Media object evaluation method and device, computer program product and electronic equipment

Abstract

The embodiment of the invention relates to the technical field of computers, in particular to a media object evaluation method and device, a computer program product and electronic equipment. The method comprises the following steps: obtaining a target user according to historical behavior data of a user group, pushing a target media object to the target user, and obtaining a score of the target user on the target media object; and determining a preference coefficient of the target user, determining a score weight of the target user for the target media object based on the preference coefficient, and adjusting the score through the score weight to obtain a target score of the target media object. The method improves the scoring accuracy of the target media object.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and more specifically, to a method and apparatus for evaluating a media object, a computer program product, and an electronic device. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the disclosure that are recited in the claims, and no statement herein is admitted to be prior art by inclusion in this section.

[0003] In the digital music era, the promotion and evaluation mechanisms for new songs after they are released are receiving increasing attention. To ensure that new songs receive fair evaluation and quality assessments, and that high-quality songs can succeed in the market, new songs will first be reviewed by specific groups after they are released. Related technologies include expert review mechanisms and audio parameter standardization review mechanisms. The expert review mechanism involves building a professional review team, which manually scores songs based on dimensions such as arrangement complexity and singing skills, or having a music editing team screen the songs and give them scores based on the opinions of professional listeners. Audio parameter standardization refers to the use of LUFS (Loudness Unit Full Scale) standardization for newly released songs to avoid volume jumps, and using FFT (Fast Fourier Transform) to detect high-frequency loss rates and verify the frequency domain integrity of sound quality of 320kpbs and above. Summary of the Invention

[0004] In related technologies, scoring is performed through an expert review mechanism. However, due to the small size of the expert review panel, it is easily influenced by individual aesthetic preferences. In the audio parameter standardization review mechanism, LUFS standardization leads to dynamic range compression, resulting in a 38% loss of dynamic contrast in live classical music recordings, and FFT detection is unable to detect artistically processed high-frequency attenuation.

[0005] To this end, there is a great need for an improved media object evaluation method and device, computer program product, and electronic device to provide a media object evaluation method that can perform multi-dimensional evaluation of media objects, reduce evaluation subjectivity, and improve evaluation accuracy, so as to solve the problem of a large influence of subjectivity in media object evaluation in related technologies.

[0006] In this context, embodiments of the present disclosure are intended to provide a media object evaluation method and apparatus, a computer program product, and an electronic device.

[0007] According to one aspect of the present disclosure, a media object evaluation method is provided, comprising:

[0008] Determine target users based on historical behavior data of user groups, push target media objects to the target users, and obtain ratings of the target media objects by the target users;

[0009] Determine the preference coefficient of the target user, determine the target user's scoring weight for the target media object based on the preference coefficient, adjust the score according to the scoring weight, and obtain a target score for the target media object.

[0010] According to one aspect of the present disclosure, there is provided a media object evaluation device, comprising:

[0011] A media object scoring module is used to obtain a target user based on the historical behavior data of the user group, push a target media object to the target user, and obtain the target user's score for the target media object;

[0012] The target score acquisition module is used to determine the preference coefficient of the target user, determine the score weight of the target user for the target media object based on the preference coefficient, and adjust the score according to the score weight to obtain the target score of the target media object.

[0013] According to one aspect of the present disclosure, a computer storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned media object evaluation method is implemented.

[0014] According to one aspect of the present disclosure, there is provided an electronic device, including:

[0015] A processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any one of the above-mentioned media object evaluation methods by executing the executable instructions.

