Material feeding method and device, computer program product and electronic device

Abstract

The present disclosure relates to the technical field of computers, and relates to a material putting method and device, a computer program product and an electronic device. The material putting method comprises: collecting user feedback features of put material, and determining first reward data of the put material based on the user feedback features, the first reward data reflecting the putting effect of the put material, the put material being generated based on at least one material segment obtained from a material library; performing material attribution processing according to second reward data to determine second reward data of the material segment; updating a material effect score of the material segment according to the second reward data and historical material indicators of the material segment, and generating target material from the material library based on the updated material effect score to generate target material and put it. The present disclosure can improve the quality and efficiency of put material.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more specifically, to a method for delivering materials, a device for delivering materials, a computer program product, and an electronic device. Background Technology

[0002] With the development of computer and internet technology, online content delivery to various platforms offers the advantages of immediacy and wide coverage. For example, videos, audio, text, images, and combinations of various types of content that users are interested in can be delivered to web pages and applications. However, delivering content involves steps such as content selection, editing, and optimization. If it fails to capture user interests and respond to changes in user needs, it can negatively impact the quality and efficiency of content delivery.

[0003] It should be noted that the information in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0004] The purpose of this disclosure is to provide a method and apparatus for delivering content, a computer program product, and an electronic device, thereby improving the quality and efficiency of delivering content to at least a certain extent.

[0005] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part by practice of this disclosure.

[0006] According to one aspect of this disclosure, a method for delivering content is provided, comprising: collecting user feedback features of a delivered video, and determining first reward data for the delivered content based on the user feedback features, the first reward data reflecting the delivery effect of the delivered content, the delivered content being generated based on at least one content segment obtained from a content library; performing content attribution processing based on the first reward data to determine second reward data for the content segment; updating the content effect score of the content segment based on the second reward data and historical content metrics of the content segment, and generating target content based on the updated content effect score by obtaining target content segments from the content library and delivering it.

[0007] In one exemplary embodiment of this disclosure, determining the first reward data of the deployed materials based on the user feedback features includes: obtaining weight information corresponding to the user feedback features, the weight information reflecting the importance of the user feedback features in the first reward data; and fusing the user feedback features corresponding to the deployed materials based on the weight information to obtain the first reward data.

[0008] In one exemplary embodiment of this disclosure, the step of performing material attribution processing based on the first reward data to determine the second reward data of the material segment includes: determining the material weight corresponding to the material segment based on the segment position of the material segment in the deployed material; and determining the second reward data of the material segment based on the material weight and the first reward data.

[0009] In one exemplary embodiment of this disclosure, determining the material weight corresponding to the material segment based on the segment position of the material segment in the deployed material includes: determining the material weight corresponding to the material segment based on the segment position according to a preset weight reduction model; wherein, the weight reduction model is used to characterize the change of material weight with segment position.

[0010] In one exemplary embodiment of this disclosure, updating the material effect score of the material segment based on the second reward data and the historical material index of the material segment includes: obtaining the current material reward corresponding to the material segment; obtaining the reward difference value between the current material reward and the second reward data; determining a reward correction parameter based on the historical material index; and updating the material effect score of the material segment based on the reward correction parameter, the reward difference value, and the current material reward.

[0011] In one exemplary embodiment of this disclosure, the historical material metrics include at least one of the following: the number of times the material segment was selected, the number of times the material was completed, and the number of times the material was interacted with; wherein, the number of times the material segment was selected indicates the number of times the material segment was used to generate historical delivered materials, the number of times the material segment was completed indicates the number of times the historical delivered materials played the material segment completely, and the number of times the material was interacted with indicates the total number of interactions that occurred during the playback of the material segment.

[0012] In one exemplary embodiment of this disclosure, the step of obtaining target material fragments from the material library based on the updated material effect score, generating target material, and deploying the material includes: obtaining a material exploration probability, wherein the material exploration probability is used to indicate the proportion of random material in the target material fragment; obtaining random material from the material library according to the material exploration probability, and obtaining generated material from the material library based on the updated material effect score, so as to determine the target material fragment and generate target material for deployment based on the random material and the generated material.

[0013] In one exemplary embodiment of this disclosure, the material fragments in the material library each have their own corresponding category tags; the process of obtaining target material fragments from the material library based on the updated material effect score, generating target material, and delivering it includes: obtaining target material fragments from the material library based on the updated material effect score to generate multiple materials to be delivered; for each material to be delivered, evaluating the material compatibility of the material to be delivered based on the category tags of the target material fragments contained in the material to be delivered; and determining the target material from the multiple materials to be delivered based on the evaluation results of the material compatibility.

[0014] In one exemplary embodiment of this disclosure, the step of obtaining target material fragments from the material library based on the updated material effect score, generating target materials, and deploying them includes: obtaining a material generation template; and generating multiple target materials from the target material fragments based on the material generation template and deploying them.

[0015] In one exemplary embodiment of this disclosure, the step of collecting user feedback features of the deployed materials includes: obtaining the target user category for the material deployment; and obtaining user feedback features of the deployed materials corresponding to the target user category based on the target user category.

[0016] According to one aspect of this disclosure, a material delivery device is provided, comprising: a feature processing module, configured to collect user feedback features of delivered materials, and determine first reward data of the delivered materials based on the user feedback features, the first reward data reflecting the delivery effect of the delivered materials, the delivered materials being generated based on at least one material fragment obtained from a material library; a reward attribution module, configured to perform material attribution processing based on the first reward data to determine second reward data of the material fragment; and a material generation module, configured to update the material effect score of the material fragment based on the second reward data and historical material indicators of the material fragment, and generate target materials based on the updated material effect score obtained from the material library and deliver them.

[0017] According to one aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements any of the above methods.

[0018] According to one aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any of the above methods by executing the executable instructions.

