Data processing method, recommendation method and related device applied to media resources

Abstract

The invention provides a data processing method and recommendation method applied to media resources and a related device, and relates to the technical field of computers, in particular to multiple fields of big data, intelligent search, intelligent recommendation and the like. The specific implementation scheme is as follows: determining a target scene to which a target resource belongs; determining a first interest influence of the target resource on the target object in the target scene based on a preset parameter of the target resource; determining a second interest influence of the target scene on the target object in the plurality of scene categories; and based on the first interest influence and the second interest influence, determining the comprehensive influence of the target resource on the target object in the plurality of scene categories.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and particularly to multiple fields such as big data, intelligent search, and intelligent recommendation. Background Art

[0002] With the rapid development of Internet technologies, the media resources accessible to users have become increasingly rich and diverse. In different usage scenarios, media resources that match the user's interests can be accurately matched and pushed according to the user's personalized preferences for various scenarios, so as to improve the user experience. Summary of the Invention

[0003] The present disclosure provides a data processing method, a recommendation method, and related devices for media resources.

[0004] According to one aspect of the present disclosure, there is provided a data processing method for media resources, including:

[0005] Determine a target scenario to which a target resource belongs;

[0006] Based on preset parameters of the target resource, determine a first interest influence of the target resource on a target object in the target scenario; and,

[0007] Determine a second interest influence of the target scenario on the target object among multiple scenario categories;

[0008] Based on the first interest influence and the second interest influence, determine a comprehensive influence of the target resource on the target object among multiple scenario categories.

[0009] According to another aspect of the present disclosure, there is provided a data processing device for media resources, including:

[0010] A first determination module for determining a target scenario to which a target resource belongs;

[0011] A second determination module for determining a first interest influence of the target resource on a target object in the target scenario based on preset parameters of the target resource; and determining a second interest influence of the target scenario on the target object among multiple scenario categories;

[0012] An integration module for determining a comprehensive influence of the target resource on the target object among multiple scenario categories based on the first interest influence and the second interest influence.

[0013] According to one aspect of the present disclosure, there is provided a recommendation method for media resources, including:

[0014] Obtain a resource recommendation request of a target object;

[0015] In response to a resource recommendation request of a target object, filter media resources to be recommended for the target object based on the comprehensive influence of multiple resources of the target object in multiple scenario categories; for a target resource among the multiple resources, determine the comprehensive influence corresponding to the target resource based on a data processing method applied to the media resource;

[0016] Perform a resource recommendation operation based on the media resources to be recommended.

[0017] According to another aspect of the present disclosure, there is provided a media resource recommendation apparatus, including:

[0018] An acquisition module, configured to acquire a resource recommendation request of a target object;

[0019] A response module, configured to, in response to a resource recommendation request of a target object, filter media resources to be recommended for the target object based on the comprehensive influence of multiple resources of the target object in multiple scenario categories; for a target resource among the multiple resources, determine the comprehensive influence corresponding to the target resource based on a data processing method applied to the media resource;

[0020] An execution module, configured to perform a resource recommendation operation based on the media resources to be recommended.

[0021] According to another aspect of the present disclosure, there is provided an electronic device, including:

[0022] At least one processor; and

[0023] A memory communicatively connected to the at least one processor; wherein,

[0024] The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute any method in the embodiments of the present disclosure.

[0025] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute any method in the embodiments of the present disclosure.

[0026] According to another aspect of the present disclosure, there is provided a computer program product, including a computer program, which when executed by a processor, implements any method in the embodiments of the present disclosure.

[0027] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings are used to better understand the present solution and do not constitute a limitation to the present disclosure. Among them:

[0029] Figure 1 is a schematic flowchart of a data processing method applied to media resources according to an embodiment of the present disclosure;

[0030] Figure 2 is a schematic flowchart of determining the first interest influence according to an embodiment of the present disclosure;

[0031] Figure 3 is a schematic flowchart of determining the comprehensive influence according to an embodiment of the present disclosure;

[0032] Figure 4 is a schematic flowchart of a recommendation method for media resources according to an embodiment of the present disclosure;

[0033] Figure 5 is a schematic overall flowchart of a data processing method applied to media resources according to an embodiment of the present disclosure;

[0034] Figure 6 is a schematic structural diagram of a data processing device applied to media resources according to an embodiment of the present disclosure;

[0035] Figure 7 is a schematic structural diagram of a recommendation device for media resources according to an embodiment of the present disclosure;

[0036] Figure 8 is a block diagram of an electronic device for implementing the data processing method applied to media resources and / or the recommendation method for media resources according to an embodiment of the present disclosure. Detailed implementation manners

[0037] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted below.

[0038] Terms such as "first" and "second" in the present disclosure are used to distinguish similar objects and do not necessarily describe a specific order or sequence. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0039] With the rapid development of Internet technology, the media resources accessible to users are becoming increasingly rich and diverse. Against this background, the recall technology based on content interest points has emerged. It mainly relies on the attribute information of content resources and the historical behavior data of users, and conducts content recommendation by calculating the similarity between contents or the matching degree between user interests and content attributes.

[0040] As the application scenarios become increasingly rich, users' interests in the same media resource often show diversity as the scenarios change. Traditional methods for matching the interests of target objects in a single scenario are difficult to cope with the changes in the interests of target objects in multiple scenarios, and cannot fully capture the diverse behaviors and interest points of target objects in different scenarios. This undoubtedly poses higher requirements for content matching methods.

[0041] In view of this, a data processing method for media resources is proposed in the embodiments of the present disclosure. It should be noted that in the technical solutions of the present disclosure, the acquisition, storage, and application of the personal information of the target object comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0042] As Figure 1 shown, it is a schematic flowchart of the data processing method for media resources provided by the embodiments of the present disclosure, including the following content:

[0043] S101, determine the target scenario to which the target resource belongs.