[0016] According to the media object evaluation method of the disclosed embodiment, on the one hand, historical behavior data of a user group is obtained, and target users are obtained by screening based on the historical behavior data. The target users are then used to score the target media object, reflecting the public's preference for the media object and enhancing the representativeness of the score. On the other hand, after obtaining the target user's score for the target media object, the target user's score weight for the target media object is determined based on the target user's preference coefficient. The score is adjusted using the score weight to obtain the target score for the target media object. The preference coefficient reduces the influence of subjective factors on the scoring results, thereby improving the professionalism and accuracy of the scoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become readily understood by reading the detailed description below with reference to the accompanying drawings, in which several embodiments of the present disclosure are shown by way of example and not limitation, wherein:

[0018] Figure 1 The following schematically shows a flow chart of a media object evaluation method according to an embodiment of the present disclosure;

[0019] Figure 2 The following schematically shows a flow chart of a method for obtaining target users based on historical behavior data of a user group according to an embodiment of the present disclosure;

[0020] Figure 3 A flowchart of a method for screening users based on the appreciation score of each user to obtain the target user according to an embodiment of the present disclosure is schematically shown;

[0021] Figure 4 A flowchart schematically illustrates a method for determining a preference coefficient of a target user and determining a scoring weight of the target user for the target media object based on the preference coefficient according to an embodiment of the present disclosure;

[0022] Figure 5 A flowchart schematically illustrates a method for determining a scoring weight for the target media object based on the preference coefficient according to an embodiment of the present disclosure;

[0023] Figure 6 A flowchart of a media object scoring method after obtaining a target score of the target media object according to an embodiment of the present disclosure is schematically shown;

[0024] Figure 7 Schematically shows a block diagram of a media object evaluation device according to an embodiment of the present disclosure;

[0025] Figure 8 A schematic diagram of a computer storage medium according to an embodiment of the present disclosure is shown;

[0026] Figure 9 A block diagram of an electronic device according to a disclosed embodiment is schematically shown.

[0027] In the drawings, the same or corresponding reference numerals denote the same or corresponding parts. DETAILED DESCRIPTION

[0028] The principles and spirit of the present disclosure will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided solely to enable those skilled in the art to better understand and implement the present disclosure, and are not intended to limit the scope of the present disclosure in any way. Rather, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0029] Those skilled in the art will appreciate that the embodiments of the present disclosure may be implemented as a system, apparatus, device, method, or computer program product. Therefore, the present disclosure may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software.

[0030] According to an embodiment of the present disclosure, a data communication method, a data communication apparatus, a computer program product, and an electronic device are provided.

[0031] In this article, the terms involved are explained as follows when necessary to understand:

[0032] Appreciation: The ability of an individual to understand, analyze and evaluate the elements of a media object during the process of appreciating the media object. Users with high appreciation can not only identify the basic elements of a media object, but also perceive the emotions, cultural background and artistic value of the media object.

[0033] In this document, any number of elements in the drawings is for illustration and not for limitation, and any naming is for distinction only and does not have any limiting meaning.

[0034] The principles and spirit of the present disclosure are described in detail below with reference to several representative embodiments of the present disclosure. SUMMARY OF THE INVENTION

[0036] The inventors have found that in the era of digital music, the promotion and evaluation mechanism of new songs after they are launched are receiving more and more attention. In order to ensure that new songs can receive fair evaluation and quality assessment, and that high-quality songs can be successful in the market, new songs will first be reviewed by specific groups after they are launched. In the relevant technologies, there are expert review mechanisms and audio parameter standardization review mechanisms. The expert review mechanism is to build a professional review team, which will manually score the song's arrangement complexity, singing skills and other dimensions, or the music editing team will screen the songs and give scores based on the opinions of professionals. Audio parameter standardization refers to the use of LUFS (Loudness Unit Full Scale) standardization for newly launched songs to avoid volume jumps, and the use of FFT (Fast Fourier Transform) to detect high-frequency loss rate and verify the frequency domain integrity of sound quality of 320kpbs and above.

[0037] However, scoring through an expert review mechanism is susceptible to individual aesthetic preferences due to the small size of the expert jury. In the audio parameter standardization review mechanism, LUFS standardization leads to dynamic range compression, resulting in a 38% loss of dynamic contrast in live classical music recordings, and FFT detection is unable to identify artistically processed high-frequency attenuation.