[0019] The exemplary embodiment of this disclosure discloses a method for delivering content, which involves collecting user feedback features of delivered content and determining first reward data for the delivered content based on these features. The first reward data reflects the playback effect of the delivered content, which is generated from content segments obtained from a content library. Content attribution processing is performed based on the first reward data to determine second reward data for the content segments. The content effect score of the content segments is updated based on the second reward data and historical content metrics of the content segments. Based on the updated content effect score, target content is generated from target content segments obtained from the content library and then delivered. On one hand, by collecting user feedback features of delivered content, the method can evaluate the content delivery effect and attribute the effect to content segments, thereby updating the content effect scores of content segments in the content library to control subsequent content selection and generation of delivered content. This process, driven by user feedback features, improves the quality of delivered content, ensuring it meets the actual interests and needs of different user groups and increasing the efficiency of content delivery. On the other hand, the process continuously optimizes the quality of the generated target material segments based on user feedback through a cyclical execution process of generating materials, delivering materials, collecting information, evaluating materials, and optimizing materials. This reduces the complexity and time cost of manual intervention and improves the efficiency of material delivery.

[0020] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0021] The above and other objects, features, and advantages of this disclosure will become readily apparent from the following detailed description of exemplary embodiments, taken in conjunction with the accompanying drawings. Several embodiments of this disclosure are illustrated in the drawings by way of example and not limitation.

[0022] Figure 1 An application environment according to an exemplary embodiment of this disclosure is shown.

[0023] Figure 2 A flowchart of a material delivery method according to an exemplary embodiment of the present disclosure is shown.

[0024] Figure 3 A flowchart illustrating an implementation of determining first reward data according to an exemplary embodiment of the present disclosure is shown.

[0025] Figure 4 A flowchart illustrating an implementation of determining second reward data according to an exemplary embodiment of this disclosure is shown.

[0026] Figure 5 A flowchart illustrating an implementation of updating the material effect score of a material segment according to an exemplary embodiment of the present disclosure is shown.

[0027] Figure 6 A flowchart of a policy-based material selection method according to an exemplary embodiment of the present disclosure is shown.

[0028] Figure 7 A schematic diagram of the composition of a material delivery apparatus according to an exemplary embodiment of the present disclosure is shown.

[0029] Figure 8 A block diagram of an electronic device according to an exemplary embodiment of the present disclosure is shown.

[0030] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed Implementation

[0031] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and therefore their detailed description will be omitted.

[0032] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced without one or more of the specific details described, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known structures, methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0033] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, or in one or more software-hardened modules, or in different network and / or processor devices and / or microcontroller devices.

[0034] Currently, the preparation of campaign materials relies on manual decisions regarding material selection, editing optimization, and effect evaluation. However, manually generating campaign materials is inefficient, fails to accurately capture user interests and market demands, and leaves the effectiveness of the materials unknown before deployment, resulting in low efficiency and poor campaign performance.

[0035] Based on this, an exemplary embodiment of this disclosure provides a method for delivering content, which improves the efficiency and quality of content delivery by collecting user feedback features of delivered content and using them to control the selection of content segments. It should be noted that the content delivery method of the exemplary embodiment of this disclosure can be applied to various content delivery scenarios, such as delivering videos, audio, images, text, or combinations of various content segments (e.g., audio + video) on applications or web pages. The exemplary embodiment of this disclosure does not specifically limit the application field of the content delivery method. The exemplary embodiment of this disclosure uses video as an example for illustration.

[0036] The exemplary embodiments of this disclosure provide a material delivery method that can be applied to, for example, Figure 1 The application environment shown is illustrated. Terminal 101 communicates with server 102 via a network. A data storage system can store the data that server 102 needs to process. The data storage system can be integrated onto server 102, or it can be located in the cloud or on another network server.

[0037] In one exemplary embodiment, the material delivery method provided by the exemplary embodiment of this disclosure can be executed by server 102, and the corresponding material delivery device is disposed in server 102. Correspondingly, in this method of execution by server 102, server 102 can start executing the steps in the technical solution of the exemplary embodiment of this disclosure in response to a triggering command, wherein the triggering command can be sent by a terminal used by a user, or can be triggered locally by the server in response to some automated events.

[0038] Server 102 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. Server 102 can execute background tasks.

[0039] Furthermore, in another exemplary embodiment, terminal 101 may also have similar functions to server 102, thereby performing the material delivery method provided by the exemplary embodiments of this disclosure.

[0040] The terminal 101 can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, IoT device, or portable wearable device. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. The terminal 101 can also be referred to as a mobile terminal, terminal device, mobile device, etc. The exemplary embodiments of this disclosure do not limit the type of terminal 101.

[0041] Furthermore, the technical solutions of the exemplary embodiments of this disclosure can also be executed collaboratively by terminal 101 and server 102. In this method of collaborative execution by terminal 101 and server 102, some steps in the technical solutions provided by the exemplary embodiments of this disclosure are executed by terminal 101, while other steps are executed by server 102. It should be noted that in this method of collaborative execution by terminal 101 and server 102, the steps executed by terminal 101 and server 102 respectively can be dynamically adjusted according to the actual situation, and no special restrictions are imposed on this.

[0042] The terminal 101 and the server 102 can be connected directly or indirectly via wireless communication, and the exemplary embodiments of this disclosure are not particularly limited herein.

[0043] It should be noted that the information (including but not limited to user input information, such as information entered by the user into an input box) and data (including but not limited to data used for analysis, stored data, and displayed data, such as user feedback characteristics of deployed materials, historical material metrics of material clips, and user categories) involved in the embodiments of this disclosure are all authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with relevant laws, regulations, and standards. For example, the user feedback characteristics of deployed materials, historical material metrics of material clips, and user categories involved in the embodiments of this disclosure were all obtained under full authorization.

[0044] In an exemplary embodiment of this disclosure, a method for delivering content is provided, with reference to... Figure 2 The diagram shown is a flowchart of a media delivery method according to an exemplary embodiment of this disclosure. The media delivery method includes steps S210 to S230, as detailed below:

[0045] In step S210, user feedback features of the deployed materials are collected, and the first reward data of the deployed materials is determined based on the user feedback features. The first reward data reflects the deployment effect of the deployed materials, which are generated based on material fragments obtained from the material library.

[0046] In the exemplary embodiments of this disclosure, "delivered content" refers to content that has already been delivered to the target platform, which can be a social media platform or other platform capable of delivering content. Delivering content to the target platform allows for the acquisition of user feedback characteristics of the delivered content. These user feedback characteristics are indicators reflecting the performance of the content, including impressions, plays, completion rate, bounce rate, interaction rate (such as the number of likes, comments, and shares), viewing duration, and member views. Based on these user feedback characteristics, it is possible to understand users' emotional reactions and interactive behaviors towards the delivered content. Specifically, impressions refer to the number of times the delivered content is displayed, plays refer to the number of times the delivered content is clicked to play, completion rate refers to the proportion of users who watch the delivered content in its entirety, and bounce rate refers to the proportion of users who leave while watching the content (such as watching a video). The exemplary embodiments of this disclosure can collect the aforementioned user feedback characteristics in real time through deep integration of the data collection module with the target platform's interface, without limitation.