[0044] In the embodiments of the present disclosure, the target resource is the historical resource operated by the target object. During implementation, any historical resource operated by the target object can be used as the target resource respectively.

[0045] In the embodiments of the present disclosure, one target resource is used as an example for illustration. It can be understood that in the case of having multiple target resources, the processing method for each target resource is the same.

[0046] In the embodiments of the present disclosure, the target resource refers to a specific media resource, such as video, audio, article, picture, etc. Determining the target scenario to which the target resource belongs can be based on the interactive behavior data of the target object with content resources in different scenarios. According to dimensions such as the operation time, operation location, and operation device of the target resource in the interactive behavior data, the behavior data is divided into n different scenarios, where n is a positive integer. Each scenario represents the behavior pattern of the target object under specific conditions.

[0047] In the case where there is a natural scenario division in the application or platform containing the target resource, such as the recommendation scenario, live broadcast scenario, and e-commerce scenario, the scenario information of the original data can be directly utilized at this time, and there is no need to determine the target scenario to which the target resource belongs through other means.

[0048] It should be understood that the foregoing divided scenarios in the embodiments of the present disclosure are only for illustrative purposes and are not used to limit the embodiments of the present disclosure.

[0049] S102. Determine a first interest influence of the target resource on the target object in the target scenario based on preset parameters of the target resource.

[0050] The preset parameters are indicators used to describe the relevance between the target object and the target resource. The first interest influence determined based on the preset parameters of the target resource can be used to measure the degree of interest of the target object in a specific target resource in a specific target scenario.

[0051] S103. Determine a second interest influence of the target scenario on the target object among multiple scenario categories.

[0052] The second interest influence is used to measure the degree of interest of the target object in the target scenario among multiple scenario categories.

[0053] Among them, the execution order of steps S102 and S103 is not limited.

[0054] S104. Determine a comprehensive influence of the target resource on the target object among multiple scenario categories based on the first interest influence and the second interest influence.

[0055] During implementation, the first interest influence and the second interest influence can be fused to obtain a comprehensive influence to measure the comprehensive degree of interest of the target object in the target resource among multiple scenario categories.

[0056] The target resource and its comprehensive influence can be stored for use when recommending the target resource to the target object.

[0057] Among them, for each interest tag, the corresponding multiple scenarios and the target resources interacted by the target object included in each scenario under the interest tag can be determined respectively. Thus, based on the method provided in the embodiments of the present disclosure, the comprehensive degree of interest of the target object in each target resource under each interest tag can be determined, so as to facilitate the recommendation of target resources based on the interest tag.

[0058] In the embodiments of the present disclosure, based on the preset parameters of the target resource, the first interest influence of the target resource on the target object in the target scenario is determined, which can accurately describe the degree of interest of the target object in the target resource in the target scenario. Determining the second interest influence of the target scenario on the target object among multiple scenario categories can accurately describe the degree of interest generated by the target object due to the characteristics and classification of the scenario itself in a wider range of scenario categories, which helps to determine the interest tendency of the target object from the scenario categories. The comprehensive influence determined based on the first interest degree and the second interest degree can comprehensively and objectively reflect the actual influence effect of the target resource under different scenario categories, and thus the comprehensive interest degree of the target resource on the target object can be comprehensively measured. Thereby, it is possible to more pertinently allocate media resources during the recommendation process, so as to more accurately match the interests and needs of the target object and improve the resource utilization efficiency and recommendation effect.

[0059] In the embodiments of the present disclosure, the preset parameters of the target resource include at least one of the following sub-parameters:

[0060] (1) The degree of time decay;

[0061] The degree of time decay refers to the degree to which the interest influence of the target resource on the target object gradually weakens over time. For example, a target resource may have a high attraction to the target object when it is just released, but this attraction may gradually decrease over time.

[0062] During implementation, the degree of time decay can be set based on linear decay or exponential decay.

[0063] It is also possible to set the degree of time decay separately according to the importance of different scenarios. For example, a slower time decay is set for important scenarios to reflect their relatively lasting influence.

[0064] (2) The operation value of the specified operation of the target object on the target resource.

[0065] The specified operation of the target object on the target resource refers to some specific operations performed by the target object on the target resource, which can reflect the degree of interest or participation of the target object in the resource. Such as clicking on the target resource, staying on the target resource, etc. The operation value is a quantified value of these operations, used to measure the degree of interest of the target object in the target resource. During implementation, the operation value can be selected as the click frequency of the target object on the target resource, the stay duration / average stay duration / maximum stay duration on the target resource, etc.

[0066] In the embodiments of the present disclosure, the degree of time decay can more accurately reflect the timeliness of the target object's interest in the target resource, and can avoid the outdated recommendation of the target resource caused by simply relying on historical operation values, so as to more reasonably arrange the recommendation frequency of the target resource. The operation value of the specified operation of the target object on the target resource can more intuitively measure the intensity of the target object's interest in the target resource, so as to improve the accuracy of the first interest influence.

[0067] During implementation, when the preset parameters include multiple sub-parameters, the first interest influence of the target resource on the target object in the target scenario can be determined based on the preset parameters of the target resource. The specific implementation method can be as Figure 2 shown and includes the following content:

[0068] S201. Based on each sub-parameter, respectively determine the sub-influence of the target resource on the target object in the target scenario.

[0069] For the target scenario, the behavior sequence of the target object in the target scenario i can be generated through data analysis That is, the sequence set of multiple target resources interacted by the target object in the target scenario i.

[0070] During implementation, for the interaction behavior of the target object u with the target resource j in the target scenario i, the key behavior feature set F can be extracted uj . At the same time, the keywords in the target resource can be extracted as interest points by using NLP (Natural Language Processing) technology and added to the feature set F uj together, and finally aggregated to obtain which can be expressed as:

[0071]

[0072] In formula (1), represents the set of behavior sequences of a single target object interacting with multiple target resources in the i-th target scenario.

