Method and device for providing media data, equipment and medium

Abstract

The invention provides a method, a device, equipment and a medium for providing media data. In one method, value information for a provider of media data for providing media data to a user is obtained. And determining a recommendation index of the media data based on the value information and the interestingness of the user in the media data. And in response to determining that the recommendation index meets the predetermined condition, providing the media data to the user. According to the embodiment of the invention, in the process of recommending the media data, the requirements of the user and the provider of the media data can be comprehensively considered, so that the user experience of the user and the provider is improved.

Description

Technical Field

[0001] Exemplary implementations of the present disclosure relate generally to media data management, and more particularly to methods, apparatuses, devices, and computer-readable storage media for providing media data to users of media applications. Background Art

[0002] With the development of computer technology, various types of media data can be provided at client devices. For example, a client device can receive media data from different data providers from a server device, and each media data can be presented in a display area at the client device. Technical solutions for recommending media data to users have been proposed. However, these technical solutions cannot meet the needs of users and data providers. At this time, it is expected to select users and recommend media data to users in a more flexible and effective way. Summary of the invention

[0003] In a first aspect of the present disclosure, a method for providing media data is provided. In the method, value information of providing media data to a user for a provider of the media data is obtained. Based on the value information and the user's interest in the media data, a recommendation index for the media data is determined. In response to determining that the recommendation index satisfies a predetermined condition, the media data is provided to the user.

[0004] In a second aspect of the present disclosure, a device for providing media data is provided. The device includes: an acquisition module configured to acquire value information of providing media data to a user for a provider of the media data; a determination module configured to determine a recommendation index of the media data based on the value information and the user's interest in the media data; and a provision module configured to provide the media data to the user in response to determining that the recommendation index meets a predetermined condition.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The electronic device includes: at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit, and when the instructions are executed by the at least one processing unit, the electronic device executes the method according to the first aspect of the present disclosure.

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the processor implements the method according to the first aspect of the present disclosure.

[0007] It should be understood that the content described in this content section is not intended to limit the key features or important features of the implementation of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In the following, in conjunction with the accompanying drawings and with reference to the following detailed description, the above and other features, advantages and aspects of various implementations of the present disclosure will become more apparent. In the accompanying drawings, the same or similar figure labels represent the same or similar elements, wherein:

[0009] Figure 1 A block diagram showing an environment for providing media data according to an exemplary implementation of the present disclosure;

[0010] Figure 2 A block diagram for providing media data according to some implementations of the present disclosure is shown;

[0011] Figure 3 A block diagram showing a recommendation model according to some implementations of the present disclosure;

[0012] Figure 4 A block diagram showing a first recommendation model in the recommendation model according to some implementations of the present disclosure is shown;

[0013] Figure 5 A block diagram showing a second recommendation model in the recommendation model according to some implementations of the present disclosure is shown;

[0014] Figure 6 A block diagram illustrating attribution operations according to some implementations of the present disclosure is shown;

[0015] Figure 7 A block diagram illustrating a process for generating reference samples according to some implementations of the present disclosure;

[0016] Figure 8 A flowchart of a method for providing media data according to some implementations of the present disclosure is shown;

[0017] Fig. 9 A block diagram showing an apparatus for providing media data according to some implementations of the present disclosure; and

[0018] Fig.10 A block diagram of a device capable of implementing multiple implementations of the present disclosure is shown. DETAILED DESCRIPTION

[0019] The implementation of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain implementations of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be interpreted as being limited to the implementations described herein. On the contrary, these implementations are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and implementations of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0020] In the description of the implementation methods of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "an implementation" or "the implementation" should be understood as "at least one implementation". The term "some implementations" should be understood as "at least some implementations". The following may also include other explicit and implicit definitions. As used herein, the term "model" can represent the association relationship between various data. For example, the above-mentioned association relationship can be obtained based on a variety of technical solutions currently known and / or to be developed in the future.

[0021] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0022] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0023] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0024] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information is sent to the user in a manner such as a pop-up window, in which the prompt information can be presented in text form. In addition, the pop-up window can also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0025] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0026] The term "in response to" as used herein refers to a state in which a corresponding event occurs or a condition is satisfied. It will be understood that the timing of executing a subsequent action executed in response to the event or condition is not necessarily strongly related to the time when the event occurs or the condition is satisfied. For example, in some cases, the subsequent action may be executed immediately when the event occurs or the condition is satisfied; while in other cases, the subsequent action may be executed some time after the event occurs or the condition is satisfied.

