Data distribution method, apparatus, and computer readable storage medium

Abstract

The present disclosure relates to a data distribution method, an apparatus, and a computer readable storage medium, which relate to the technical field of terminals. The data distribution method comprises: displaying first multimedia content data selected from a first database according to a first distribution strategy; in response to a feedback trigger condition being met, displaying a feedback interface; receiving natural language instructions from a user by means of the feedback interface; and displaying, on the basis of a machine understanding result of the natural language instructions, second multimedia content data selected from a second database according to a second distribution strategy, wherein the second distribution strategy is obtained by using the machine understanding result to adjust the first distribution strategy.

Description

[0001]Cross-Reference to Related Applications: This application is based on and claims priority from Chinese application No. 202311274109.X, filed September 27, 2023. The disclosure of that Chinese application is hereby incorporated by reference in its entirety into this application. Technical Field: This disclosure relates to the field of terminal technology, and more particularly to a data distribution method, device, and computer-readable storage medium. Background: Multimedia applications can push multimedia content to users using data distribution algorithms. For example, corresponding multimedia content can be distributed to users based on user feedback such as likes, favorites, and skips for various categories of multimedia content, as well as user profile information. SUMMARY According to a first aspect of some embodiments of the present disclosure, a data distribution method is provided, comprising: displaying first multimedia content data selected from a first database according to a first distribution policy; displaying a feedback interface in response to a feedback trigger condition being met; receiving a natural language instruction from a user via the feedback interface; and displaying second multimedia content data selected from a second database according to a second distribution policy based on a machine understanding of the natural language instruction, wherein the second distribution policy is obtained by adjusting the first distribution policy using the machine understanding. In some embodiments, the first distribution policy includes one or more selection conditions, each of which includes one or more dimensions; the machine understanding includes adjustment information for at least one dimension of at least one selection condition, or includes a new selection condition. In some embodiments, the dimensions of each selection condition include description information and a preference for selecting multimedia content data having the description information. In some embodiments, the dimensions of the selection condition also include at least one of the degree of preference for the preference and the effective time of the selection condition. In some embodiments, the second multimedia content data is selected based on the similarity between the embedding vector of the second distribution policy and the embedding vectors of the multimedia content data in the second database. In some embodiments, the feedback trigger condition includes performing a specified operation on the first multimedia content data. In some embodiments, the designated operation includes triggering an entry control on a feedback interface. In some embodiments, in response to the feedback triggering condition being met, displaying the feedback interface includes: displaying an interaction panel for the first multimedia content data in response to an interaction operation on the first multimedia content data on a playback interface of the first multimedia content data, wherein the interaction panel includes an entry control on the feedback interface; and displaying the feedback interface in response to the user triggering the entry control.In some embodiments, in response to a feedback trigger condition being met, displaying a feedback interface includes: displaying a questionnaire interface in response to a switching operation on the first multimedia content data in the playback interface of the first multimedia content data, wherein the questionnaire interface includes candidate feedback information and an entry control of the feedback interface; and displaying the feedback interface in response to a user triggering the entry control. In some embodiments, displaying second multimedia content data selected from a second database according to a second distribution policy based on a machine understanding result of a natural language instruction includes: displaying the machine understanding result of the natural language instruction; and displaying the second multimedia content data selected from the second database according to the second distribution policy in response to a user confirming the machine understanding result. In some embodiments, the data distribution method further includes: displaying a history record interface, wherein the history record interface includes one or more historical machine understanding results; and displaying third multimedia content data selected from a third database based on the uncancelled historical machine understanding results in response to a user cancelling operation on at least some of the historical machine understanding results. In some embodiments, the data distribution method further includes: displaying a history record entry control in the playback interface of the second multimedia content data, wherein the history record entry control is used to trigger display of the history record interface. In some embodiments, receiving a natural language instruction from a user includes: receiving text or voice input from the user including a natural language instruction; or receiving a natural language instruction selected by the user from one or more candidate natural