[0073] After that, the can be used to count the sub-influence of the target object on each interacted target resource in a single target scenario i Taking the half-life decay as an example, the specific calculation method is as follows:

[0074]

[0075] In formula (2), is the sub-influence of the j-th target resource in the behavior sequence of the target object in the i-th target scenario; t j is the time span from the occurrence of the interaction behavior with the j-th target resource to the current time, such as days, hours, minutes, etc.; Thalf is the half-life (the unit is aligned with t). For example, when T half is set to 15 days, it means that the importance of interest on the most recent day is 1.0, and the importance of interest of the behavior that occurred 15 days ago will exponentially decay to 0.5; a is a constant.

[0076] Of course, in the case of determining the first influence based on the degree of time decay, the calculated in formula (2) is the first influence.

[0077] In the case of determining the sub-influence based on the operation value of the specified operation of the target object on the target resource, when the specified operation is used to express that the target object is interested in the resource, there is a direct proportional relationship between the operation value of the specified operation and its corresponding sub-influence. For example, it can be considered according to the click frequency of the target object and the residence time of the target object in the resource. The more the number of clicks and / or the longer the residence time, the greater the corresponding sub-influence.

[0078] Correspondingly, when the specified operation is used to express that the target object is not interested in the resource, there is an inverse proportional relationship between the operation value of the specified operation and its corresponding sub-influence.

[0079] S202, fuse multiple sub-influences of multiple sub-parameters to obtain the first interest influence.

[0080] In some embodiments, the multiple sub-influences of the obtained multiple sub-parameters can be directly fused in an additive manner to obtain the first interest influence.

[0081] In other embodiments, according to the actual business scenario, different weights can also be assigned to the sub-influences of each sub-parameter, and then the sub-influences are multiplied by their weights and added together to obtain the first interest influence. Or the weights of each sub-parameter are automatically learned through a neural network model to make the first interest influence obtained by fusion reach the optimal under a certain evaluation index.

[0082] It can be understood that the first interest influence has a direct proportional relationship with each sub-influence. The specific expression can be determined according to actual needs, and the embodiments of the present disclosure do not limit this.

[0083] In the embodiments of the present disclosure, different sub-parameters included in the preset parameters of the target resource can reflect the degree of interest of the target object in the target resource from different angles. Determining sub-influences based on different sub-parameters can more carefully and comprehensively understand the specific role of each sub-parameter on the first interest influence, so as to provide a detailed and multi-dimensional analysis basis for subsequent comprehensive evaluation, making the finally obtained first interest influence more objective and accurate, avoiding the one-sidedness that may be brought by a single sub-parameter evaluation, and providing support for subsequent comprehensive influence evaluation.

[0084] In the embodiments of the present disclosure, determining the second interest influence of a target scenario on a target object among multiple scenario categories can be affected by multiple key parameters. That is, according to specific business scenarios and application requirements, the importance of each key parameter in different scenario categories is also different.

[0085] During implementation, the key parameters of the target scenario include at least one of the following key parameters:

[0086] (1) Resource operation duration parameter;

[0087] In the target scenario, the resource operation duration parameter refers to the total duration that the target object spends operating all resources in the target scenario.

[0088] In multiple scenario categories, the resource operation duration parameter refers to the total operation duration of the target object for all resources under these multiple scenario categories.

[0089] (2) Resource quantity parameter;

[0090] In the target scenario, the resource quantity parameter refers to the number of resources that the target object has interacted with in the target scenario.

[0091] In multiple scenario categories, the resource quantity parameter refers to the total number of resources that the target object has interacted with under these multiple scenario categories.

[0092] (3) Activity parameter.

[0093] In the target scenario, the activity parameter is a parameter that comprehensively measures the activity level of the target object in the target scenario.

[0094] In multiple scenario categories, the activity parameter refers to the activity parameter of the target object under multiple scenario categories.

[0095] After determining the key parameters of the target scenario, based on the importance corresponding to the key parameters, the second interest influence of the target scenario on the target object among multiple scenario categories can be determined.

[0096] During implementation, in the case where the target scenario contains only one parameter, since the importance of the same parameter may also be different in different scenario categories. Therefore, during implementation, the importance weight of the target scenario among multiple scenario categories can be determined based on this parameter to obtain the second interest influence.

[0097] In the case where the target scenario contains multiple parameters, according to the importance of each parameter in the scenario category, a weight is assigned to each parameter, and using the method of weighted summation, the standardized parameter value is multiplied by the corresponding weight, and then they are added together to obtain the second interest influence.

[0098] In the embodiments of the present disclosure, based on the importance corresponding to the key parameters, the second interest influence of the target scenario on the target object among multiple scenario categories can be determined, which can comprehensively and accurately evaluate the interest influence of the target scenario on the target object in different scenario categories, and can relatively accurately describe the second interest influence to improve the recommendation effect and user experience.

[0099] In the embodiments of the present disclosure, to determine the importance corresponding to the resource operation duration parameter, the importance corresponding to the resource operation duration parameter can be determined based on the first resource operation duration of the target object in the target scenario and the second resource operation duration of the target object for the resources in multiple scenario categories; wherein, the importance corresponding to the resource operation duration parameter has a direct proportional relationship with the first resource operation duration and an inverse proportional relationship with the second resource operation duration.

[0100] The first resource operation duration refers to the total duration spent by the target object in operating the resource in the target scenario.

[0101] The second resource operation duration refers to the total duration spent by the target object in operating the resource in multiple scenario categories. That is, it is the duration obtained by adding up the time of the target object interacting with the resource in each different scenario category.