[0027] Example Environment

[0028] With the development of computer technology, it is now possible to provide various types of media data at a client device. For example, a client device can receive media data from different data providers from a server device and present each media data in a display area at the client device. Figure 1 Describes an application environment according to an example implementation of the present disclosure. Figure 1 A block diagram 100 of an environment for providing media data according to an exemplary implementation of the present disclosure is shown. Figure 1 As shown, a media providing application may be executed at the client device 120 , and media data may be presented to the user 170 in a page 112 of the media providing application.

[0029] Specifically, the client device 110 may receive one or more media data from the server device 120 via the network 130. According to an example implementation of the present disclosure, the media data may come from a repository 140, and the repository 140 may include media data from one or more providers. For example, the repository 140 may include one or more media data 150 from a provider 152, etc., ..., the repository 140 may include one or more media data 160 from a provider 162, etc.

[0030] Generally speaking, the provider 152 has certain expectations for the users who browse the media data 150 provided by the provider 152. For example, the provider 152 may hope that the media data 150 will have an impact on the user 170, such as hoping that the user 170 can obtain more information and / or knowledge through the media data 150, or hoping that the user 170 can interact with the media data 150, etc., so as to achieve the purpose of data promotion and dissemination.

[0031] Technical solutions for recommending media data to users have been proposed. However, these technical solutions cannot meet the needs of users and data providers. For example, some recommendation models can recommend media data to specific users according to the expectations of the provider, however, these users may not like the recommended media data. In particular, a large amount of recommended data may cause interference to users, thereby reducing user experience. For another example, some recommendation models can select and recommend media data from a repository according to the user's preferences (e.g., user subscriptions, preferences, etc.). In this case, the user can only receive the media data of interest and may miss a lot of media data of potential interest. At this point, it is desired to recommend media data in a more flexible and effective manner.

[0032] Provides a summary of media data

[0033] In order to at least partially solve the deficiencies in the prior art, according to an exemplary implementation of the present disclosure, a method for providing media data is proposed. Figure 2 An overview of an exemplary implementation of the present disclosure is described. Figure 2 A block diagram 200 for providing media data according to some implementations of the present disclosure is shown. Figure 2 As shown, in the process of recommending media data 150 to user 170, value information 210 of providing the media data 150 to user 170 for provider 152 may be obtained. For example, value information 210 may indicate the degree of match between the result of providing the media data to the user and the expectation of the provider, where the higher the match, the higher the value, and the lower the match, the lower the value.

[0034] Further, the interest 220 of the user 170 in the media data 150 may be obtained, and based on the value information 210 and the interest 220 of the user in the media data 150, a recommendation index 230 for providing the media data 150 to the user 170 may be determined. Here, the recommendation index 230 may comprehensively reflect the degree of match between the media data 150 and the expectations of the provider 152 and the interests of the user 170. According to an example implementation of the present disclosure, if it is determined that the recommendation index 230 can meet a predetermined condition (e.g., higher than a certain threshold, etc.), the media data 150 may be provided to the user 170.

[0035] By utilizing the example implementation of the present disclosure, in the process of recommending media data, the needs of both the user 170 and the provider 152 can be comprehensively considered, thereby improving the user experience of both the user 170 and the provider 152 .

[0036] Detailed process of providing media data

[0037] Having described an overview of an example implementation according to the present disclosure, in the following, see Figure 3 More details of an example implementation according to the present disclosure are described. Figure 3 A block diagram 300 of a recommendation model according to some implementations of the present disclosure is shown. Figure 3 As shown, the recommendation model 330 may include a first recommendation model 310 and a second recommendation model 320. Here, the first recommendation model 310 may describe the association relationship between the user, the media data, and the value information. For example, the first recommendation model 310 may be determined based on the value information of the provider of the media data 342 for recommending the media data 342 to the user 340. In other words, the first recommendation model 310 is more inclined to recommend media data with higher value to the user, and for given media data, the first recommendation model 310 may find a target user who can generate higher value for the media data.