[0047] The media library stores media clips. Each time media is generated, a media clip is retrieved from the library. The quality of the selected media clips affects the playback effect of the generated media to some extent. The first reward data reflects the performance of the deployed media; a larger first reward data indicates a better playback effect. The first reward data can be determined by combining multiple user feedback features of the deployed media, so that the first reward data can comprehensively reflect the overall performance of the deployed media across multiple feature dimensions. It should be understood that an audio clip, a video clip (without audio), a video clip (with audio), or even a text clip and an image clip can all be used as media clips; no special limitations are made. For example, a video can be generated as the target media for deployment by selecting a piece of music, some images, and a piece of text. This embodiment of the disclosure does not impose special limitations on the type of target media or the specific types of media clips contained within the target media.

[0048] It should be understood that, for audio and video, "playback" means broadcasting audio or video through radio or television (or via the internet) for users to watch or listen to. For images or text, it may refer to providing a format for browsing images or text. This will not be explained again later.

[0049] In step S220, material attribution processing is performed based on the first reward data to determine the second reward data for the material fragment.

[0050] In an exemplary embodiment of this disclosure, material attribution processing refers to allocating the first reward data corresponding to the delivered materials to each material segment to obtain the second reward data of the material segment, that is, the degree of contribution of the material segment to the performance of the delivered materials.

[0051] In particular, considering that users may leave the video at any time during the viewing process, the earlier the video clip is displayed, the greater its contribution to the video's performance. Therefore, video clip attribution can be performed based on the position of the video clip within the already played video clips.

[0052] In step S230, the material effect score of the material segment is updated based on the first reward data and the historical material index of the material segment, and the target material segment is generated from the material library based on the updated material effect score and then deployed.

[0053] In the exemplary embodiments of this disclosure, the historical material metrics of a material segment refer to performance information reflecting the material segment when generating historical material, including at least one of the following: the number of times the material segment was selected, the number of times the material segment was completed, and the number of times the material segment was interacted. Specifically, the number of times the material segment was selected indicates the number of times it was used to generate historically delivered material; the number of times the material segment was completed indicates the number of times the historically delivered material segment was played in its entirety; and the number of times the material segment was interacted indicates the total number of interactions that occurred during the playback of the historically delivered material segment.

[0054] The clip's performance rating reflects the clip's playback effect. A higher performance rating indicates that users have a stronger interest in the clip's content. Consequently, a higher performance rating will increase the probability that the clip will be selected when generating future clips.

[0055] For example, after obtaining the second reward data and historical metrics for each deployed material, the material performance score of the material clip can be updated to control the material selection when generating the next video. When generating a video from target material clips based on the updated performance score, the number of videos generated each time can be flexibly set according to actual needs, without any limit.

[0056] It should be noted that the exemplary embodiments of this disclosure repeatedly execute steps S210 to S230 above, continuously updating the material effect score of the material segments based on user feedback on the deployed materials, so as to optimize the quality of the material segments generated for subsequent materials and improve the quality and efficiency of material deployment.

[0057] The exemplary embodiment of the present disclosure of the material delivery method, on the one hand, can evaluate the delivery effect of materials by collecting user feedback features of the delivered materials, and attribute the delivery effect to material segments. This allows for updating the material effect scores of material segments in the material library to control subsequent material selection and generation of delivery materials. This process, driven by user feedback features, improves the quality of delivery materials, ensuring they align with users' actual interests and needs, and increasing delivery efficiency. On the other hand, the process, through a cyclical execution flow of material generation, delivery, information collection, material evaluation, and material optimization, continuously optimizes the quality of the generated target material segments based on user feedback, reducing the complexity and time cost of manual intervention and improving delivery efficiency.

[0058] In one exemplary embodiment, an implementation method for determining first reward data is provided. For example... Figure 3 As shown, the first reward data for determining the deployed creative materials based on user feedback characteristics may include:

[0059] Step S310: Obtain the weight information corresponding to the user feedback features. The weight information reflects the importance of the user feedback features in the first reward data. The weight information corresponding to the user feedback features can be set according to the actual material delivery task, and there are no specific restrictions on this.

[0060] Step S320: Based on the weight information, the user feedback features corresponding to the deployed materials are fused to obtain the first reward data.

[0061] The collected user feedback features can be preprocessed, including but not limited to data cleaning, standardization, and normalization to remove outliers, in order to generate high-quality indicator data for analysis. Specifically, user feedback features corresponding to the deployed materials can be weighted and fused based on weight information to obtain the first reward data.

[0062] For example, taking video as the material already deployed, and using user feedback characteristics including play count, completion rate, and interaction rate as examples, the first reward data can be obtained through the following formula:

[0063] R t =α×(V) t / V max )+β×C t +γ×E t (1)

[0064] Where α, β, and γ are the weight information corresponding to each user feedback feature, V t C represents the number of views for the already delivered video (taking the t-th delivered video as an example). t E represents the completion rate of the videos already delivered. tV represents the interaction rate. max The maximum number of views among all videos that have been played is used for data normalization. Of course, other metrics can also be selected for data normalization based on the user feedback characteristics on which the first reward data depends.

[0065] It should be noted that the first reward data can be obtained using formula (1) for other types of materials that have already been deployed, which will not be elaborated here.

[0066] By integrating user feedback features corresponding to the deployed creative materials to obtain the first reward data, the performance of the deployed creative materials can be comprehensively evaluated, providing an accurate data foundation for determining the second reward data.

[0067] In one exemplary embodiment, an implementation method for determining second reward data is provided. For example... Figure 4 As shown, the second reward data for determining the footage segment may include the following: (The text then goes on to describe the process of attributing the footage based on the first reward data.)

[0068] Step S410: Determine the material weight corresponding to the material fragment based on its position in the already deployed material fragments.