[0102] Based on the first resource operation duration and the second resource operation duration to determine the importance corresponding to the resource operation duration parameter, it can be implemented based on formula (3):

[0103]

[0104] In formula (3), A is the importance corresponding to the resource operation duration parameter, that is, the proportion of the total stay duration of the target object in the target scenario in the total stay duration of all scenarios; represents the total duration spent by the target object in operating the resource in the i-th target scenario, that is, the stay duration in the target scenario; wherein, is the feature set of the j-th content in the i-th scenario of the target object u, represents taking the feature of the stay duration. represents the total duration spent by the target object in operating the resource in all scenarios, and n is the number of categories of multiple scenario categories, that is, the total stay duration of the target object in multiple scenario categories.

[0105] The fact that the importance corresponding to the resource operation duration parameter has a direct proportional relationship with the first resource operation duration indicates that the longer the first resource operation duration, the more time the target object invests in operating the resource in the target scenario and the more interested it is in the resource in this target scenario.

[0106] The importance level corresponding to the resource operation duration parameter is inversely proportional to the second resource operation duration, indicating that when the target object has a longer second resource operation duration for resources in multiple scene categories, the importance level of the resource operation duration parameter in evaluating the target scene is lower. That is, the lower the level of interest of the target object in the target scene.

[0107] In the embodiments of the present disclosure, by comparing and analyzing the first resource operation duration of the target object in the target scene with the second resource operation duration in multiple scene categories, the attractiveness and influence of the target scene on the target object relative to other scenes can be accurately measured. Specifically, the first resource operation duration reflects the depth of interest of the target object in the target scene, while the second resource operation duration reflects the breadth of interest of the target object in other scene categories. Through this comparison, the unique attractiveness of the target scene to the target object among multiple scene categories can be evaluated more accurately, providing a strong basis for subsequent scene optimization and resource recommendation.

[0108] In the embodiments of the present disclosure, to determine the importance level corresponding to the resource quantity parameter, it can be based on the first resource quantity represented by the resource quantity parameter of the target object in the target scene and the second resource quantity of the resources operated by the target object in multiple scene categories, and determine the importance level corresponding to the resource quantity parameter; wherein, the importance level corresponding to the resource quantity parameter is directly proportional to the first resource quantity and inversely proportional to the second resource quantity.

[0109] The first resource quantity refers to the total number of resources interacted by the target object in the target scene. For example, the total number of videos watched in the target scene.

[0110] The second resource quantity refers to the total number of resources operated by the target object in multiple scene categories. That is, the total number obtained by adding up the resource quantities operated by the target object in multiple scene categories.

[0111] Based on the first resource quantity and the second resource quantity to determine the importance level corresponding to the resource quantity parameter, as shown in formula (4):

[0112]

[0113] In formula (4), B represents the importance level corresponding to the resource quantity parameter, that is, the proportion of the number of resources interacted by the target object in the target scene in all scenes; represents the number of resources interacted by the target object u in the i-th scene; represents the sum of the number of resources interacted by the target object u in all scenes, and n is the number of categories of multiple scene categories.

[0114] The importance level corresponding to the resource quantity parameter is directly proportional to the first resource quantity, indicating that the larger the first resource quantity, the more content resources the target object has interacted with in the target scenario, indicating that the target object has a higher demand for and dependence on the quantity of resources in this scenario, that is, the target object has a higher interest level in the target scenario.

[0115] However, the importance level corresponding to the resource quantity parameter is inversely proportional to the second resource quantity, indicating that when the second resource quantity of the target object in multiple scenario categories is larger, the importance level of the resource quantity parameter in evaluating the target scenario is lower, that is, the interest level of the target object in the target scenario is lower.

[0116] In the embodiments of the present disclosure, by comparing the first resource quantity of the target object in the target scenario with the second resource quantity in multiple scenario categories, that is, calculating the proportion of the number of content interactions in the current scenario to all scenarios, the importance level of the resource quantity parameter can be accurately determined.

[0117] In the embodiments of the present disclosure, to determine the importance level corresponding to the activity parameter, it can be based on the first activity corresponding to the activity parameter of the target object in the target scenario and the second activity of the target object in multiple scenario categories; wherein, the importance level corresponding to the activity parameter is directly proportional to the first activity and inversely proportional to the second activity;

[0118] The first activity is inversely proportional to the time span between the operation time of the resources in the target scenario by the target object and the current time, and is directly proportional to the resource quantity of the target object in the target scenario;

[0119] The second activity is directly proportional to the time span between the operation time of the resources in multiple scenario categories by the target object and the current time, and is inversely proportional to the resource quantity of the target object in multiple scenario categories.

[0120] Based on the first activity and the second activity to determine the importance level corresponding to the activity parameter, it can be as shown in formula (5):

[0121]

[0122] In formula (5), C represents the importance level corresponding to the activity parameter; represents the average time span for the target object to interact with resources in the i-th target scenario, that is, the average time span from the time when the target object has an interaction behavior with each resource to the current time, where t j is the time span from the time when the interaction behavior with the j-th target resource occurs to the current time; represents the sum of the average time spans of the target object interacting with resources in all scenarios; exp(-·) is the exponential function used to calculate the recent activity of the current scenario; the smaller the time span (i.e., the closer the content behavior is to the current time), the larger the value of the exponential function, indicating higher recent activity.

[0123] The first activity level reflects the activity level of the target object in the target scenario. The importance level corresponding to the activity parameter has a direct proportional relationship with the first activity level, indicating that the higher the activity level of the target object in the target scenario, the more important the activity parameter is when evaluating the target scenario. The second activity level reflects the overall activity level of the target object in multiple scenario categories, and the importance level corresponding to the activity parameter has an inverse proportional relationship with the second activity level, indicating that when the activity level of the target object in multiple scenario categories is relatively high, the activity of the target object is dispersed in multiple scenarios, resulting in a relatively lower activity level in the target scenario.