[0038] According to an example implementation of the present disclosure, media data may be of multiple types, for example, including but not limited to text data, image data, audio data, video data, and the like. Here, the second recommendation model 320 may describe the association relationship between the user, the media data, and the interest level. For example, the second recommendation model 320 may be determined based on the interest level 322 of the user 340 in the media data 342. In other words, the second recommendation model 320 is more inclined to recommend to the user the media data that the user is more interested in, and for given media data, the second recommendation model 320 may find a target user who is more interested in the media data. Further, the recommendation index 350 may be determined based on the value information 312 and the interest level 322.

[0039] By using the example implementation of the present disclosure, the experience of both the provider and the user can be comprehensively considered, so that the recommended media data can meet the expectations of the user and the provider as much as possible. In this way, in addition to recommending media data based on value information and interest respectively, an association relationship can be established between the two recommendation methods, so that when selecting target users for a certain media data, the media data can be preferentially recommended to users who may be potentially interested in the media data if it meets the expectations of the provider.

[0040] According to an example implementation of the present disclosure, the first recommendation model 310 may be used to determine the value information of providing media data to a user for a provider of the media data. The first recommendation model 310 herein may be a pre-trained model. Specifically, the first recommendation model 310 may describe the association relationship between the first reference media data, the first reference user, and the reference value information, and the reference value information may represent the value of providing the first reference media data to the first reference user for a reference provider of the first reference media data.

[0041] See also Figure 4 Describing more details about the first recommendation model 310, the Figure 4 A block diagram 400 of a first recommendation model 310 in a recommendation model 330 according to some implementations of the present disclosure is shown. Figure 4 As shown, the first recommendation model 310 may be trained using reference samples.

[0042] Here, the media data 420 is, for example, referred to as the first reference media data, and can be represented by features related to the media data ID and / or various attributes of the media data. The user 410 is, for example, referred to as the first reference user, and can be represented by features related to the user's relevant attributes. The value information 312 represents the value of providing the media data 420 to the user 410 for the provider of the media data 420. For example, a real number in the range of [0,1], [0,100] or other ranges can be used to represent the value information. Here, the value information can have a pre-marked numerical value, the larger the numerical value, the higher the value, and the smaller the numerical value, the lower the value. Alternatively and / or additionally, other formats can be used to represent the value information.

[0043] A large number of reference samples can be obtained based on various methods that are known in the past and / or will be developed in the future, and these reference samples can be used to continuously optimize the first recommendation model 310 in a manner that makes the predicted value of the value information output by the first recommendation model 310 consistent with the labeled value. Here, the first recommendation model 310 can have multiple functions. When user and media data are input, the model can output value information; when a user is input, media data that can generate value information within a predetermined range can be output; when media data is input, target users that can generate value information within a predetermined range can be output. Using the example implementation of the present disclosure, the knowledge accumulated by the existing first recommendation model 310 can be fully utilized to simplify the operational complexity of the recommendation process, thereby improving the efficiency of the recommendation process.

[0044] According to an example implementation of the present disclosure, the user's interest in media data may be determined using the second recommendation model 320. Here, the second recommendation model 320 may describe the association relationship between the second reference media data, the second reference user, and the reference interest, and the reference interest may represent the second reference user's interest in the second reference media data.

[0045] See also Figure 5 Describing more details about the second recommendation model 320, the Figure 5 A block diagram 500 is shown of the second recommendation model 320 in the recommendation model 330 according to some implementations of the present disclosure. Figure 5 As shown, the second recommendation model 320 may be trained using reference samples.

[0046] Here, the media data 520 is, for example, referred to as the second reference media data, and can be represented by features related to the media data ID and / or various attributes of the media data. The user 510 is, for example, referred to as the second reference user, and can be represented by features related to the user's relevant attributes. The interest level 322 can represent the user's 510 interest in the media data 520. For example, a real number in [0,1], [0,100] or other ranges can be used to represent the interest level. Here, the interest level can have a pre-marked numerical value, and the larger the numerical value, the more interested the user is in the media data, otherwise the smaller the numerical value, the less interested the user is in the media data. Alternatively and / or additionally, other formats can be used to represent the interest level.