[0069] Considering that users may leave the viewing session at any time, the earlier clips in the content should be assigned higher weights. Weights can be assigned to clips based on a weighted progression model associated with the average user viewing time. A pre-established weight reduction model can be used to characterize how the weight of a clip changes with its position. Based on this pre-defined weight reduction model, the weight of a clip is determined according to its position. The sum of the weights of all clips in the already deployed content is 1.

[0070] For example, if the delivered video contains n clips, and the average user playback time covers the first m clips, then the weight of the i-th clip can be determined using the following linearly decreasing model:

[0071] w i1 =w0-k×i (2)

[0072] Where w0 is the initial weight, k is the decreasing coefficient, both of which can be set according to requirements, and i is the position of the material clip in the already deployed video clip.

[0073] For example, the weight of the i-th clip can be determined using the following exponentially decreasing model:

[0074] w i2 =w0×exp(-λ×i) (3)

[0075] Where λ is the decrease rate, which can be set according to requirements.

[0076] Step S420: Determine the second reward data for the material segment based on the material weight and the first reward data.

[0077] After obtaining the material weight and the first reward data, the second reward data of the material fragment can be obtained through the material weight and the first reward data. In other words, the first reward data is multiplied by the material weight of the material fragment to obtain the second reward data of the material fragment.

[0078] The linear decreasing model constrains the weight of each clip to decrease gradually by a fixed margin, while the exponential decreasing model constrains the weight of clips to decrease exponentially with their position, thus allowing for flexible adjustment of the importance of different clips. By designing the weight decreasing model, clips positioned earlier in the sequence receive higher weights, because even with a high bounce rate, earlier clips have a greater impact on the user's overall visual experience. Attributing the first reward data to each clip clarifies the contribution of each clip to the performance of the played content, ensuring that content seen earlier in the sequence has a greater impact on the overall effect. In other words, by rationally allocating the weights of clips, the overall effect of the content can be improved.

[0079] It should be noted that for other types of materials that have been deployed, the material weight of the i-th material segment can be obtained by using formulas (2) and (3), which will not be elaborated here.

[0080] In one exemplary embodiment, an implementation method for updating the material effect score of a material segment is also provided. For example... Figure 5 As shown, based on the second reward data and the historical material metrics of the material clip, updating the material clip's material effect score may include:

[0081] Step S510: Obtain the current material reward corresponding to the material fragment.

[0082] The current material reward refers to the material reward of the material clip that is yet to be updated, which is the material reward obtained after the previous update. For example, the material reward can be updated once every preset period, and the current material reward is the material reward (second reward data) obtained in the previous period update. The exemplary embodiments of this disclosure do not impose specific limitations on the preset period.

[0083] Step S520: Obtain the reward difference value between the current material reward and the second reward data. This can be achieved by obtaining the difference between the current material reward and the second reward data, which will be used as the reward difference value.

[0084] Step S530: Determine the reward correction parameters based on historical material indicators, and update the material effect score of the material segment according to the reward correction parameters, reward difference value and current material reward.

[0085] As mentioned above, historical material metrics may include at least one of the following: the number of times a material segment is selected, the number of times the material is completed, and the number of times the material is interacted with. Taking the number of times a material segment is selected as an example, the reciprocal of the number of selections can be used as a reward correction parameter. If the historical material metrics include the number of times a material segment is selected, the number of times the material is completed, and the number of times the material is interacted with, the sum of the number of selections, the number of times the material is completed, and the number of times the material is interacted with can be calculated, and then the reciprocal can be used as a reward correction parameter. The exemplary embodiment of this disclosure uses historical material metrics to determine the reward correction parameter, so that when updating the material effect score based on the material reward (current material reward, second reward data), the playback performance of the material segment itself can be fully considered, further improving the accuracy of updating the material effect score.

[0086] The material effect score of a clip is updated based on the reward correction parameters, the reward difference value, and the current material reward. The reward difference value can be corrected using the reward correction parameters (e.g., by multiplication), and then the corrected result is merged with the current material reward to obtain the updated material effect score. For example, the material effect score of a clip can be updated using the following formula:

[0087] Q i' =Q i +(1 / N i )×(R i -Q i (4)

[0088] Among them, Q i Q is the current material reward for the material clip. i’ Rate the updated footage quality, 1 / N i To reward the correction parameters, R i For the second reward data, (R) i -Q i () represents the difference in reward value.

[0089] By updating the performance scores of the aforementioned clips, the performance of the clips can be gradually adjusted. Clips with high user feedback can obtain higher performance scores, increasing their probability of being used to generate target materials in the future. This also improves the quality of the materials used to generate campaign materials, thereby enhancing the overall quality of the campaign materials.

[0090] As an example, if the current material reward for a certain material fragment i is Q... i=0.5, and the number of times the clip was selected after being submitted is N. i =1, and the calculated second reward data is 0.8. Then, by substituting into formula (4), the updated material effect score is: Q i’ =0.5+(1 / 1)×(0.8-0.5)=0.8, which means that the performance score of the material clip improved from 0.5 to 0.8, indicating that the material clip performed well in this campaign.

[0091] By analyzing the performance of clips within already deployed content, the effectiveness score of each clip can be adjusted. This allows for a greater preference for clips with higher effectiveness scores when generating subsequent content, thus improving the overall delivery performance. For example, if a clip containing natural scenery has a higher average viewing time for videos containing it, resulting in a higher effectiveness score, then in the next round of content selection, the updated effectiveness score will likely favor selecting that natural scenery clip or combining it with other content (such as new music) to generate a new video version.

[0092] By iterating and optimizing the selection of materials multiple times, the best combination of materials can be obtained, and the overall delivery effect of materials can be continuously improved.

[0093] In one exemplary embodiment, a strategy-based material selection method is also provided, such as... Figure 6 As shown, the process of retrieving target clips from the media library based on the updated media performance score, generating target media, and then deploying it includes:

[0094] Step S610: Obtain the material exploration probability, which indicates the proportion of random materials in the target material fragment.

[0095] Material exploration probability is the material selection probability based on a greedy strategy. It refers to the random selection of some materials from the material library according to a certain proportion when generating a target, to ensure exploration of material fragments in the entire material library and prevent getting trapped in local optima. Specifically, the material exploration probability is preset, which is the proportion of random materials in each target material, for example, setting the material exploration probability ∈ = 0.1.