[0124] Among them, the inverse proportional relationship between the first activity level and the time span indicates that the shorter the time span, the closer the operation behavior of the target object on the resources in the target scenario is to the current time, and the higher the activity level. The direct proportional relationship with the resource quantity indicates that the more resources the target object interacts with in the target scenario, the higher its activity level in this target scenario.

[0125] The direct proportional relationship between the second activity level and the time span indicates that in multiple scenario categories, the longer the time span of the operation behavior of the target object, the farther the operation behavior of the target object on the resources in these multiple scenario categories is from the current time, indicating that its recent activity level in these scenarios is lower. The inverse proportional relationship with the resource quantity in multiple scenario categories indicates that the more resources the target object interacts with in multiple scenario categories, it also means that its interests are widely dispersed in each scenario rather than focused on the target scenario, so the activity level is lower.

[0126] In the embodiments of the present disclosure, by comparing the first activity level and the second activity level, the importance level of the activity parameter of the target object in the target scenario can be evaluated more accurately. By comprehensively considering the activity performance of the target object in the target scenario and other multiple scenario categories, more comprehensive evaluation data is provided.

[0127] In summary, after determining the importance levels corresponding to the resource operation duration parameter, the resource quantity parameter, and the activity parameter respectively, the second interest influence can be obtained by fusing based on the weights corresponding to each parameter:

[0128]

[0129] In formula (6), δ (i) represents the second interest influence, γ1, γ2, and γ3 are the weights controlling the above three importance levels respectively, and each weight satisfies constraint

[0130] In the embodiments of the present disclosure, based on the first interest influence and the second interest influence, the implementation manner of determining the comprehensive influence of the target resource on the target object in multiple scenario categories can be as Figure 3 shown, including:

[0131] S301, based on the first interest influence and the second interest influence, determine the influence intermediate value of the target resource; the influence intermediate value has a direct proportional relationship with both the first interest influence and the second interest influence.

[0132] Based on the content described above, the influence intermediate value of the jth target resource in the behavior sequence of the target object in the ith scenario is Since this intermediate value is a measure of the target resource in a single target scenario, it is necessary to find, in S302, the influence intermediate value of the target resource in other scenarios except the target scenario among multiple scenario categories.

[0133] S303, in the case where the influence intermediate value of the target resource in other scenarios is found, based on the influence intermediate value of the target resource in the target scenario and the influence intermediate value of the target resource in other scenarios, determine the comprehensive influence of the target resource on the target object in multiple scenario categories.

[0134] That is, for the same target resource appearing in multiple scenarios, the obtained intermediate values can be further merged and de-duplicated to determine the comprehensive influence of the target resource on the target object in multiple scenario categories. When implementing, it can be achieved based on the following steps:

[0135] Step A1, obtain the influence intermediate value of the target resource in the target scenario and the maximum value among the influence intermediate values of the target resource in other scenarios;

[0136] Step A2, based on the total number of scenarios to which the target resource belongs and the maximum value, determine the comprehensive influence.

[0137] That is, after finding the maximum value from the influence intermediate values generated by the target resource in different scenarios (including the target scenario and other scenarios), and combining the total number of scenarios to which the target resource belongs, a comprehensive influence that can more comprehensively measure the target resource on the target object in multiple scenario categories can be obtained.

[0138] When implementing, in the case where the influence intermediate values of the target resource in different scenarios are all different, by comparing the intermediate values of the target resource, select the maximum value and multiply it by the total number of scenarios to determine the comprehensive influence. In the case where the intermediate values are all the same, select any value and multiply it by the total number of scenarios to determine the comprehensive influence.

[0139] In the embodiments of the present disclosure, based on the total number of scenarios to which the target resource belongs and the maximum value, the comprehensive influence is determined, and the comprehensive influence of the target resource on the target object can be evaluated more comprehensively and reasonably according to the diversity of scenarios and the performance of the resource in different scenarios.

[0140] In the embodiments of the present disclosure, by finding the intermediate value of the influence of the target resource in other scenarios except the target scenario, the influence of the target resource can be comprehensively considered from multiple scenarios, avoiding evaluation deviation caused by the limitation of a single scenario. Then, based on the intermediate values of the influence of the target resource in the target scenario and other scenarios, the comprehensive influence is determined, which can more accurately reflect the true influence of the target resource on the target object.

[0141] Based on the data processing method for media resources described above, the present disclosure also provides a method for recommending media resources, as Figure 4 shown, including the following:

[0142] S401, obtaining a resource recommendation request of the target object.

[0143] S402, in response to the resource recommendation request of the target object, screening media resources to be recommended for the target object based on the comprehensive influence of multiple resources of the target object in multiple scenario categories; for the target resource among the multiple resources, the corresponding comprehensive influence of the target resource is determined based on the method described above.

[0144] During implementation, the corresponding comprehensive influence of the target resource can be determined based on the method described above, and resources with higher comprehensive influence can be screened out as media resources to be recommended.

[0145] S403, performing a resource recommendation operation based on the media resources to be recommended.

[0146] The screened media resources to be recommended are generated into a recommendation list in a certain order and format, and the recommendation list is pushed to the target object in an appropriate manner.

[0147] In the embodiments of the present disclosure, by screening resources based on the comprehensive influence, the interests and needs of the target object can be more accurately matched, the relevance and attractiveness of the recommended content can be improved, thereby enhancing the experience of the target object and the satisfaction of the platform. The comprehensive influence takes into account the performance of the resource in different scenarios and the behavioral characteristics of the target object, making the recommendation result more comprehensive and objective, and avoiding recommendation deviation caused by a single factor. This recommendation method can dynamically adjust the recommended content according to the behavioral changes of the target object and the update of the resource, and has good real-time performance and adaptability, always maintaining the freshness and effectiveness of the recommendation.