[0038] In view of the above content, the basic idea of ​​the present disclosure is: to screen users in a user group according to the historical behavior data of the user group, to obtain the target user, to push the target media object to the target user, and to have the target user score the target media object to obtain the target user's score for the target media object; after obtaining the score, it is also necessary to obtain the target user's preference coefficient, and to adjust the user's score for the target media object according to the user's preference coefficient to obtain the target score for the target media object.

[0039] After introducing the basic principles of the present disclosure, various non-limiting embodiments of the present disclosure are described in detail below.

[0040] Exemplary Methods

[0041] The following combination Figure 1 A media object evaluation method according to an exemplary embodiment of the present disclosure is described below.

[0042] refer to Figure 1 As shown, the media object evaluation method may include the following steps:

[0043] Step S110. Obtain a target user based on the historical behavior data of the user group, push a target media object to the target user, and obtain the target user's rating of the target media object;

[0044] Step S120: Determine the preference coefficient of the target user, determine the target user's scoring weight for the target media object based on the preference coefficient, adjust the score according to the scoring weight, and obtain a target score for the target media object.

[0045] In the media object evaluation method of the disclosed embodiment, on the one hand, historical behavior data of a user group is obtained, and target users are identified based on this historical behavior data. The target users are then used to score the target media object, reflecting the public's preferences for the media object and enhancing the representativeness of the score. On the other hand, after obtaining the target user's score for the target media object, the target user's score weight for the target media object is determined based on the target user's preference coefficient. The score is then adjusted using the score weight to obtain a target score for the target media object. The preference coefficient reduces the influence of subjective factors on the scoring results, improving the professionalism and accuracy of the scoring.

[0046] The following further explains and illustrates the media object evaluation method.

[0047] In step S110 , a target user is obtained based on historical behavior data of a user group, a target media object is pushed to the target user, and a rating of the target media object by the target user is obtained.

[0048] The target media object can be launched on any platform, and the user group is the users of the platform. The target media object can be music, movies, etc., and there is no specific limitation on the target media object in this example embodiment. The target media object can be a newly launched media object. The historical behavior data of the user group can be the user's playback behavior data, sharing behavior data, and collection behavior data of the media object on the platform. After obtaining the historical behavior data of the user group, the users in the user group are screened according to the historical behavior data to obtain the target users. After the media object is launched, the target media object is pushed to the target user, and the target user scores the target media object based on his or her appreciation to obtain a score for the target media object.

[0049] In an exemplary embodiment, referring to Figure 2 As shown, the method of obtaining target users based on historical behavior data of user groups includes:

[0050] Step S210: Obtain historical behavior data of the user group on the media object, input the historical behavior data into the appreciation model, and obtain the appreciation score of each user in the user group;

[0051] Step S220: Screen users based on the appreciation score of each user to obtain the target user.

[0052] Below, step S210 and step S220 will be further explained and illustrated. Specifically, the historical behavior data of the user group on the media object is obtained, and the historical behavior data is input into the appreciation model to obtain the appreciation score of each user in the user group. The target user is obtained by screening based on the appreciation score of each user. Among them, the appreciation model can be a deep neural network model, in which multi-source behavior data such as playback time, collection frequency, number of shares, and item filtering are integrated, and high-order feature cross-linking is achieved through a fully connected layer to capture the user's preference for the media object. The appreciation model can also be a hybrid model of a gradient boosting tree and a neural network. Specifically, a gradient boosting tree (such as XGBoost) is first used to screen important features (such as sharing behavior has a higher weight than playing), and nonlinear fitting is performed on the input neural network to improve the interpretability of the model. The appreciation model can also be a statistical model, and the user's historical behavior data is input into the statistical model. Based on preset analysis rules, the user's historical behavior data is analyzed to obtain the appreciation score of each user. In this example embodiment, the appreciation model is not specifically limited. This appreciation model not only relies on the user's identity, but also combines the user's behavioral data. It can comprehensively evaluate the user's appreciation and improve the evaluation accuracy of the user's appreciation level.