language instructions. In some embodiments, the machine understanding result includes descriptive information and a preferred selection of multimedia content data having the descriptive information. In some embodiments, the machine understanding result also includes at least one of the degree of preferred selection, the source of the multimedia content data, and the effective time of the natural language instruction. According to a second aspect of some embodiments of the present disclosure, a data distribution device is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute any of the aforementioned data distribution methods based on instructions stored in the memory. According to a third aspect of some embodiments of the present disclosure, a computer-readable storage medium is provided, having stored thereon a computer program, which, when executed by the processor, implements any of the aforementioned data distribution methods. According to a fourth aspect of some embodiments of the present disclosure, a computer program is provided, comprising: instructions, which, when executed by the processor, cause the processor to execute any of the aforementioned data distribution methods. Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings.BRIEF DESCRIPTION OF THE DRAWINGS To more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below only illustrate some embodiments of the present disclosure. Persons skilled in the art can derive other drawings based on these drawings without inventive effort. FIG1 illustrates a flow chart of a data distribution method according to some embodiments of the present disclosure. FIG2A exemplarily illustrates a schematic diagram of a multimedia content data playback interface according to some embodiments of the present disclosure. FIG2B exemplarily illustrates a schematic diagram of an interactive panel according to some embodiments of the present disclosure. FIG2C exemplarily illustrates a schematic diagram of a multimedia content data playback interface according to other embodiments of the present disclosure. FIG2D exemplarily illustrates a schematic diagram of a questionnaire interface according to some embodiments of the present disclosure. FIG2E exemplarily illustrates a schematic diagram of a feedback interface according to some embodiments of the present disclosure. FIG2F exemplarily illustrates a schematic diagram of a confirmation interface according to some embodiments of the present disclosure. FIG3 illustrates a schematic diagram of the structure of a data distribution device according to some embodiments of the present disclosure. FIG4 illustrates a schematic diagram of the structure of a data distribution device according to other embodiments of the present disclosure. FIG5 illustrates a schematic diagram of the structure of a data distribution device according to yet other embodiments of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following will provide a clear and complete description of the technical solutions in the embodiments of the present disclosure, in conjunction with the accompanying drawings. It should be understood that the described embodiments are only some of the embodiments of the present disclosure, and not all of them. The following description of at least one exemplary embodiment is merely illustrative and in no way limits the present disclosure, its application, or use. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present disclosure without inventive effort are within the scope of protection of the present disclosure. Unless otherwise specified, the relative arrangement of components and steps, numerical expressions, and values ​​described in these embodiments do not limit the scope of the present disclosure. It should also be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn to scale. Technologies, methods, and devices known to persons of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such technologies, methods, and devices should be considered part of the specification. In all examples shown and discussed herein, any specific values ​​should be interpreted as merely illustrative and not limiting. Therefore, other examples of the exemplary embodiments may have different values. It should be noted that like numbers and letters refer to like items in the following figures, so once an item is defined in one figure, it does not need to be further discussed in subsequent figures.After analysis, it was found that related technologies adjust multimedia content distribution strategies based on a few fixed user actions. While interactive actions such as "Like," "Add to Favorites," and "Skip" can assist in adjusting distribution strategies, these adjustments are implicit, and users cannot intuitively understand the extent of feedback these actions will generate. Therefore, a more intuitive method for providing user feedback is needed. For example, various types of multimedia content data and their associated adjustment options can be listed for users to choose from. For example, for each video category, adjustment options include increasing or decreasing the distribution frequency, with the increase and decrease levels divided into several levels. Adjustment options also include options for taking effect within the next week, month, or permanently. However, multimedia content data has a wide variety of types and adjustment methods. If all these adjustable options are presented to the user, they will need to perform multiple interactive operations to set them, and it will be difficult for users to browse all the adjustable information. If only a small number of options are presented to the user, accurate feedback cannot be achieved. Therefore, in related technologies, it is difficult to effectively obtain feedback information on the data distribution process. As a result, many multimedia content data, after being distributed to users, is directly skipped by users because it is not the data they want to receive, wasting network resources and user terminal resources. Therefore, a technical problem to be solved by embodiments of