[0148] In summary, the overall process of the data processing method for media resources provided in the embodiments of the present disclosure is asFigure 5 As shown in the figure, it includes:

[0149] S501, Point of Interest collection and preprocessing.

[0150] First, collect the interaction behavior data of the target object on content resources in different scenarios, including search, click, browse, etc., which can be determined according to actual needs. These data can be obtained through various channels such as website logs and mobile application data. After that, perform data cleaning and screening on abnormal data, including identifying and deleting duplicate data records to improve the accuracy and reliability of the data; detecting and processing outliers, null data, invalid data, etc. to ensure the integrity and consistency of the data; finally, according to the defined rules of actual needs, convert the data into a unified format, such as the first column of data is the target object, the second column of data is the network resource of the operation, and the third column of data is the operation time, so as to facilitate data storage.

[0151] S502, Scene splitting and feature processing.

[0152] First, the behavior data can be divided into n different scenarios according to dimensions such as the operation time, operation location, and operation device of the target object on the target resource. Each scenario represents the behavior pattern of the target object under specific conditions. The interaction behavior data of the target object u on the target resource is denoted as S, then:

[0153]

[0154] Among them, the superscripts 0 - n represent n different scenarios. In terms of the method of scene division, some applications or platforms naturally have scene divisions, such as recommendation scenarios, live broadcast scenarios, and e-commerce scenarios. At this time, the scene information of the original data can be directly used without manual division.

[0155] For the interaction behavior of the target object u on the target resource j in each scenario, extract the key behavior feature set F uj , such as the behavior occurrence time, click frequency, stay time, etc. At the same time, the keywords in the target resource can be extracted using NLP (Natural Language Processing) technology as points of interest and added to the feature set F uj Finally, each scenario separately aggregates the behavior sequence of the target object (i is a certain single scenario mentioned in the previous text), that is:

[0156]

[0157] S503, Multi-scenario interest fusion and sorting.

[0158] That is, in the case where the preset parameters include multiple sub-parameters, based on each sub-parameter, the sub-influence of the target resource on the target object in the target scenario is determined respectively. Then, the multiple sub-influences of the multiple sub-parameters are fused to obtain the first interest influence.

[0159] Specifically, based on the obtained behavior sequence of the target object u The overall steps for fusing each scenario are as follows:

[0160] The first step is to statistically analyze the first interest influence of the target object u on each interacted target resource in a single scenario i Taking the half-life decay as an example for the specific calculation method:

[0161]

[0162] Thus, each scenario can obtain its own ordered behavior sequence in the way of half-life decay.

[0163] The second step is based on the second interest influence of the target scenario on the target object in multiple scenario categories, denoted as δ (i) , and the specific calculation method is the same as formula (6).

[0164] The third step, from the first and second steps, it can be obtained that the interest importance of the target object u in the behavior sequence of the i-th scenario for the j-th target resource is According to the final interest importance, the ordered behavior sequences obtained in the first step are merged and de-duplicated. For example, for the interest importance of the same target resource, the maximum value is taken and multiplied by the number of repeated occurrences. That is, in different scenarios, when the same target resource appears simultaneously, when merging these different scenarios, the interest importance of the same target resource is compared. In the case where the interest importance is the same, any value is selected and multiplied by the number of repeated occurrences; in the case where the interest importance is different, the maximum value is selected and multiplied by the number of repeated occurrences.

[0165] Finally, as new interaction behaviors between the target object and the target resource continuously occur, δ (i) and will be updated offline at regular intervals to achieve the effect of dynamic weighting.

[0166] S504, Interest fusion and ranking in multiple scenarios.

[0167] After obtaining the interest points after multi-scenario fusion, a relatively conventional content-based recall method can be used to match the target resources. Specifically, taking the target object's interest points as the query key, the target resources with this key are retrieved from the target resource database, and finally the recall results are obtained.

[0168] During implementation, for each interest tag of the target object, the above content-based recall method can be separately used for statistics to clearly understand the comprehensive interest degree of the recallable content resources under each interest tag.

[0169] For example, for interest tag 1, the top n resources with higher comprehensive interest degree are selected as candidate recommended resources according to the screening and sorting, or the sorting scores are calculated according to the comprehensive interest degree and other parameters, and the top n resources with higher sorting scores are selected.

[0170] In the case of multiple interest tags, appropriate resources can be selected from the resource sets corresponding to each interest tag based on the comprehensive interest degree of each resource for recall and sorting, and the recalled target resources are presented to the target object.

[0171] In summary, through the data processing method for media resources provided by the implementation of the present disclosure, the problems that the interest points of the target object are scattered, difficult to accurately integrate, and difficult to balance multiple interests during cross-scene content recommendation can be solved, so as to realize the in-depth mining and efficient response to the personalized needs of the target object.

[0172] Based on the same technical concept, the embodiments of the present disclosure also provide a data processing device 600 for media resources, as Figure 6 shown, including:

[0173] The first determination module 601 is configured to determine the target scene to which the target resource belongs;

[0174] The second determination module 602 is configured to determine the first interest influence of the target resource on the target object in the target scene based on the preset parameters of the target resource; and determine the second interest influence of the target scene on the target object among multiple scene categories;

[0175] The comprehensive module 603 is configured to determine the comprehensive influence of the target resource on the target object among multiple scene categories based on the first interest influence and the second interest influence.

[0176] In some embodiments, the preset parameters include at least one of the following sub-parameters:

[0177] The time decay degree, the operation value of the specified operation of the target object on the target resource.

[0178] In some embodiments, when the preset parameters include multiple sub-parameters, the second determination module includes:

[0179] The first determination unit is configured to separately determine the sub-influence of the target resource on the target object in the target scene based on each sub-parameter;

[0180] A fusion unit for fusing multiple sub - influences of multiple sub - parameters to obtain a first interest influence.