[0053] In an exemplary embodiment, the historical behavior data of the user group on the media object includes the playback history data of each user on the media object, the portrait of each user and the interactive behavior data of each user; wherein, the playback history data includes at least one of the following: the number and frequency of playbacks, skip rate, number of repeated playbacks, style type, language type and coverage area of ​​the media object played, and artist coverage within a preset time period; the portrait includes comment content and user identity; the interactive behavior data includes at least one of the following: sharing behavior data, collection behavior data and network ecological value data.

[0054] Specifically, the user group's historical behavior data for media objects includes each user's playback history data, which includes at least one of the following: the number of media object plays, playback frequency, skip rate, number of repeated plays, genre type of the media object played, language type of the media object played, geographic coverage of the media object played, and artist coverage for each user within a preset time period. For music, the genre type can be lyrical or rock, and the language type can be Chinese, English, Korean, or other languages. In this example embodiment, the genre type and language type are not specifically limited. The artist can be an object associated with the media object. The historical behavior data can also include a user profile, which includes the user's identity and the user's comments. The user's identity can be a creator, a member of the public, a musician, a key opinion leader, or other individuals. In this example embodiment, the user's identity is not specifically limited. The comments can be the user's comments on the media object. A key opinion leader is a media object that is frequently collected and viewed by other users after the user creates a media object list on the platform. Historical behavior data can also include interactive behavior data. The user's interactive behavior data can be at least one of the user's sharing behavior data, collection behavior data, and network ecological mechanism data. The sharing behavior data can include: sharing timeliness, dissemination level, and user fission effect; the collection behavior data can include collection timeliness and playback growth trend; the network ecological value data is to measure the user's value in the digital ecology based on the user's interactive behavior data. The user's interactive behavior can be input into the value evaluation model, and the value evaluation model can be used to output the user's content creation type, fan growth quality, and network expansion scale. The content creation type, fan growth quality, and network expansion scale are used as the user's ecological value data.

[0055] In an exemplary embodiment, referring to Figure 3 As shown, the user screening is performed based on the appreciation score of each user to obtain the target user, including:

[0056] Step S310: Obtain the activity level of each user and the preset appreciation score range corresponding to the activity level group;

[0057] Step S320: Determine a first activity group corresponding to the activity of each user and a first appreciation score range corresponding to the first activity group. When the appreciation score is within the first appreciation score range, determine the user as a target user.

[0058] In the following, step S310 and step S320 will be further explained and illustrated. Specifically, the activity of each user in the platform is obtained, wherein the activity of the user in the platform can be determined by the user's interactive behavior and deep participation behavior. The deep participation behavior can be that the length of time for playing the media object reaches a preset length, or it can be that the number of times participating in the discussion is greater than a preset number. In this example embodiment, there is no specific limitation on the deep participation behavior. After obtaining the user's activity, the preset appreciation score range corresponding to the activity group can also be obtained. According to the user's activity, the first activity group corresponding to it is determined in the preset activity group, and whether the user is a target user is determined according to the first appreciation score range corresponding to the first activity group. When the user's appreciation score is within the first appreciation score range, the user is determined to be a target user.

[0059] The higher the user's activity level, the lower the lower limit of the appreciation score range corresponding to the activity group in which the activity level is located. The appreciation score ranges corresponding to different activity groups may overlap, which is not specifically limited in this example embodiment. For example, when the user's activity level is (0.1, 0.3], the appreciation score range may be [0.6, 0.9]; when the user's user level is (0.4, 0.6], the appreciation score range may be [0.3, 0.8]; and when the user's activity level is (0.7, 0.9], the appreciation score range may be [0.2, 0.5].

[0060] In an exemplary embodiment, after a target media object is pushed to a target user, the target user may rate the target media object. When rating, the target user may select a rating from a preset rating range as the rating for the target media object. The preset rating range may be 1-10 points or 1-5 stars, and this preset rating range is not specifically limited in this exemplary embodiment.