[0047] A large number of reference samples can be obtained based on various methods known in the past and / or to be developed in the future, and these reference samples can be used to continuously optimize the second recommendation model 320 in a manner that makes the predicted value of the interest output by the second recommendation model 320 consistent with the labeled value. Here, the second recommendation model 320 can have multiple functions. When a user and media data are input, the model can output the interest; when a user is input, media data that can generate a predetermined range of interest can be output; when media data is input, target users that can generate a predetermined range of interest can be output. Using the example implementation of the present disclosure, the knowledge accumulated by the existing second recommendation model 320 can be fully utilized to simplify the operational complexity of the recommendation process, thereby improving the efficiency of the recommendation process.

[0048] According to an example implementation of the present disclosure, a recommendation index may be determined based on value information and interest. For example, a recommendation index may be determined based on a weighted sum function and / or other functions of value information and interest. Alternatively and / or additionally, a recommendation index may be determined based on a machine learning network. Using an example implementation of the present disclosure, the experience of both the provider and the user may be comprehensively considered, so that the recommended media data can meet the expectations of the user and the provider as much as possible.

[0049] According to an example implementation of the present disclosure, one or more media data may be acquired based on a variety of methods. For example, media data may be acquired based on a variety of recommendation schemes currently available and / or to be developed in the future. Further, for each of the one or more media data acquired, the first recommendation model 310 and / or the second recommendation model 320 may be used to determine a target user for each media data.

[0050] Specifically, for specific media data, the first recommendation model 310 can be used to determine which users to recommend the specific media data to. In this case, when the media data is recommended to these users, higher value information can be obtained. For another example, the second recommendation model 320 can be used to determine which users to recommend the specific media data to. In this case, when the media data is recommended to these users, a higher interest can be obtained. Further, for each user from the two recommendation models, a corresponding recommendation index can be determined.

[0051] According to an example implementation of the present disclosure, a predetermined condition may be set in advance, and the media data may be selected to be recommended to a specific user based on the predetermined condition. For example, the predetermined condition may indicate: recommend the media data to the user corresponding to the highest recommendation index. For another example, the predetermined condition may indicate: recommend the media data to the user corresponding to the recommendation index within a predetermined range, and so on. In this way, the degree of match between the media data and the user may be measured in a quantitative manner, thereby preferentially recommending to the user media data that meets both the user's interest points and the value annotations of the data provider.

[0052] According to an example implementation of the present disclosure, in the process of using the recommendation model, at least any one of the first recommendation model 310 and the second recommendation model 320 may be updated. For ease of description, the updated recommendation model may be referred to as a target recommendation model. Specifically, in the process of updating the target recommendation model, a reference sample for updating the target recommendation model may be generated based on the source of the user (i.e., the method of determining the user), and then the generated reference sample may be used to update the target recommendation model.

[0053] By using the example implementation of the present disclosure, the corresponding attribution method can be determined based on different sources, thereby improving the accuracy of the recommendation model. In this way, it is possible to measure which of the user's previous interactions has the greatest impact on the user's subsequent valuable interactions (e.g., payment, forwarding, watching live broadcasts, etc.), thereby acting in reverse on the model and subsequent recommendations. As a result, higher value can be obtained for the provider, for example, obtaining higher attention and more conversion data, etc. For users, the accuracy of media data delivery can be improved while meeting the value needs of the provider, thereby better meeting the needs of customers.

[0054] In order to better determine the association relationship between users and media data, we can Figure 6 The imputation operation shown is used to generate the reference sample. Figure 6 A block diagram 600 of attribution operations according to some implementations of the present disclosure is shown. Figure 6 As shown, the attribution operation 640 can be divided into three stages. The first stage 610 corresponds to applying the first recommendation model 310 alone to determine the user's scenario, the second stage 620 corresponds to applying the second recommendation model 320 alone to determine the user's scenario, and the third stage 630 corresponds to applying the first recommendation model 310 and the second recommendation model 320 in combination to determine the user's scenario. For the above three stages 610, 620 and 630, reference samples can be generated based on corresponding attribution conditions 612, 622 and 632, respectively.

[0055] According to an example implementation of the present disclosure, in the process of generating reference samples, if it is determined that the user comes from the first recommendation model 310, the reference sample can be generated based on the attribution condition 612. That is, the reference sample can be generated based on the interaction between the user and the media data. Using the example implementation of the present disclosure, multiple samples can be generated in a simple and effective manner, so that the user's subsequent interaction with the media data can further affect the recommendation model, thereby improving the accuracy of the recommendation model.

