory 42 to determine the third parameter of the tag corresponding to the historical behavior information based on the historical behavior information, in order to implement the following steps:

[0203] Analyze historical behavior information to determine the number of times each candidate media asset's tag has been manipulated;

[0204] Based on the number of operations and the number of deduplicated tags, a third initial vector for the target object is generated.

[0205] Normalize each element in the third initial vector to obtain the third target vector; where the third parameter includes the third target vector.

[0206] In other embodiments of this application, the processor 41 is configured to execute the media asset determination program in the memory 42 to normalize each element in the third initial vector to obtain the third target vector, thereby implementing the following steps:

[0207] Identify the target element; where the target element is the element corresponding to the tag that is operated on most frequently among the tags of the media assets to be selected;

[0208] Determine the number of first objects and second objects for each candidate media asset's tag; wherein, the second object refers to the object registered in the application corresponding to the candidate media asset;

[0209] Each element is processed based on the target element, the number of the first object, and the number of the second object to obtain the third target vector.

[0210] In other embodiments of this application, the processor 41 is configured to execute a media asset determination program in the memory 42 based on a first parameter, a second parameter, and a third parameter to determine the correlation between the media asset to be matched and each candidate media asset, in order to implement the following steps:

[0211] Based on the first target vector, the second target vector, and the third target vector, determine the first numerical value;

[0212] The first target vector is moduloed to obtain the first modulo value, and the second target vector is moduloed to obtain multiple second modulo values.

[0213] The second value is obtained by performing calculations on the first modulus and multiple second modulus values, and the correlation degree is obtained by performing calculations on the first value and the second value.

[0214] In other embodiments of this application, processor 41 is used to execute a media asset determination program in memory 42 to determine a first value based on a first target vector, a second target vector, and a third target vector, in order to implement the following steps:

[0215] Perform operations on the corresponding elements of the first target vector, each second target vector, and the third target vector to obtain multiple third values;

[0216] The first value is obtained by performing calculations on multiple third values.

[0217] In other embodiments of this application, processor 41 is used to execute a media asset determination program in memory 42 based on correlation degree to determine the target media asset corresponding to the target object from a plurality of candidate media assets, in order to implement the following steps:

[0218] Multiple candidate media assets are sorted based on their relevance to obtain the sorted candidate media assets;

[0219] Select target media assets from the sorted candidate media assets.

[0220] It should be noted that the specific implementation process of the steps executed by the processor in this embodiment can be referred to Figure 1 and 2 The implementation process of the media asset determination method provided in the corresponding embodiment will not be described in detail here.

[0221] The media asset determination device provided in this application takes into account the historical behavior information of the target object towards the media asset to be matched, and recommends target media assets based on the first parameter corresponding to the media asset to be matched, the second parameter corresponding to the media asset to be selected, and the third parameter of the tag corresponding to the historical behavior information, which jointly determine the similarity between the media asset to be matched and each media asset to be selected. Instead of simply recommending media assets based on the similarity between the media asset to be matched and each media asset to be selected, which is determined by the first parameter corresponding to the media asset to be matched and the second parameter corresponding to the media asset to be selected, the device improves the intelligence of media asset recommendation and enhances the matching degree between the recommended media assets and the user.

[0222] Based on the foregoing embodiments, this application provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors to achieve... Figure 1 and 2 The steps in the media asset determination method provided in the corresponding embodiment.

[0223] It should be noted that the aforementioned computer-readable storage media can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM), etc.; or it can be various electronic devices that include one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0224] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0225] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0226] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0227] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0228] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0229] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0230] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for determining media assets, characterized in that, The method includes: Based on the tags of the media asset to be matched and the tags of each candidate media asset, a first parameter corresponding to the media asset to be matched and a second parameter corresponding to each candidate media asset are determined; wherein, the first parameter represents the tag situation of the media asset to be matched; and the second parameter represents the tag situation of the candidate media asset. The system obtains historical behavior information of the target object regarding the media asset to be matched, and determines a third parameter of the tag corresponding to the historical behavior information based on the historical behavior information; wherein the third parameter represents the target object's preference. Based on the first parameter, the second parameter, and the third parameter, the correlation degree between the media asset to be matched and each candidate media asset is determined; Based on the correlation, the target media asset corresponding to the target object is determined from a plurality of candidate media assets; The step of determining the first parameter corresponding to the media asset to be matched and the second parameter corresponding to each media asset to be selected based on the tags of the media asset to be matched and the tags of each media asset to be selected includes: The tags of the media assets to be matched and the tags of each media asset to be selected are deduplicated to obtain deduplicated tags; The first parameter is determined based on the deduplication tag and the tag of the media asset to be matched; Based on the deduplication tag and the tag of each candidate media asset, a plurality of the second parameters are determined; The step of determining the third parameter of the tag corresponding to the historical behavior information based on the historical behavior information includes: The historical behavior information is analyzed to determine the number of times each candidate media asset's tag has been manipulated; Based on the number of operations and the number of deduplication tags, a third initial vector for the target object is generated; Each element in the third initial vector is normalized to obtain the third target vector; wherein the third parameter includes the third target vector.