[0061] In step S120, the preference coefficient of the target user is determined, and the scoring weight of the target user for the target media object is determined based on the preference coefficient. The score is adjusted according to the scoring weight to obtain a target score for the target media object.

[0062] When the target media object is music, the user's preference coefficient is the user's preference for each genre and language. This coefficient can be calculated based on the number of times the user has favorited that genre or language. Rating weighting is designed to dynamically adjust the weight of the rating based on the user's appreciation for specific genres and languages. By identifying the preferences and appreciation of different target users for different types of music, we can more accurately reflect the user's actual ratings.

[0063] In an exemplary embodiment, after obtaining the target user's rating of the target media object, the method further includes:

[0064] The scores are verified to remove invalid scores from the scores.

[0065] Specifically, after obtaining the target user's rating of the target media object, invalid ratings can be removed from the ratings. Invalid ratings can also be caused by interface manipulation or by the number of target media objects being different from the number of ratings received by the user. For example, if the number of target media objects is 3, only one rating from the target user is received. While a user is rating a target media object, the target user's requests can be monitored. If the target user initiates multiple consecutive interface requests of the same type within a preset time period, the target user's rating can be deemed invalid.

[0066] In an exemplary embodiment, referring to Figure 4 As shown, determining the preference coefficient of the target user and determining the scoring weight of the target user for the target media object based on the preference coefficient includes:

[0067] Step S410. Obtain the number of times the target user has collected and played a first type of media object, and obtain a preference coefficient of the target user based on the number of times collected and played.

[0068] Step S420: Determine a scoring weight for the target media object based on the preference coefficient.

[0069] The following will further explain and illustrate step S410 and step S420. Specifically, the number of times the target object collects and plays the first type of media object is obtained, and the target user's preference coefficient is obtained based on the number of collections and plays. The first type can be the style type of the media object or the language type of the media object. If the number of collections is k and the number of plays is n, then the target user's preference coefficient is After obtaining the user's preference coefficient, the scoring weight for the target media object is determined according to the preference coefficient.

[0070] For further reference, Figure 5 As shown, determining the scoring weight of the target media object according to the preference coefficient includes:

[0071] Step S510. Obtaining a preset preference threshold and a preset weight;

[0072] Step S520: When the preference coefficient is greater than the preset preference threshold, the preset weight is adjusted according to the first preset coefficient to obtain a scoring weight for the target media object;

[0073] Step S530: When the preference coefficient is less than a preset preference threshold, the preset weight is adjusted according to a second preset coefficient to obtain a scoring weight for the target media object.

[0074] Steps S510-S530 will be further explained and illustrated below. Specifically, a preset preference threshold and a preset weight are obtained. The preset preference threshold can be 0.6, which is not specifically limited in this example embodiment. When the target user's preference coefficient is greater than the preset preference threshold, the preset weight can be adjusted based on a first preset coefficient to obtain the target user's scoring weight for the target media object. For example, when the target user's preference coefficient for a certain music genre is 0.9, which is greater than the preset preference threshold of 0.6, the target user's weight for the first type of target media object can be increased from 1 to 1.5. When the target user's preference coefficient is less than the preset preference threshold, the preset weight can be adjusted based on a second preset coefficient to obtain the target user's scoring weight for the first type of target media object. For example, when the target user's preference coefficient for a certain music genre is 0.3, which is less than the preset preference threshold of 0.6, the target user's weight for the first type of target media object can be reduced from 1 to 0.5. In this example embodiment, the first and second preset coefficients are not specifically limited.

[0075] In this exemplary embodiment, the accuracy and fairness of the target user ratings are ensured through a differentiated weight model.