[0096] Step S620: Obtain random materials from the material library based on the material exploration probability, and obtain generated materials from the material library based on the updated material effect score, so as to determine the target material fragment and generate the target material for deployment based on the random materials and generated materials.

[0097] Instead of selecting materials based on their performance ratings, you can first obtain material probabilities from the material library based on the material exploration probability. Then, based on the subsequent performance ratings, you can obtain generated materials from the material library. Finally, you can generate target materials for deployment based on the target material fragments determined by the random materials and the generated materials.

[0098] Specifically, when retrieving generated materials from the material library based on the updated material effect scores, the material clips in the material library can be sorted in descending order of material effect scores, and a preset number of material clips with the highest scores can be retrieved as generated material clips. The preset number can be set according to actual needs to ensure the quality of the material clips.

[0099] By employing a material exploration strategy, new material combinations are attempted with a certain probability. Even if the material fragments in the material library have low performance scores, materials will be randomly selected based on the material exploration probability to ensure the exploration of the entire material library. This helps to uncover potential excellent materials, especially underutilized material fragments. The exploration and utilization can be balanced by continuously adjusting the material exploration probability, thus adapting to the dynamic changes in the material library at different stages. This ensures that potential excellent material fragments are fully explored while utilizing currently known high-quality material fragments, thereby improving the overall material delivery effect.

[0100] In one exemplary embodiment, a method for optimizing the delivery effect of promotional materials is also provided. The material clips in the material library each have corresponding category tags, such as live-action footage, traditional Chinese style, lofty and natural, lyrical, and CG (Computer Graphics), which can be set according to requirements. Material clips of the same type have higher compatibility; for example, live-action videos are more compatible with each other, while live-action videos have slightly lower compatibility with CG animations.

[0101] First, based on the updated material performance score, multiple target material segments can be generated from the material library to produce multiple materials to be deployed. For each material to be deployed, the material compatibility of the material to be deployed is evaluated according to the category tags of the target material segments contained in the material to be deployed. Finally, based on the material compatibility evaluation results, the target material is selected from the multiple materials to be deployed for deployment.

[0102] For example, for each creative to be deployed, the correlation between the category tags of the target creative segments contained in the creative can be determined. Optionally, an evaluation model for judging creative compatibility can be pre-trained to determine the compatibility of the creative segments in each creative to be deployed. Optionally, correlation data between different creative categories can also be pre-set, and the correlation data can be queried according to the category tags of the creative segments in the creative to be deployed, so as to determine the creative compatibility of the creative to be deployed based on the query results.

[0103] By further assessing the compatibility of the creative materials to be deployed, the compatibility of the target creative materials can be further optimized, thereby improving the quality of the deployed creative materials.

[0104] In one exemplary embodiment, generating target video material from a material library based on the updated material effect score and then delivering it includes:

[0105] Obtain the material generation template, and based on the material generation template, generate multiple target materials from the target material fragment and deploy them.

[0106] The media generation template provides guidance for controlling media generation, including but not limited to video frame structure, video editing methods, cut points and transitions, text editing methods, and combinations of different types of media clips. In other words, in the exemplary embodiments of this disclosure, when generating multiple media clips to be deployed based on target media clips, the same media generation template is used, with diversity only in the selected media clips, resulting in multiple different versions of the target media. Based on this, the impact of media clips on the performance of deployed media can be more accurately quantified and evaluated, avoiding the influence of other variables on the evaluation of media clips and improving the accuracy of subsequent media clip selection.

[0107] The templates for generating materials can be provided manually or generated randomly by the system, without any specific restrictions.

[0108] In one exemplary embodiment, collecting user feedback features of delivered content may include:

[0109] Obtain the target user category for the ad creative, and based on the target user category, obtain the user feedback characteristics of the ad creative corresponding to that target user category.

[0110] User categories can be set based on age groups or other user characteristics, such as gender and occupation, and can be flexibly set according to actual needs.

[0111] Considering that different content clips have varying appeal to different user groups, the data range used to calculate content effectiveness scores can be adjusted based on the user category selected for content delivery. For example, when calculating the first reward data, values ​​such as play rate, interaction rate, and completion rate can be used. If this data range is set to young people, then the first reward data targets rewards more popular with them. In other words, without changing the formula itself, by adjusting the specific data sources, the first reward data can be adapted to the needs of different target audience characteristics, thereby selecting content clips more popular with young people to generate target content for delivery.

[0112] The exemplary embodiment of this disclosure discloses a method for delivering content, which involves collecting user feedback features of delivered content and determining first reward data for the delivered content based on these features. The first reward data reflects the delivery effect of the delivered content, which is generated from content clips obtained from a content library. Content attribution processing is performed based on the first reward data to determine second reward data for the content clips. The content effect score of the content clips is updated based on the second reward data and historical content metrics of the content clips. Based on the updated content effect score, target content is generated from target content clips obtained from the content library and then delivered. On one hand, by collecting user feedback features of delivered content, the method can evaluate the playback effect of the content and attribute the playback effect to the content clips. This allows for updating the content effect scores of the content clips in the content library to control subsequent content selection and generate delivery content. This process, driven by user feedback features, improves the quality of delivered content, ensuring it meets the actual interests and needs of different user groups and increasing the efficiency of content delivery. On the other hand, the process continuously optimizes the quality of generated materials based on user feedback through a cyclical execution process of generating materials, delivering materials, collecting information, evaluating materials, and optimizing materials. This reduces the complexity and time cost of manual intervention and improves the efficiency of material delivery.

[0113] In an exemplary embodiment of this disclosure, a material delivery device is also provided. (See reference...) Figure 7 As shown, the material delivery device 700 may include a feature processing module 710, a reward attribution module 720, and a material generation module 730. Specifically:

[0114] The feature processing module 710 is used to collect user feedback features of the deployed materials and determine the first reward data of the deployed materials based on the user feedback features. The first reward data reflects the deployment effect of the deployed materials. The deployed materials are generated based on material clips obtained from the material library. The reward attribution module 720 is used to perform material attribution processing based on the first reward data to determine the second reward data of the material clip. The material generation module 730 is used to update the material effect score of the material clip based on the second reward data and the historical material indicators of the material clip, and generate target materials based on the updated material effect score by obtaining target material clips from the material library and deploying them.