[0056] Specifically, if it is determined that there is interaction between the user and the media data, a positive reference sample for updating the target recommendation model may be generated. If it is determined that there is no interaction between the user and the media data, a negative reference sample for updating the target recommendation model may be generated.

[0057] This type of attribution condition can be called click-through attribution. From the historical data, the revenue brought by the first stage 610 is much higher than that of the second stage 620 and the third stage 630, so it is necessary to accurately measure the value of the first stage. If the user clicks, then the user's recognition of the recommendation result of the first recommendation model 310 is relatively high. Valuable interactions that occur in the subsequent time can be considered as the revenue brought by the attribution of the first stage. Using the example implementation method of the present disclosure, the accuracy of the recommendation model can be improved.

[0058] According to an example implementation of the present disclosure, the interaction may include multiple types, for example, including but not limited to: a user's click operation on the media data, a user's comment operation on the media data, a user's forwarding operation on the media data, a user's conversion operation on the media data, and the like. In the context of the present disclosure, the conversion operation may be further subdivided. For example, in the case where the media data is software promotion data, the conversion operation may include the user downloading the promoted software via a link in the media data and / or other means. In the case where the media data is movie promotion data, the conversion operation may include the user browsing the relevant movie introduction via a link in the media data and / or other means, or purchasing a movie ticket for the promoted movie, and the like. In the case where the media data is product promotion data, the conversion operation may include the user browsing the information of the promoted product via a link in the media data and / or other means, or purchasing the product, and the like.

[0059] Using the example implementation of the present disclosure, in the process of generating reference samples, if it is determined that the user comes directly from the second recommendation model 320, the reference sample can be generated according to the attribution condition 622. Within the time period specified by the provider, a reference sample for updating the target recommendation model can be generated based on the user's interaction data. Specifically, a positive reference sample for updating the target recommendation model can be generated based on the user's interaction data that matches the provider's needs. Different providers may have different needs. For example, in the case where the media data is software promotion data, the user does not have to click on the media data directly, but when it is detected that the user has browsed other media data related to the software, downloaded other software via other media data, etc., a corresponding positive reference sample can be generated. Similarly, based on the user's interaction data that does not match the provider's needs, a negative reference sample for updating the target recommendation model can be generated.

[0060] By using the example implementation of the present disclosure, a broad attribution method is provided, and for valuable interaction data during the regulation period (that is, interaction data that matches the needs of the provider), corresponding positive reference samples can be generated as long as they help meet the needs of the provider. In this way, the performance of the recommendation model can be further improved.

[0061] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0062] According to an example implementation of the present disclosure, in the process of generating reference samples, if it is determined that the user comes from a combination of the first recommendation model 310 and the second recommendation model 320, the reference sample can be generated according to the attribution condition 632. Specifically, the media data obtained by calling both the first recommendation model 310 and the second recommendation model 320 can be pre-annotated, and a positive reference sample for updating the target recommendation model is generated based on the media data.

[0063] The attribution of the third stage can be called push attribution, and the recommendation value of this part is second only to the first stage. When measuring this part of the data, you can observe whether the user involves the second stage before performing a valuable action. This attribution method is between the first stage attribution and the second stage attribution method. If the user clicks on the pushed media data, the attribution is performed according to the first stage; if the user does not click, the attribution is performed according to the third stage. Figure 7 A block diagram 700 of a process for generating reference samples according to some implementations of the present disclosure is shown. Figure 7 As shown, one or more media data may be acquired in advance, and the method of the present disclosure may be performed for each media data. For example, for media data 150, the recommendation model 330 may be called to determine user data 710 associated with each attribution stage. For example, user data of the first type 712 corresponds to the first recommendation model 310, user data of the second type 714 corresponds to the second recommendation model 320, and user data of the third type 716 corresponds to a combination of the first recommendation model 310 and the second recommendation model 320.

[0064] In the process of the user browsing the media data 150, the user's interaction data 730 can be obtained, and then according to the above reference Figure 6 The three stages described above generate corresponding reference samples 740. Further, the reference samples 740 can be used to update the first recommendation model 310. In this way, when recommending media data from a provider, the needs of both the provider and the user can be comprehensively considered, so that more and more accurate users can be selected, thereby expanding the influence of the media data.