2. The method according to claim 1, characterized in that, Determining the first parameter based on the deduplication tag and the tag of the media asset to be matched includes: Based on the number of deduplicated tags, a first initial vector corresponding to the tags of the media asset to be matched is generated; wherein, the values ​​of all elements in the first initial vector are the same; The deduplicated tags are sorted using a target sorting method to obtain sorted deduplicated tags; Determine the first order of the tags of the media asset to be matched in the sorted and deduplicated tags; The values ​​of the elements in the first initial vector corresponding to the first arrangement order are modified to obtain the first target vector; wherein, the first parameter includes the first target vector; Accordingly, the determination of multiple second parameters based on the deduplication tag and the tag of each candidate media asset includes: Based on the number of deduplication tags, a second initial vector is generated corresponding to the tag of each candidate media asset; wherein, the values ​​of the elements in the second initial vector are all the same, and the values ​​of the corresponding elements in the first initial vector and the second initial vector are the same; Determine the second arrangement order of the tags for each candidate media asset in the sorted and deduplicated tags; The values ​​of the elements in the second initial vector corresponding to the second arrangement order are modified to obtain the second target vector; wherein, the second parameter includes the second target vector.

3. The method according to claim 2, characterized in that, The step of normalizing each element in the third initial vector to obtain the third target vector includes: determining the target element; wherein the target element is the element corresponding to the most frequently operated tag among the tags of the candidate media assets; Determine the number of first objects and the number of second objects that operate on the tag of each candidate media asset; wherein, the second object refers to an object registered in the application corresponding to the candidate media asset; The third target vector is obtained by processing each element based on the target element, the number of the first object, and the number of the second object.

4. The method according to claim 1, characterized in that, The step of determining the correlation between the media asset to be matched and each candidate media asset based on the first parameter, the second parameter, and the third parameter includes: Based on the first target vector, the second target vector, and the third target vector, determine the first numerical value; The first target vector is moduloed to obtain a first modulo value, and each second target vector is moduloed to obtain multiple second modulo values; The first modulus value and the plurality of second modulus values ​​are used to calculate the second value, and the first value and the second value are used to calculate the correlation degree.

5. The method according to claim 4, characterized in that, Determining the first numerical value based on the first target vector, the second target vector, and the third target vector includes: Calculate the corresponding elements in the first target vector, each of the second target vectors, and the third target vector to obtain multiple third values; The first value is obtained by performing calculations on the plurality of third values.

6. The method according to claim 1, characterized in that, The step of determining the target media asset corresponding to the target object from a plurality of candidate media assets based on the correlation degree includes: The candidate media assets are sorted based on the correlation to obtain the sorted candidate media assets; The target media asset is determined from the sorted candidate media assets.

7. A media asset determining device, characterized in that, The device includes: The first processing unit is configured to determine a first parameter corresponding to the media asset to be matched and a second parameter corresponding to each media asset to be selected, based on the tags of the media asset to be matched and the tags of each media asset to be selected; wherein, the first parameter represents the tag information of the media asset to be matched; and the second parameter represents the tag information of the media asset to be selected. The second processing unit is used to acquire historical behavior information of the target object towards the media asset to be matched, and to determine a third parameter of the tag corresponding to the historical behavior information based on the historical behavior information; wherein the third parameter represents the preference of the target object; The third processing unit is used to determine the correlation between the media asset to be matched and each candidate media asset based on the first parameter, the second parameter and the third parameter; The determining unit is configured to determine the target media asset corresponding to the target object from a plurality of candidate media assets based on the correlation degree; The first processing unit is further configured to perform deduplication processing on the tags of the media asset to be matched and the tags of each candidate media asset to obtain deduplicated tags; determine the first parameter based on the deduplicated tags and the tags of the media asset to be matched; and determine a plurality of second parameters based on the deduplicated tags and the tags of each candidate media asset. The second processing unit is further configured to analyze the historical behavior information to determine the number of times each candidate media asset's tag has been operated on; based on the number of operations and the number of deduplicated tags, generate a third initial vector for the target object; normalize each element in the third initial vector to obtain a third target vector; wherein the third parameter includes the third target vector.

8. A media asset determination device, characterized in that, The device includes: a processor, a memory, and a communication bus; The communication bus is used to realize the communication connection between the processor and the memory; The processor is used to execute the media asset determination program stored in the memory to implement the steps of the media asset determination method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The storage medium stores one or more programs, which can be executed by one or more processors to implement the steps of the media asset determination method as described in any one of claims 1 to 6.

Images