[0076] In an exemplary embodiment, referring to Figure 6 As shown, after obtaining the target score of the target media object, the method further includes:

[0077] Step S610. Obtain historical rating data of the target user for the first type of media object, compare the historical rating data with the target rating of the target media object, and determine whether the target user's preference has changed;

[0078] Step S620: When the target user's preference changes, adjust the appreciation model and the preference coefficient.

[0079] In the following, step S610 and step S620 will be further explained and illustrated. Specifically, historical rating data of the target user for the first type of media object is obtained, and the historical rating data is compared with the target user's target rating for the target media object, and whether the user's preference has changed is determined based on the difference between the ratings. Specifically, the average or median of the historical rating data can be obtained, and the difference between the target rating and the median or average can be calculated. When the difference is greater than a preset difference, it is determined that the target user's preference for the first type of media object has changed. When the user's preference for the first type of media object changes, the appreciation model and the preference coefficient are adjusted. Specifically, the parameters in the appreciation model can be adjusted, and the target user's preference coefficient for the first type of media object can be adjusted based on the preset adjustment coefficient.

[0080] Furthermore, when a target user rates a first type of target media object, their understanding of the rating may differ from that of other target users. Some target users may be overly lenient, giving higher ratings, while others may be overly critical, giving lower ratings. Therefore, statistical methods can be used to analyze the target users' ratings of the first type of target media object to identify outliers that deviate from the overall mean. When the first type of target media object is pushed to target users again, the number of pushes to these outliers can be reduced.

[0081] Through the feedback mechanism (adjusting the preference coefficient based on changes in target scores and adjusting the push notifications to abnormal target users), not only the accuracy of target user scores is improved, but also the accuracy of personalized recommendations is improved, enhancing the user experience. Moreover, through continuous feedback and optimization, it can better adapt to changes in user preferences and appreciation.

[0082] In an exemplary embodiment, after the target user's target rating for the target media object is obtained, the target rating may be aggregated to calculate an average rating for each target media object, and the average rating may be displayed.

[0083] Exemplary devices

[0084] After introducing the media object evaluation method according to the exemplary embodiment of the present disclosure, Figure 7 A media object evaluation device according to an exemplary embodiment of the present disclosure will be described.

[0085] refer to Figure 7 As shown, the media object evaluation apparatus according to the exemplary embodiment of the present disclosure may include: a media object scoring module 710 and a target scoring acquisition module 720; wherein:

[0086] The media object scoring module 710 is used to obtain a target user based on the historical behavior data of the user group, push a target media object to the target user, and obtain the target user's score for the target media object;

[0087] The target score acquisition module 720 is used to determine the preference coefficient of the target user, determine the target user's score weight for the target media object based on the preference coefficient, and adjust the score according to the score weight to obtain the target score of the target media object.

[0088] According to an exemplary embodiment of the present disclosure, the media object scoring module includes:

[0089] an appreciation score acquisition module, configured to acquire historical behavior data of the user group on the media object, input the historical behavior data into an appreciation model, and obtain an appreciation score of each user in the user group;

[0090] The target user determination module is used to screen users according to the appreciation score of each user to obtain the target user.

[0091] According to an exemplary embodiment of the present disclosure, the historical behavior data of the user group on the media object includes the playback history data of each user on the media object, the portrait of each user and the interactive behavior data of each user; wherein, the playback history data includes at least one of the following: the number and frequency of playbacks, skip rate, number of repeated playbacks, style type, language type and coverage area of ​​the media object played, and artist coverage within a preset time period; the portrait includes comment content and user identity; the interactive behavior data includes at least one of the following: sharing behavior data, collection behavior data and network ecological value data.

[0092] According to an exemplary embodiment of the present disclosure, the target user determination module includes:

[0093] A scoring range determination module, configured to obtain the activity level of each user and a preset appreciation scoring range corresponding to the activity level group;

[0094] The user screening module is configured to determine a first activity group corresponding to the activity of each user and a first appreciation score range corresponding to the first activity group, and determine that the user is a target user when the appreciation score is within the first appreciation score range.