the present disclosure is how to efficiently and accurately obtain feedback information on distributed data to improve the accuracy of multimedia content data distribution, thereby conserving network resources and user terminal resources. First, a data distribution scenario in some embodiments of the present disclosure is described as an example. When determining multimedia content data to distribute to users, multimedia content data can be selected from a database based on a distribution policy. The multimedia content data in the database may be uploaded by the creator of the multimedia content. For example, a user can create and upload multimedia content data as a creator, and this uploaded multimedia content data can be stored in one or more databases. Each user can also act as a viewer, receiving multimedia content data selected and distributed to the user by the server according to the distribution policy. In embodiments of the present disclosure, the distribution policy can be adjusted based on the user's natural language instructions. The following describes an embodiment of the data distribution method based on the user's natural language instructions, with reference to FIG1. Figure 1 illustrates a schematic flow diagram of a data distribution method according to some embodiments of the present disclosure. This data distribution method can be executed on a user terminal, such as a mobile phone, tablet, personal computer, wearable device, or the like. The user terminal can execute the method flow by loading an application (APP). When necessary, the user terminal can exchange data with a server via a network.As shown in Figure 1, the data distribution method of this embodiment includes steps S102 to S108. In step S102, first multimedia content data selected from a first database according to a first distribution policy is displayed. In some embodiments, a server may select the first multimedia content data from the server's first database according to the first distribution policy and send it to a user terminal for display. Alternatively, the server may send multiple multimedia content data at once and store them in the user terminal's first database. The terminal then selects and displays the first multimedia content data according to the first distribution policy. The first distribution policy is determined, for example, based on user interaction with one or more displayed multimedia content data, such as likes, browsing time, etc. Alternatively, it may be determined based on a user profile, which may reflect user preferences. Alternatively, if a user has previously provided feedback, the first distribution policy may be determined based on historical feedback information. The first distribution policy may also be determined using other methods, which will not be elaborated here. The operation of the first and second distribution policies will be further described later when describing the second distribution policy. In step S104, in response to the feedback trigger condition being met, a feedback interface is displayed. Feedback triggering conditions can be designated actions actively performed by the user, or conditions passively achieved through user behavior, such as staying on the first multimedia content data interface for a specified period of time or playing the first multimedia content data more than a specified number of times. In some embodiments, feedback triggering conditions include performing designated actions on the first multimedia content data. For example, a designated action on the first multimedia content means performing the designated action on the playback interface of the first multimedia content data or on another interface associated with the first multimedia content data. The designated action can be a gesture such as a click, a long press, or a swipe, or an action indicating a function such as triggering a specific interface or switching videos. The designated action can include one or more actions. In some embodiments, the designated action includes triggering an entry control on a feedback interface. The entry control on the feedback interface can be located on an interface associated with the first multimedia content data. For example, the entry control can be directly located on the playback interface of the first multimedia content data. Furthermore, embodiments of the present disclosure exemplify two triggering methods. Figures 2A, 2B, and 2E exemplify one triggering method. In Figure 2A, the playback interface 21 of the first multimedia content data plays the first multimedia content.A user performs an interactive operation on the first multimedia content data in the playback interface 21, for example, by long-pressing the first multimedia content, triggering the display of the interactive panel 211 shown in FIG2B . The interactive panel 211 includes an entry control 2111 for the feedback interface. Furthermore, the interactive panel 211 provides other interactive operations associated with the first multimedia content data, such as one or more of: saving, indicating no interest in the multimedia content, forwarding, and adding it to favorites. In response to the user's triggering operation on the entry control 2111, the feedback interface 23 shown in FIG2E is displayed. FIG2C , FIG2D , and FIG2E exemplify another triggering method. The playback interface shown in FIG2C and FIG2A may be the same. However, in FIG2C , the user performs an operation different from that in FIG2A . In response to a switching operation on the first multimedia content data in the playback interface 21 of the first multimedia content data, such as the upward swipe operation shown in the figure, the questionnaire interface 22 shown in FIG2D is displayed. Generally, after a user performs a switching operation on the playback interface of the first multimedia content data, the user switches to the next multimedia content data. The embodiments of the present disclosure insert a questionnaire interface 22 between the currently playing first multimedia content data and the next multimedia content data