[0181] In some embodiments, the second determination module includes:

[0182] A second determination unit for determining the importance degree of at least one of the following key parameters of the target scenario in multiple scenario categories: resource operation duration parameter, resource quantity parameter, activity parameter;

[0183] A third determination unit for determining the second interest influence of the target scenario on the target object in multiple scenario categories based on the importance degree corresponding to the key parameter.

[0184] In some embodiments, when the second determination module determines the importance degree corresponding to the resource operation duration parameter, it includes:

[0185] Based on the first resource operation duration of the target object in the target scenario and the second resource operation duration of the target object for resources in multiple scenario categories, determine the importance degree corresponding to the resource operation duration parameter;

[0186] Among them, the importance degree corresponding to the resource operation duration parameter has a direct proportional relationship with the first resource operation duration and an inverse proportional relationship with the second resource operation duration.

[0187] In some embodiments, when the second determination module determines the importance degree corresponding to the resource quantity parameter, it includes:

[0188] Based on the first resource quantity represented by the resource quantity parameter of the target object in the target scenario and the second resource quantity of the resources operated by the target object in multiple scenario categories, determine the importance degree corresponding to the resource quantity parameter;

[0189] Among them, the importance degree corresponding to the resource quantity parameter has a direct proportional relationship with the first resource quantity and an inverse proportional relationship with the second resource quantity.

[0190] In some embodiments, when the second determination module determines the importance degree corresponding to the activity parameter, it includes:

[0191] Based on the first activity corresponding to the activity parameter of the target object in the target scenario and the second activity of the target object in multiple scenario categories;

[0192] Among them, the importance degree corresponding to the activity parameter has a direct proportional relationship with the first activity and an inverse proportional relationship with the second activity;

[0193] The first activity level has an inverse relationship with the time span between the operation time of the target object on the resources in the target scenario and the current time, and has a direct relationship with the amount of resources of the target object in the target scenario;

[0194] The second activity level has a direct relationship with the time span between the operation time of the target object on the resources in multiple scenario categories and the current time, and has an inverse relationship with the amount of resources of the target object in multiple scenario categories.

[0195] In some embodiments, the comprehensive module includes:

[0196] The fourth determination unit is configured to determine an intermediate influence value of the target resource based on the first interest influence and the second interest influence; the intermediate influence value has a direct relationship with both the first interest influence and the second interest influence;

[0197] The search unit is configured to search for the intermediate influence value of the target resource in other scenarios except the target scenario in multiple scenario categories;

[0198] The fifth determination unit is configured to, when the intermediate influence value of the target resource in other scenarios is found, determine the comprehensive influence of the target resource on the target object in multiple scenario categories based on the intermediate influence value of the target resource in the target scenario and the intermediate influence value of the target resource in other scenarios.

[0199] In some embodiments, the fifth determination unit is specifically configured to:

[0200] Obtain the maximum value between the intermediate influence value of the target resource in the target scenario and the intermediate influence value of the target resource in other scenarios;

[0201] Determine the comprehensive influence based on the total number of scenarios to which the target resource belongs and the maximum value.

[0202] Based on the same technical concept, an embodiment of the present disclosure further provides a media resource recommendation device 700, as Figure 7 shown, including:

[0203] The acquisition module 701 is configured to acquire a resource recommendation request of the target object;

[0204] The response module 702 is configured to, in response to the resource recommendation request of the target object, screen the media resources to be recommended for the target object based on the comprehensive influence of multiple resources of the target object in multiple scenario categories; for the target resource among the multiple resources, determine the comprehensive influence corresponding to the target resource based on any of the foregoing methods;

[0205] The execution module 703 is configured to perform a resource recommendation operation based on the media resources to be recommended.

[0206] For the specific functions and examples of the modules and sub - modules of the device according to the embodiments of the present disclosure, reference may be made to the relevant descriptions of the corresponding steps in the above - mentioned method embodiments, which will not be elaborated herein.

[0207] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0208] Figure 8 FIG. shows a schematic block diagram of an exemplary electronic device 800 that can be used to implement the embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital assistant, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely exemplary and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0209] As Figure 8 shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read - only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random - access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0210] A plurality of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0211] The computing unit 801 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 executes the various methods and processes described above, such as the data processing method applied to media resources and the recommendation method for media resources. For example, in some embodiments, the data processing method applied to media resources and the recommendation method for media resources can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the data processing method applied to media resources and the recommendation method for media resources described above can be executed. Alternatively, in other embodiments, the computing unit 801 can be configured to execute the data processing method applied to media resources and the recommendation method for media resources by any other suitable means (such as, by means of firmware).

[0212] Various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), system on a chip systems (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: implemented in one or more computer programs, the one or more computer programs can be executed and / or interpreted on a programmable system including at least one programmable processor, the programmable processor can be a special or general programmable processor, can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0213] The program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, a special purpose computer, or other programmable data processing device, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on the remote machine or server.

[0214] In the context of the present disclosure, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0215] In order to provide interaction with a user, the systems and techniques described herein may be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0216] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend, middleware, or frontend components. The components of the system can be interconnected with each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), and the Internet.

[0217] A computer system can include a client and a server. The client and the server are generally far from each other and typically interact through a communication network. The client-server relationship is created by computer programs that run on the respective computers and have a client-server relationship with each other. The server can be a cloud server, a server of a distributed system, or a server integrated with a blockchain.

[0218] Based on the foregoing electronic device, the present disclosure also provides a vehicle, which can include the electronic device, and can also include a communication component, a display screen for implementing a human-machine interface, an information collection device for collecting surrounding environment information, etc. The communication component, the display screen, and the information collection device are communicatively connected to the electronic device.

[0219] According to an embodiment of the present disclosure, the electronic device can be integrally integrated with the communication component, the display screen, and the information collection device, or can be separately provided from the communication component, the display screen, and the information collection device.