[0115] In one exemplary embodiment of this disclosure, the feature processing module 710 is configured to perform: obtaining weight information corresponding to the user feedback feature, the weight information reflecting the importance of the user feedback feature in the first reward data; and fusing the user feedback features corresponding to the deployed materials based on the weight information to obtain the first reward data.

[0116] In one exemplary embodiment of this disclosure, the reward attribution module 720 is configured to perform: determining the material weight corresponding to the material fragment based on the fragment position of the material fragment in the delivered material; and determining the second reward data of the material fragment based on the material weight and the first reward data.

[0117] In one exemplary embodiment of this disclosure, the reward attribution module 720 is configured to perform: determining the material weight corresponding to the material segment based on the segment position according to a preset weight reduction model; wherein, the weight reduction model is used to characterize the change of material weight with the segment position.

[0118] In one exemplary embodiment of this disclosure, the material generation module 730 is configured to perform: obtaining the current material reward corresponding to the material fragment; obtaining the reward difference value between the current material reward and the second reward data; determining the reward correction parameter based on the historical material index; and updating the material effect score of the material fragment according to the reward correction parameter, the reward difference value and the current material reward.

[0119] In one exemplary embodiment of this disclosure, the historical material metrics include at least one of the following: the number of times the material segment was selected, the number of times the material was completed, and the number of times the material was interacted with; wherein, the number of times the material segment was selected indicates the number of times the material segment was used to generate historical delivered materials, the number of times the material segment was completed indicates the number of times the historical delivered materials played the material segment completely, and the number of times the material was interacted with indicates the total number of interactions that occurred during the playback of the material segment.

[0120] In one exemplary embodiment of this disclosure, the material generation module 730 is configured to perform: obtaining a material exploration probability, the material exploration probability being used to indicate the proportion of random materials in the target material segment; obtaining random materials from the material library according to the material exploration probability, and obtaining generated materials from the material library based on the updated material effect score, so as to determine the target material segment and generate target materials for deployment based on the random materials and the generated materials.

[0121] In one exemplary embodiment of this disclosure, the material fragments in the material library have their own corresponding category tags; the material generation module 730 is configured to perform: obtaining target material fragments from the material library based on the updated material effect score to generate multiple materials to be deployed; for each material to be deployed, evaluating the material compatibility of the material to be deployed based on the category tags of the target material fragments contained in the material to be deployed; and determining the target material from the multiple materials to be deployed for deployment based on the evaluation results of the material compatibility.

[0122] In one exemplary embodiment of this disclosure, the material generation module 730 is configured to perform: obtaining a material generation template; and generating multiple target materials from the target material fragment based on the material generation template and then deploying them.

[0123] In one exemplary embodiment of this disclosure, the feature processing module 710 is configured to perform: obtaining the target user category for material delivery; and obtaining user feedback features corresponding to the target user category for the delivered material based on the target user category.

[0124] Since the details of each functional module of the material delivery device of the exemplary embodiments of this disclosure have been described in the exemplary embodiments of the material delivery method described above, they will not be repeated here.

[0125] It should be noted that although several modules or units of the material delivery device have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0126] Exemplary embodiments of this disclosure also provide a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the above-described material delivery method.

[0127] In one embodiment, the computer program product can be a tangible product containing a computer program, such as a computer-readable storage medium storing the computer program. The readable storage medium can be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, or other signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory, hard disk drive (HDD), solid-state drive (SSD), etc. For example, the computer program product can be implemented as a non-volatile storage medium storing the computer program, such as read-only memory, NAND flash memory, etc.

[0128] In one implementation, the computer program product can be an intangible product containing a computer program. For example, the computer program product can be implemented as a virtual digital product, such as an executable file, installation package, or other digital file storing the computer program.

[0129] Computer program code can be written in one or more programming languages. Examples of programming languages ​​include C, Java, and C++. Program code can execute entirely on the user's computing device, partially on the user's computing device, or as a standalone software package. It can also execute partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, such as a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via an internet connection provided by a mobile network operator).

[0130] Computer programs can be carried or transmitted via signals such as electricity, magnetism, light, electromagnetic fields, and infrared radiation. Electronic devices can convert signals carrying computer programs into digital signals, thereby running the computer programs. When a computer program runs on an electronic device, its code is used to cause the electronic device to execute (more specifically, the processor of the electronic device to execute) the method steps of various exemplary embodiments of this disclosure, such as the above-described material delivery method, which includes the following steps: collecting user feedback features of delivered materials, and determining first reward data for the delivered materials based on the user feedback features, wherein the first reward data reflects the delivery effect of the delivered materials, and the delivered materials are generated based on material fragments obtained from a material library; performing material attribution processing based on the first reward data to determine second reward data for the material fragments; updating the material effect score of the material fragments based on the second reward data and the historical material indicators of the material fragments, and generating target materials based on the updated material effect score by obtaining target material fragments from the material library and delivering them.

[0131] By executing the above methods and steps through a computer program, on the one hand, the playback effect of the deployed materials can be evaluated by collecting user feedback features, and the playback effect can be attributed to the material segments. This allows for updating the material effect scores of material segments in the material library, which is then used to control subsequent material selection and generation. This process, driven by user feedback features, improves the quality of deployed materials, ensuring they meet the actual interests and needs of different user groups and increasing the efficiency of material deployment. On the other hand, this process, through a cyclical execution flow of material generation, deployment, information collection, material evaluation, and optimization, continuously optimizes the quality of generated materials based on user feedback, reducing the complexity and time cost of manual intervention and further improving the efficiency of material deployment.

[0132] In one exemplary embodiment of this disclosure, determining the first reward data of the deployed materials based on the user feedback features includes: obtaining weight information corresponding to the user feedback features, the weight information reflecting the importance of the user feedback features in the first reward data; and fusing the user feedback features corresponding to the deployed materials based on the weight information to obtain the first reward data.

[0133] In one exemplary embodiment of this disclosure, the step of performing material attribution processing based on the first reward data to determine the second reward data of the material segment includes: determining the material weight corresponding to the material segment based on the segment position of the material segment in the deployed material; and determining the second reward data of the material segment based on the material weight and the first reward data.