[0095] According to an exemplary embodiment of the present disclosure, the target score acquisition module includes:

[0096] The invalid score removal module is used to verify the scores and remove invalid scores from the scores.

[0097] According to an exemplary embodiment of the present disclosure, the target score acquisition module includes:

[0098] a preference coefficient determination module, configured to obtain the number of times the target user has collected and played a first type of media object, and obtain the preference coefficient of the target user based on the number of times the target user has collected and played the first type of media object;

[0099] The scoring weight acquisition module is used to determine the scoring weight for the target media object according to the preference coefficient.

[0100] According to an exemplary embodiment of the present disclosure, the scoring weight acquisition module includes:

[0101] A preset parameter acquisition module is used to obtain a preset preference threshold and a preset weight;

[0102] a first scoring weight adjustment module, configured to adjust the preset weight according to the first preset coefficient to obtain a scoring weight for the target media object of the first type when the preference coefficient is greater than the preset preference threshold;

[0103] The second scoring weight adjustment module is configured to adjust the preset weight according to a second preset coefficient to obtain a scoring weight for the target media object of the first type when the preference coefficient is less than a preset preference threshold.

[0104] According to an exemplary embodiment of the present disclosure, the target score acquisition module includes:

[0105] a rating comparison module, configured to obtain historical rating data of the target user for the first type of media object, compare the historical rating data with the target rating of the target media object, and determine whether the target user's preference has changed;

[0106] The model coefficient adjustment module is used to adjust the appreciation model and the preference coefficient when the preference of the target user changes.

[0107] Since the functional modules of the screen effect determination device in the embodiment of the present disclosure are the same as those in the disclosed embodiment of the screen effect determination method, they will not be described in detail here.

[0108] Exemplary Storage Media

[0109] After introducing the screen effect determination method and device according to the exemplary embodiment of the present disclosure, Figure 8 A computer-readable storage medium according to an exemplary embodiment of the present disclosure is described.

[0110] refer to Figure 8 As shown, a program product 800 for implementing the above method according to an embodiment of the present disclosure is described. The program product 800 may be a portable compact disk read-only memory (CD-ROM) and includes program code, and may be run on a device such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0111] The program product may be implemented in any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0112] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0113] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0114] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and the like, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0115] Exemplary electronic devices

[0116] After introducing the storage medium of the exemplary embodiment of the present disclosure, next, reference is made to Figure 9 An electronic device according to an exemplary embodiment of the present disclosure will be described.

[0117] Figure 9 The electronic device 900 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0118] like Figure 9 As shown, electronic device 900 is implemented as a general-purpose computing device. Components of electronic device 900 may include, but are not limited to, the at least one processing unit 910 described above, the at least one storage unit 920 described above, a bus 930 connecting various system components (including storage unit 920 and processing unit 910), and a display unit 940.

[0119] The storage unit stores program codes, which can be executed by the processing unit 910, so that the processing unit 910 performs the steps described in the "Exemplary Method" section of the present disclosure according to various exemplary embodiments. For example, the processing unit 910 can perform the following steps: Figure 1 Steps S110 and S120 shown in FIG.

[0120] The storage unit 920 may include a volatile storage unit, such as a random access memory unit (RAM) 9201 and / or a cache memory unit 9202 , and may further include a read-only memory unit (ROM) 9203 .

[0121] The storage unit 920 may also include a program / utility 9204 having a set (at least one) of program modules 9205, such program modules 9205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0122] The bus 930 may include a data bus, an address bus, and a control bus.

[0123] The electronic device 900 can also communicate with one or more external devices 1000 (e.g., a keyboard, a pointing device, a Bluetooth device, etc.), and such communication can be performed via an input / output (I / O) interface 950. The electronic device 900 also includes a display unit 940, which is connected to the input / output (I / O) interface 950 for display. In addition, the electronic device 900 can also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 960. As shown, the network adapter 960 communicates with other modules of the electronic device 900 via a bus 930. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0124] It should be noted that although the song relationship identification device and several modules or submodules of the song relationship identification device are mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided to be embodied by multiple units / modules.