to facilitate user feedback after viewing the first multimedia content data. Those skilled in the art will appreciate that the long-press operation shown in FIG2A and the sliding operation shown in FIG2C are merely exemplary. Other specific operations can be used to implement interactive operations or multimedia content data switching operations as needed, and are not described in detail here. In some embodiments, after the user's interaction with the first multimedia content data meets specified questionnaire triggering conditions, the questionnaire interface is displayed in response to the switching operation on the first multimedia content data. Questionnaire triggering conditions include, for example, a browsing time exceeding a first threshold or less than a second threshold, the number of times the first multimedia content data is played exceeding a third threshold, or a like, favorite, or feedback indicating lack of interest has been given for the first multimedia content data. As needed, the questionnaire triggering conditions can be a combination of some of the aforementioned conditions, or can include other conditions, and are not described here in detail here. The questionnaire interface 22 provides several candidate feedback messages 221 and 222, and the user can provide feedback by directly selecting these prompts. The feedback information displayed in the questionnaire interface 22 can include one or more pieces of information. The feedback information may be general feedback information, that is, applicable to each multimedia content data, such as “show more videos of this type” as shown in the feedback information 221.Alternatively, this feedback information may be generated based on one or more multimedia content items recently viewed by the user. For example, if the first multimedia content item is a video about cats, the feedback information may be "Show more pet videos" as shown in feedback information 222. Furthermore, the questionnaire interface 22 also includes a feedback interface entry control 223. In response to the user triggering the entry control, the feedback interface 23 shown in FIG2E is displayed. In FIG2E , the feedback interface 23 includes, for example, an input box 231 for the user to enter text including natural language instructions. In other words, the user enters the natural language instructions in text form. Alternatively, the user can enter natural language instructions via voice. For example, the user can begin speaking after triggering the voice input control. The user's voice is then recognized as text and displayed in the feedback interface 23. In some embodiments, the feedback interface 23 may also include candidate feedback information 232. Candidate feedback information is pre-generated natural language instructions. The generation method for candidate feedback information in the questionnaire interface 22 can refer to the candidate feedback information in the questionnaire interface 22. The user can quickly enter text by selecting a prompt. For example, after the user selects a prompt, the prompt is automatically displayed in the input box 231, allowing the user to further edit the text in the input box 231. In some embodiments, the feedback interface 23 may also include a submit control 233 for submitting the natural language instruction entered by the user for further processing. In step S106, a natural language instruction from the user is received through the feedback interface. For example, a natural language instruction submitted by the user in the input box 231 in FIG. 2E or a natural language instruction entered by the user via voice input is received. Natural language instructions are unformatted and unconditional, allowing users to more freely express desired adjustments to the distribution of multimedia content data. Natural language instructions represent user feedback on the first multimedia content data. After obtaining the natural language instruction submitted by the user through the feedback interface, machine understanding (NLU) of the natural language instruction can be performed. For example, the natural language instruction can be processed using a machine learning model to obtain machine understanding results of the natural language instruction. This understanding process can be performed by an electronic device such as a computer. Ideally, machine understanding results would accurately reflect intent, but in a more canonical form.For example, if a user's natural language instruction is "I want to watch more videos about cats and dogs," the natural language understanding result may be "More pet videos." The machine understanding result of the natural language instruction may include the extraction of information from multiple dimensions included in the natural language instruction. This information may be formatted data (e.g., data represented as key-value pairs) or data still represented in natural language but with a specified sentence structure and vocabulary. Of course, the machine understanding result may also be data that cannot be directly interpreted, such as an embedding vector. In some embodiments, the machine understanding result includes descriptive information and a preference for multimedia content data with descriptive information. Descriptive information may describe the theme, category, source, etc. of the multimedia content data, such as news, entertainment news, or the account from which it was uploaded. The preference indicates whether the user has a positive or negative attitude toward the multimedia content data with descriptive information. A positive attitude indicates that the user desires to receive more multimedia content data with descriptive information, while a negative attitude indicates that the user desires to receive less or no multimedia content data with descriptive information. Furthermore, the machine understanding result may include at least one of the degree of preference for the preference selection and the effective time of the natural language instruction. For example, when the preference is negative, the