[0065] Alternatively and / or additionally, the second recommendation model 320 may be updated using the reference sample 740. In this way, when recommending media data of interest to the user, it may be further considered whether the media data is helpful in satisfying the needs of a specific provider. In this way, media data that meets the interests of the user and can satisfy the expectations of a specific provider may be recommended on the premise of satisfying the interests of the user.

[0066] According to an exemplary implementation of the present disclosure, the target user associated with the target media data can be determined by using the updated target recommendation model in the first recommendation model 310 and the second recommendation model 320. Further, the target media data can be provided to the target user. At this time, the updated recommendation models can have higher accuracy and performance, thereby improving the efficiency of the recommendation process, and the media data recommended to the target user can meet the respective needs of the user and the provider.

[0067] According to an example implementation of the present disclosure, for a certain media data, after finding a target user suitable for the media data, other users similar to the target user can be found, and the media data can be provided to the other similar users found. For example, similar users can be determined based on the similarity between the users (e.g., the distance between the features of the users, etc.). In this way, the promotion scope of the media data can be further expanded, thereby improving the data dissemination efficiency and making the promotion results more in line with the expectations of the provider.

[0068] By utilizing the exemplary implementation of the present disclosure, in the process of recommending media data, the needs of both users and providers of media data can be comprehensively considered, thereby improving the user experience of both users and providers.

[0069] Example Process

[0070] Figure 8 A flow chart of a method 800 for providing media data according to some implementations of the present disclosure is shown. At box 810, value information of providing media data to a user for a provider of the media data is obtained. At box 820, a recommendation index for the media data is determined based on the value information and the user's interest in the media data. At box 830, it is determined whether the recommendation index meets a predetermined condition. If the determination result is "yes", the method 800 proceeds to box 840. At box 840, the media data is provided to the user.

[0071] According to an example implementation of the present disclosure, obtaining value information includes: determining the value information using a first recommendation model, the first recommendation model describing an association relationship between first reference media data, a first reference user, and reference value information, the reference value information representing the value of providing the first reference media data to the first reference user for a reference provider of the first reference media data.

[0072] According to an example implementation of the present disclosure, determining a recommendation indicator includes: using a second recommendation model to determine a user's interest in media data, the second recommendation model describes an association between second reference media data, a second reference user, and a reference interest, the reference interest representing the second reference user's interest in the second reference media data; and determining a recommendation indicator based on the value information and the interest.

[0073] According to an example implementation of the present disclosure, the user is acquired based on the media data by at least any one of the first recommendation model and the second recommendation model.

[0074] According to an exemplary implementation of the present disclosure, the method 800 further includes: updating a target recommendation model in the first recommendation model and the second recommendation model.

[0075] According to an example implementation of the present disclosure, the method 800 further includes: determining a target user associated with the target media data using the updated target recommendation model in the first recommendation model and the second recommendation model; and providing the target media data to the target user.

[0076] According to an example implementation of the present disclosure, updating the target recommendation model includes: generating a reference sample for updating the target recommendation model based on a source of a user; and updating the target recommendation model using the reference sample.

[0077] According to an example implementation of the present disclosure, generating reference samples includes: in response to determining that a user is from a first recommendation model, generating reference samples based on at least any one of the following: in response to determining that there is an interaction between the user and the media data, generating a positive reference sample for updating a target recommendation model based on the media data; in response to determining that there is no interaction between the user and the media data, generating a negative reference sample for updating the target recommendation model based on the media data.

[0078] According to an example implementation of the present disclosure, the interaction includes at least any one of the following: a click operation of a user on the media data; a comment operation of a user on the media data; a forwarding operation of a user on the media data; a conversion operation of a user on the media data.

[0079] According to an example implementation of the present disclosure, generating reference samples includes: in response to determining that the user comes directly from the second recommendation model, generating reference samples based on at least any one of the following: generating positive reference samples for updating the target recommendation model based on the user's interaction data that matches the provider's requirements; and generating negative reference samples for updating the target recommendation model based on the user's interaction data that does not match the provider's requirements.

[0080] According to an example implementation of the present disclosure, generating a reference sample includes: in response to determining that the user comes from a combination of a first recommendation model and a second recommendation model, generating a positive reference sample for updating a target recommendation model.

[0081] According to an exemplary implementation of the present disclosure, the method 800 further includes: acquiring other users similar to the user; and providing media data to the other users.