[0134] In one exemplary embodiment of this disclosure, determining the material weight corresponding to the material segment based on the segment position of the material segment in the deployed material includes: determining the material weight corresponding to the material segment based on the segment position according to a preset weight reduction model; wherein, the weight reduction model is used to characterize the change of material weight with segment position.

[0135] In one exemplary embodiment of this disclosure, updating the material effect score of the material segment based on the second reward data and the historical material index of the material segment includes: obtaining the current material reward corresponding to the material segment; obtaining the reward difference value between the current material reward and the first reward data; determining a reward correction parameter based on the historical material index; and updating the material effect score of the material segment based on the reward correction parameter, the reward difference value, and the current material reward.

[0136] In one exemplary embodiment of this disclosure, the historical material metrics include at least one of the following: the number of times the material segment was selected, the number of times the material was completed, and the number of times the material was interacted with; wherein, the number of times the material segment was selected indicates the number of times the material segment was used to generate historical delivered materials, the number of times the material segment was completed indicates the number of times the historical delivered materials played the material segment completely, and the number of times the material was interacted with indicates the total number of interactions that occurred during the playback of the material segment.

[0137] In one exemplary embodiment of this disclosure, the step of obtaining target material fragments from the material library based on the updated material effect score, generating target material, and deploying the material includes: obtaining a material exploration probability, wherein the material exploration probability is used to indicate the proportion of random material in the target material fragment; obtaining random material from the material library according to the material exploration probability, and obtaining generated material from the material library based on the updated material effect score, so as to determine the target material fragment and generate target material for deployment based on the random material and the generated material.

[0138] In one exemplary embodiment of this disclosure, the media clips in the media library each have their own corresponding category tags; obtaining target media clips from the media library based on the updated media effect score to generate a video and then delivering it includes: obtaining target media clips from the media library based on the updated media effect score to generate multiple media clips to be delivered; for each media clip to be delivered, evaluating the media compatibility of the media clip to be delivered based on the category tags of the target media clips contained in the media clip to be delivered; and determining the target media clip from the multiple media clips to be delivered based on the media compatibility evaluation results.

[0139] In one exemplary embodiment of this disclosure, the step of obtaining target material fragments from the material library based on the updated material effect score, generating target materials, and deploying them includes: obtaining a material generation template; and generating multiple target materials from the target material fragments based on the material generation template and deploying them.

[0140] In one exemplary embodiment of this disclosure, the step of collecting user feedback features of the deployed video includes: obtaining the target user category for the deployment of the material; and obtaining user feedback features of the deployed material corresponding to the target user category based on the target user category.

[0141] Furthermore, in exemplary embodiments of this disclosure, an electronic device capable of implementing the above-described methods is also provided. Those skilled in the art will understand that various aspects of this disclosure can be implemented as systems, methods, or program products. Therefore, various aspects of this disclosure can be specifically implemented as entirely hardware embodiments, entirely software embodiments (including firmware, microcode, etc.), or embodiments combining hardware and software aspects, collectively referred to herein as "circuit," "module," or "system."

[0142] The following reference Figure 8 To describe an electronic device 800 according to such an embodiment of the present disclosure. Figure 8 The electronic device 800 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0143] like Figure 8As shown, the electronic device 800 is presented in the form of a general-purpose computing device. The components of the electronic device 800 may include, but are not limited to: at least one processing unit 810, at least one storage unit 820, a bus 830 connecting different system components (including storage unit 820 and processing unit 810), and a display unit 840.

[0144] The storage unit stores program code that can be executed by the processing unit 810, causing the processing unit 810 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. For example, the processing unit 810 may perform the following steps: collecting user feedback features of the deployed video, and determining first reward data for the deployed material based on the user feedback features, the first reward data reflecting the deployment effect of the deployed material, the deployed material being generated based on at least one material segment obtained from a material library; performing material attribution processing based on the first reward data to determine second reward data for the material segment; updating the material effect score of the material segment based on the second reward data and the historical material indicators of the material segment, and generating target material from the material library based on the updated material effect score and deploying it.

[0145] In one exemplary embodiment of this disclosure, determining the first reward data of the deployed materials based on the user feedback features includes: obtaining weight information corresponding to the user feedback features, the weight information reflecting the importance of the user feedback features in the first reward data; and fusing the user feedback features corresponding to the deployed materials based on the weight information to obtain the first reward data.

[0146] In one exemplary embodiment of this disclosure, the step of performing material attribution processing based on the first reward data to determine the second reward data of the material segment includes: determining the material weight corresponding to the material segment based on the segment position of the material segment in the deployed material; and determining the second reward data of the material segment based on the material weight and the first reward data.

[0147] In one exemplary embodiment of this disclosure, determining the material weight corresponding to the material segment based on the segment position of the material segment in the deployed material includes: determining the material weight corresponding to the material segment based on the segment position according to a preset weight reduction model; wherein, the weight reduction model is used to characterize the change of material weight with segment position.

[0148] In one exemplary embodiment of this disclosure, updating the material effect score of the material segment based on the second reward data and the historical material index of the material segment includes: obtaining the current material reward corresponding to the material segment; obtaining the reward difference value between the current material reward and the second reward data; determining a reward correction parameter based on the historical material index; and updating the material effect score of the material segment based on the reward correction parameter, the reward difference value, and the current material reward.

[0149] In one exemplary embodiment of this disclosure, the historical material metrics include at least one of the following: the number of times the material segment was selected, the number of times the material was completed, and the number of times the material was interacted with; wherein, the number of times the material segment was selected indicates the number of times the material segment was used to generate historical delivered materials, the number of times the material segment was completed indicates the number of times the historical delivered materials played the material segment completely, and the number of times the material was interacted with indicates the total number of interactions that occurred during the playback of the material segment.

[0150] In one exemplary embodiment of this disclosure, the step of obtaining target material fragments from the material library based on the updated material effect score, generating target material, and deploying the material includes: obtaining a material exploration probability, wherein the material exploration probability is used to indicate the proportion of random material in the target material fragment; obtaining random material from the material library according to the material exploration probability, and obtaining generated material from the material library based on the updated material effect score, so as to determine the target material fragment and generate target material for deployment based on the random material and the generated material.