[0125] Furthermore, although the operations of the disclosed method are described in a particular order in the accompanying drawings, this does not require or imply that the operations must be performed in this particular order, or that all illustrated operations must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0126] Although the spirit and principles of the present disclosure have been described with reference to several specific embodiments, it should be understood that the present disclosure is not limited to the specific embodiments disclosed, and the division into various aspects does not mean that the features in these aspects cannot be combined to benefit. Such division is only for the convenience of expression. The present disclosure is intended to cover various modifications and equivalent arrangements included in the spirit and scope of the appended claims.

Claims

1. A media object evaluation method, characterized in that: include: Determine target users based on historical behavior data of user groups, push target media objects to the target users, and obtain ratings of the target media objects by the target users; Determine the preference coefficient of the target user, determine the target user's scoring weight for the target media object based on the preference coefficient, adjust the score according to the scoring weight, and obtain a target score for the target media object.

2. The method according to claim 1, characterized in that Obtaining target users based on historical behavior data of user groups includes: Obtaining historical behavior data of the user group on the media object, inputting the historical behavior data into an appreciation model, and obtaining an appreciation score of each user in the user group; Users are screened according to the appreciation score of each user to obtain the target user.

3. The method according to claim 2, characterized in that The historical behavior data of the user group on the media object includes the playback history data of each user on the media object, the portrait of each user and the interactive behavior data of each user; wherein, the playback history data includes at least one of the following: the number and frequency of playbacks, skip rate, number of repeated playbacks, style type, language type, coverage area and artist coverage of the media object played within a preset time period; the portrait includes comment content and user identity; the interactive behavior data includes at least one of the following: sharing behavior data, collection behavior data and network ecological value data.

4. The method according to claim 2, characterized in that The user screening according to the appreciation score of each user to obtain the target user includes: Obtaining the activity level of each user and a preset appreciation score range corresponding to the activity level group; A first activity group corresponding to the activity of each user and a first appreciation score range corresponding to the first activity group are determined, and when the appreciation score is within the first appreciation score range, the user is determined to be a target user.

5. The method according to claim 2, characterized in that The determining the preference coefficient of the target user, and determining the scoring weight of the target user for the target media object based on the preference coefficient, includes: Obtaining the number of times the target user has collected and played a first type of media object, and obtaining a preference coefficient of the target user based on the number of times the target user has collected and played the media object; A scoring weight for the target media object is determined according to the preference coefficient.

6. The method according to claim 5, characterized in that Determining the scoring weight for the target media object according to the preference coefficient includes: Get the preset preference threshold and preset weight; When the preference coefficient is greater than the preset preference threshold, adjusting the preset weight according to the first preset coefficient to obtain a scoring weight for the target media object of the first type; When the preference coefficient is less than a preset preference threshold, the preset weight is adjusted according to a second preset coefficient to obtain a scoring weight for the target media object of the first type.

7. The method according to claim 5, characterized in that After obtaining the target score of the target media object, the method further includes: Obtaining historical rating data of the target user for the first type of media object, comparing the historical rating data with the target rating of the target media object, and determining whether the target user's preference has changed; When the preference of the target user changes, the appreciation model and the preference coefficient are adjusted.

8. A media object evaluation device, characterized in that: include: A media object scoring module is used to obtain a target user based on the historical behavior data of the user group, push a target media object to the target user, and obtain the target user's score for the target media object; The target score acquisition module is used to determine the preference coefficient of the target user, determine the score weight of the target user for the target media object based on the preference coefficient, and adjust the score according to the score weight to obtain the target score of the target media object.

9. A computer program product, comprising a computer program product, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: processor; as well as a memory for storing executable instructions of the processor; The processor is configured to perform the method according to any one of claims 1 to 7 by executing the executable instructions.

Images