[0082] Example devices and equipment

[0083] Fig. 9 A block diagram of an apparatus 900 for providing media data according to some implementations of the present disclosure is shown. The apparatus 900 includes: an acquisition module 910 configured to acquire value information of providing media data to a user for a provider of the media data; a determination module 920 configured to determine a recommendation index of the media data based on the value information and the user's interest in the media data; and a provision module 930 configured to provide the media data to the user in response to determining that the recommendation index meets a predetermined condition.

[0084] According to an example implementation of the present disclosure, the acquisition module includes: a value determination module, which is configured for use in the module, and is configured to determine value information using a first recommendation model, the first recommendation model describes an association relationship between first reference media data, a first reference user, and reference value information, and the reference value information represents the value of providing the first reference media data to the first reference user for a reference provider of the first reference media data.

[0085] According to an example implementation of the present disclosure, the determination module includes: an interest determination module, configured to determine the user's interest in media data using a second recommendation model, the second recommendation model describing an association relationship between second reference media data, a second reference user, and a reference interest, the reference interest representing the second reference user's interest in the second reference media data; and a recommendation indicator determination module, configured to determine a recommendation indicator based on value information and interest.

[0086] According to an example implementation of the present disclosure, the user is acquired based on the media data by at least any one of the first recommendation model and the second recommendation model.

[0087] According to an exemplary implementation of the present disclosure, the apparatus further includes: an updating module configured to update a target recommendation model in the first recommendation model and the second recommendation model.

[0088] According to an example implementation of the present disclosure, the device further includes: a user determination module, configured to determine a target user associated with the target media data using an updated target recommendation model in the first recommendation model and the second recommendation model; and a data providing module, configured to provide the target media data to the target user.

[0089] According to an example implementation of the present disclosure, the updating module includes: a generating module configured to generate reference samples for updating the target recommendation model based on the user's source; and a model updating module configured to update the target recommendation model using the reference samples.

[0090] According to an example implementation of the present disclosure, a generation module includes: a first generation module, configured to generate a reference sample based on at least one of the following in response to determining that a user comes from a first recommendation model: generating a positive reference sample for updating a target recommendation model based on the media data in response to determining that there is an interaction between the user and the media data; generating a negative reference sample for updating the target recommendation model based on the media data in response to determining that there is no interaction between the user and the media data.

[0091] According to an example implementation of the present disclosure, the interaction includes at least any one of the following: a click operation of a user on the media data; a comment operation of a user on the media data; a forwarding operation of a user on the media data; a conversion operation of a user on the media data.

[0092] According to an example implementation of the present disclosure, the generation module includes: a second generation module, configured to generate a reference sample based on at least any one of the following in response to determining that the user comes directly from the second recommendation model: generating a positive reference sample for updating the target recommendation model based on the user's interaction data that matches the provider's requirements; and generating a negative reference sample for updating the target recommendation model based on the user's interaction data that does not match the provider's requirements.

[0093] According to an example implementation of the present disclosure, the generation module includes: a third generation module configured to generate a positive reference sample for updating the target recommendation model in response to determining that the user comes from a combination of the first recommendation model and the second recommendation model.

[0094] According to an exemplary implementation of the present disclosure, the apparatus further includes: a similar user acquisition module configured to acquire other users similar to the user; and a data providing module configured to provide media data to other users.

[0095] Fig.10 1 shows a block diagram of a device 1000 capable of implementing multiple implementations of the present disclosure. It should be understood that Fig.10 The computing device 1000 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the implementations described herein. Fig.10 The computing device 1000 shown may be used to implement the methods described above.

[0096] like Fig.10 As shown, computing device 1000 is in the form of a general-purpose computing device. Components of computing device 1000 may include, but are not limited to, one or more processors or processing units 1010, memory 1020, storage device 1030, one or more communication units 1040, one or more input devices 1050, and one or more output devices 1060. Processing unit 1010 may be an actual or virtual processor and is capable of performing various processes according to a program stored in memory 1020. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to increase the parallel processing capabilities of computing device 1000.

[0097] The computing device 1000 typically includes a plurality of computer storage media. Such media may be any available media accessible to the computing device 1000, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 1020 may be a volatile memory (e.g., registers, caches, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 1030 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data (e.g., training data for training) and may be accessed within the computing device 1000.