[0220] It should be understood that various forms of the processes shown above can be used, steps can be reordered, added, or deleted. For example, the steps described in the present disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and no limitations are imposed herein.

[0221] The above specific embodiments do not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the principles of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

1. A data processing method for media resources, comprising: Determining a target scenario to which a target resource belongs; Based on preset parameters of the target resource, determining a first interest influence of the target resource on a target object in the target scenario; And Determining a second interest influence of the target scenario on the target object among multiple scenario categories; Based on the first interest influence and the second interest influence, determining a comprehensive influence of the target resource on the target object among the multiple scenario categories.

2. The method according to claim 1, wherein, The preset parameters include at least one of the following sub-parameters: Degree of time decay, operation value of a specified operation of the target object on the target resource.

3. The method according to claim 2, wherein When the preset parameters include multiple sub-parameters, the determining, based on the preset parameters of the target resource, a first interest influence of the target resource on a target object in the target scenario includes: Based on each sub-parameter, respectively determining a sub-influence of the target resource on the target object in the target scenario; Fusing multiple sub-influences of the multiple sub-parameters to obtain the first interest influence.

4. The method according to any one of claims 1-3, wherein, The determining a second interest influence of the target scenario on the target object among multiple scenario categories includes: Determining the importance degree of at least one of the following key parameters of the target scenario in each of the multiple scenario categories: resource operation duration parameter, resource quantity parameter, activity parameter; Based on the importance degree corresponding to the key parameter, determining a second interest influence of the target scenario on the target object among the multiple scenario categories.

5. The method according to claim 4, wherein Determining the importance degree corresponding to the resource operation duration parameter includes: Based on a first resource operation duration of the target object in the target scenario and a second resource operation duration of the target object on resources in the multiple scenario categories, determining the importance degree corresponding to the resource operation duration parameter; Wherein, the importance degree corresponding to the resource operation duration parameter has a direct proportional relationship with the first resource operation duration and an inverse proportional relationship with the second resource operation duration.

6. The method according to claim 4, wherein, Determining the importance degree corresponding to the resource quantity parameter includes: Based on a first resource quantity represented by the resource quantity parameter of the target object in the target scenario and a second resource quantity of resources operated by the target object in the multiple scenario categories, determining the importance degree corresponding to the resource quantity parameter; Wherein, the importance degree corresponding to the resource quantity parameter has a direct proportional relationship with the first resource quantity and an inverse proportional relationship with the second resource quantity.

7. The method according to claim 4, wherein, Determining the importance degree corresponding to the activity parameter includes: Based on a first activity corresponding to the activity parameter of the target object in the target scenario and a second activity of the target object in the multiple scenario categories; Wherein, the importance degree corresponding to the activity parameter has a direct proportional relationship with the first activity and an inverse proportional relationship with the second activity; The first activity level has an inverse relationship with the time span between the operation time of the target object on the resources in the target scenario and the current time, and has a direct relationship with the amount of resources of the target object in the target scenario; The second activity level has a direct relationship with the time span between the operation time of the target object on the resources in the multiple scenario categories and the current time, and has an inverse relationship with the amount of resources of the target object in the multiple scenario categories.

8. The method according to any one of claims 1-7, wherein Determining the comprehensive influence of the target resource on the target object in the multiple scenario categories based on the first interest influence and the second interest influence includes: Based on the first interest influence and the second interest influence, determining an intermediate influence value of the target resource; the intermediate influence value has a direct relationship with both the first interest influence and the second interest influence; Searching for the intermediate influence value of the target resource in other scenarios except the target scenario in the multiple scenario categories; In the case where the intermediate influence value of the target resource in the other scenarios is found, based on the intermediate influence value of the target resource in the target scenario and the intermediate influence value of the target resource in the other scenarios, determining the comprehensive influence of the target resource on the target object in the multiple scenario categories.

9. The method according to claim 8, wherein Determining the comprehensive influence of the target resource on the target object in the multiple scenario categories based on the intermediate influence value of the target resource in the target scenario and the intermediate influence value of the target resource in the other scenarios includes: Obtaining the maximum value among the intermediate influence value of the target resource in the target scenario and the intermediate influence value of the target resource in the other scenarios; Based on the total number of scenarios to which the target resource belongs and the maximum value, determining the comprehensive influence.

10. A method for recommending media resources, including: Obtaining a resource recommendation request of a target object; In response to the resource recommendation request of the target object, screening media resources to be recommended for the target object based on the comprehensive influence of multiple resources of the target object in multiple scenario categories; For the target resource among the multiple resources, determining the comprehensive influence corresponding to the target resource based on the method according to any one of claims 1-9; Performing a resource recommendation operation based on the media resources to be recommended.

11. A data processing device applied to media resources, including: A first determination module, configured to determine a target scenario to which a target resource belongs; A second determination module, configured to determine a first interest influence of the target resource on a target object in the target scenario based on preset parameters of the target resource; And determining a second interest influence of the target scenario on the target object in multiple scenario categories; A comprehensive module, configured to determine a comprehensive influence of the target resource on the target object in the multiple scenario categories based on the first interest influence and the second interest influence.

12. A media resource recommendation device, including: An acquisition module, configured to acquire a resource recommendation request of a target object; A response module, configured to, in response to the resource recommendation request of the target object, screen media resources to be recommended for the target object based on the comprehensive influence of a plurality of resources of the target object in a plurality of scenario categories; For a target resource among the plurality of resources, determine the comprehensive influence corresponding to the target resource based on the method according to any one of claims 1-9; An execution module, configured to perform a resource recommendation operation based on the media resources to be recommended.

13. An electronic device, comprising: At least one processor; And A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method according to any one of claims 1-10.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-10.

15. A computer program product, comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-10.

Images