[0151] In one exemplary embodiment of this disclosure, the material fragments in the material library each have their own corresponding category tags; the process of obtaining target material fragments from the material library based on the updated material effect score, generating target material, and delivering it includes: obtaining target material fragments from the material library based on the updated material effect score to generate multiple materials to be delivered; for each material to be delivered, evaluating the material compatibility of the material to be delivered based on the category tags of the target material fragments contained in the material to be delivered; and determining the target material from the multiple materials to be delivered based on the evaluation results of the material compatibility.

[0152] In one exemplary embodiment of this disclosure, the step of obtaining target material fragments from the material library based on the updated material effect score, generating target materials, and deploying them includes: obtaining a material generation template; and generating multiple target materials from the target material fragments based on the material generation template and deploying them.

[0153] In one exemplary embodiment of this disclosure, the step of collecting user feedback features of the deployed materials includes: obtaining the target user category for the material deployment; and obtaining user feedback features of the deployed materials corresponding to the target user category based on the target user category.

[0154] Storage unit 820 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 821 and / or cache memory 822, and may further include a read-only memory (ROM) 823.

[0155] The storage unit 820 may also include a program / utility 824 having a set (at least one) of program modules 825, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0156] Bus 830 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0157] Electronic device 800 can also communicate with one or more external devices 900 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 800, and / or with any device that enables electronic device 800 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 850. Furthermore, electronic device 800 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 860. As shown, network adapter 860 communicates with other modules of electronic device 800 via bus 830. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0158] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0159] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0160] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

Claims

1. A method for delivering materials, characterized in that, include: Collect user feedback features of the deployed materials, and determine the first reward data of the deployed materials based on the user feedback features. The first reward data reflects the deployment effect of the deployed materials. The deployed materials are generated based on at least one material fragment obtained from the material library. Based on the first reward data, material attribution processing is performed to determine the second reward data for the material fragment; Based on the second reward data and the historical material metrics of the material segment, update the material effect score of the material segment, and based on the updated material effect score, obtain the target material segment from the material library, generate the target material, and deploy it; The step of determining the first reward data for the deployed materials based on the user feedback features includes: obtaining weight information corresponding to the user feedback features, wherein the weight information reflects the importance of the user feedback features in the first reward data; and fusing the user feedback features corresponding to the deployed materials based on the weight information to obtain the first reward data. The step of performing material attribution processing based on the first reward data to determine the second reward data of the material segment includes: determining the material weight corresponding to the material segment based on the segment position of the material segment in the deployed materials; and determining the second reward data of the material segment based on the material weight and the first reward data. The step of updating the material effect score of the material segment based on the second reward data and the historical material indicators of the material segment includes: obtaining the current material reward corresponding to the material segment; obtaining the reward difference value between the current material reward and the second reward data; determining the reward correction parameter based on the historical material indicators; and updating the material effect score of the material segment based on the reward correction parameter, the reward difference value and the current material reward.

2. The method according to claim 1, characterized in that, The step of determining the material weight corresponding to the material fragment based on the fragment position of the material fragment in the already deployed material includes: Based on a preset weighting decreasing model, the material weight corresponding to the material segment is determined according to the segment position; The weighting decreasing model is used to characterize how the weight of the material changes with the position of the segment.

3. The method according to claim 1, characterized in that, The historical material metrics include at least one of the following: the number of times the material segment was selected, the number of times the material was completed, and the number of times the material was interacted with. Wherein, the number of times the material segment was selected indicates the number of times the material segment was used to generate historically delivered material, the number of times the material segment was played completely in the historically delivered material indicates the number of times the material segment was played completely in the historically delivered material, and the number of times the material segment was interacted indicates the total number of interactions that occurred in the historically delivered material during the playback of the material segment.

4. The method according to claim 1, characterized in that, The step of obtaining target material clips from the material library based on the updated material effect score, generating target material, and deploying it includes: Obtain the material exploration probability, which indicates the proportion of random materials in the target material fragment; Random materials are obtained from the material library based on the material exploration probability, and generated materials are obtained from the material library based on the updated material effect score, so as to determine the target material fragment and generate the target material for deployment based on the random materials and the generated materials.

5. The method according to claim 1, characterized in that, The media clips in the media library each have their own corresponding category tags; the process of obtaining target media clips from the media library based on the updated media effect score, generating videos, and delivering them includes: Based on the updated material performance score, target material clips are obtained from the material library to generate multiple materials to be deployed; For each of the aforementioned creative materials to be deployed, the material compatibility of the creative materials to be deployed is evaluated based on the category tags of the target material segments contained in the creative materials. Based on the assessment results of material compatibility, target materials are selected from the multiple materials to be deployed for deployment.

6. The method according to claim 1, characterized in that, The step of obtaining target material clips from the material library based on the updated material effect score, generating target material, and deploying it includes: Get source materials and generate templates; Based on the material generation template, multiple target materials are generated from the target material fragment and then deployed.

7. The method according to any one of claims 1 to 6, characterized in that, The user feedback features collected for the deployed materials include: Identify the target user categories for ad creative distribution; Based on the target user category, obtain the user feedback characteristics corresponding to the target user category for the deployed materials.

8. A material dispensing device, characterized in that, The device includes: The feature processing module is used to collect user feedback features of the deployed materials and determine the first reward data of the deployed materials based on the user feedback features. The first reward data reflects the deployment effect of the deployed materials. The deployed materials are generated based on at least one material fragment obtained from the material library. The reward attribution module is used to perform material attribution processing based on the first reward data to determine the second reward data of the material segment. The material generation module is used to update the material effect score of the material segment based on the second reward data and the historical material indicators of the material segment, and to obtain the target material segment from the material library based on the updated material effect score to generate target material and deploy it. The feature processing module is configured to perform the following: obtain weight information corresponding to the user feedback feature, wherein the weight information reflects the importance of the user feedback feature in the first reward data; and based on the weight information, fuse the user feedback features corresponding to the deployed materials to obtain the first reward data. The reward attribution module is configured to perform the following: determine the material weight corresponding to the material fragment based on the fragment position of the material fragment in the deployed material; and determine the second reward data of the material fragment based on the material weight and the first reward data. The material generation module is configured to perform the following: obtain the current material reward corresponding to the material fragment; obtain the reward difference value between the current material reward and the second reward data; determine the reward correction parameter based on the historical material index; and update the material effect score of the material fragment according to the reward correction parameter, the reward difference value and the current material reward.

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

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

Images