[0098] The computing device 1000 may further include additional removable / non-removable, volatile / non-volatile storage media. Fig.10As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. Memory 1020 may include a computer program product 1025 having one or more program modules that are configured to perform various methods or actions of various implementations of the present disclosure.

[0099] The communication unit 1040 enables communication with other computing devices via a communication medium. Additionally, the functions of the components of the computing device 1000 can be implemented in a single computing cluster or multiple computing machines that can communicate via a communication connection. Therefore, the computing device 1000 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0100] Input device 1050 may be one or more input devices, such as a mouse, keyboard, tracking ball, etc. Output device 1060 may be one or more output devices, such as a display, a speaker, a printer, etc. Computing device 1000 may also communicate with one or more external devices (not shown) through communication unit 1040 as needed, such as storage devices, display devices, etc., communicate with one or more devices that allow a user to interact with computing device 1000, or communicate with any device that allows computing device 1000 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0101] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, the computer program product is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is provided, on which a computer program is stored, and when the program is executed by a processor, the method described above is implemented.

[0102] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0103] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0104] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0105] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0106] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A method for providing media data, comprising: Acquire value information of providing the media data to the user for the provider of the media data; Determining a recommendation index for the media data based on the value information and the user's interest in the media data; as well as In response to determining that the recommendation indicator satisfies a predetermined condition, the media data is provided to the user.

2. The method according to claim 1, wherein obtaining the value information comprises: The value information is determined using a first recommendation model, which describes the association between first reference media data, a first reference user, and reference value information, wherein the reference value information represents the value of providing the first reference media data to the first reference user for a reference provider of the first reference media data.

3. The method according to claim 2, wherein determining the recommendation indicator comprises: Determining the user's interest in the media data using a second recommendation model, wherein the second recommendation model describes an association relationship between second reference media data, a second reference user, and a reference interest, wherein the reference interest represents the second reference user's interest in the second reference media data; as well as The recommendation index is determined based on the value information and the interest level. 4 . The method according to claim 3 , wherein the user is obtained according to the media data by at least any one of the first recommendation model and the second recommendation model.

5. The method according to claim 3, further comprising: Update the target recommendation model in the first recommendation model and the second recommendation model.

6. The method according to claim 5, further comprising: Determine a target user associated with target media data by using the updated target recommendation model in the first recommendation model and the second recommendation model; as well as The target media data is provided to the target user.

7. The method according to claim 5, wherein updating the target recommendation model comprises: Based on the source of the user, generating a reference sample for updating the target recommendation model; as well as The target recommendation model is updated using the reference sample.

8. The method of claim 7, wherein generating the reference sample comprises: In response to determining that the user comes from the first recommendation model, generating the reference sample based on at least any one of the following: In response to determining that there is an interaction between the user and the media data, generating a positive reference sample for updating the target recommendation model based on the media data; In response to determining that there is no interaction between the user and the media data, a negative reference sample for updating the target recommendation model is generated based on the media data.

9. The method according to claim 8, wherein the interaction comprises at least any one of the following: a click operation of the user on the media data; The user's comment operation on the media data; The user's forwarding operation on the media data; The user performs a conversion operation on the media data.

10. The method according to claim 7, wherein generating the reference sample comprises: In response to determining that the user comes directly from the second recommendation model, generating the reference sample based on at least any one of the following: Based on the user's interaction data that matches the provider's needs, generating positive reference samples for updating the target recommendation model; as well as Based on the interaction data of the user that does not match the requirements of the provider, negative reference samples are generated for updating the target recommendation model.

11. The method of claim 7, wherein generating the reference sample comprises: In response to determining that the user comes from a combination of the first recommendation model and the second recommendation model, a positive reference sample for updating the target recommendation model is generated.

12. The method according to claim 1, further comprising: Obtain other users similar to the user; as well as The media data is provided to the other users.

13. An apparatus for providing media data, comprising: An acquisition module, configured to acquire value information of providing the media data to the user for a provider of the media data; A determination module, configured to determine a recommendation index for the media data based on the value information and the user's interest in the media data; as well as A providing module is configured to provide the media data to the user in response to determining that the recommendation indicator meets a predetermined condition.

14. An electronic device, comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 12 when executed by the at least one processing unit.

15. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, causes the processor to implement the method according to any one of claims 1 to 12.

Images