preference levels are, for example, "less such content", "try not to have such content", and "remove all such content", indicating that the degree to which the user does not want to receive such content ranges from low to high. Examples of effective time periods include "within this week," "in the next month," and so on. If the user does not indicate information such as the degree of preference or effective time in the natural language instruction, default parameters may be used. In step S108, based on the machine understanding of the natural language instruction, second multimedia content data selected from the second database according to a second distribution strategy is displayed. The second distribution strategy is obtained by adjusting the first distribution strategy using the machine understanding results. To further confirm that the machine understanding results are consistent with the user's starting point, in some embodiments, the machine understanding results of the natural language instruction are displayed; in response to the user's confirmation of the machine understanding results, the second multimedia content data selected from the second database according to the second distribution strategy is displayed. The machine understanding results can be displayed on the feedback interface or on other interfaces. Figure 2F illustrates an exemplary diagram of a confirmation interface. In Figure 2F, confirmation interface 212 includes the machine understanding result "More pet videos" in response to the user's natural language instruction "I want to watch more videos of cats, dogs, and the like." This machine understanding result is displayed in the formatted paragraph 2121.The user can determine whether to distribute multimedia content data based on the machine comprehension result by triggering the cancel control 2122 or the confirm control 2123. If the user disagrees with the machine comprehension result, they can cancel the feedback or return to the feedback interface to submit another feedback. In some embodiments, the server can select second multimedia content data from the server's second database according to a second distribution policy and send it to the user terminal for display. Alternatively, the server can send multiple multimedia content data at once and store them in the user terminal's second database. The terminal then selects and displays the second multimedia content data according to the second distribution policy. The first and second databases can be the same or different databases. For example, each of the first and second distribution policies can include one or more selection conditions, each of which includes one or more dimensions. These dimensions can include descriptive information and a preference for selecting multimedia content data with descriptive information. They can also include at least one of the degree of preference for the preference and the effective time of the selection condition. The machine comprehension result can include adjustment information for at least one dimension of at least one selection condition, or a new selection condition. If the descriptive information in the machine comprehension results appears in a selection condition of the first distribution strategy, it indicates that the user's natural language instruction involves adjusting an existing selection condition. The machine comprehension results can then be used to adjust the selection condition. For example, if a selection condition in the first distribution strategy indicates that pet videos should be distributed more frequently to users, but the machine comprehension results of the user's natural language instruction indicate that pet videos should be distributed less frequently, the selection condition in the first distribution strategy can be adjusted to obtain a second distribution strategy. If the descriptive information in the machine comprehension results does not appear in any selection condition of the first distribution strategy, it indicates that the user's natural language instruction is a new restriction. In this case, the selection condition generated based on the machine comprehension results can be directly added to the first distribution strategy to generate the second distribution strategy. The selection condition in the distribution strategy can be converted into SQL (Structured Query Language) and executed to retrieve the second multimedia content data from the database. Furthermore, a machine learning model can be used to process the distribution strategy and the candidate multimedia content data in the database to generate vectors corresponding to the distribution strategy and the multimedia content data. Then, the second multimedia content data may be selected based on the similarity between the embedding vector of the second distribution strategy and the embedding vectors of the multimedia content data in the second database.During selection, for example, the multimedia content data with the highest similarity to the second distribution policy can be selected as the second multimedia content data. The process for selecting the first multimedia content data is similar to that for selecting the second multimedia content data and will not be further described here. In embodiments of the present disclosure, users provide feedback on the first multimedia content data using natural language instructions, thereby efficiently and accurately obtaining feedback information regarding the distributed data. This feedback information can improve the accuracy of multimedia content data distribution, thereby conserving network resources and user terminal resources. Some embodiments of the present disclosure may also support users issuing one or more natural language instructions to adjust the distribution policy one or more times. Accordingly, one or more historical machine understanding results for these historical natural language instructions can be displayed in a history record interface. By displaying the history record interface, users can understand the feedback that has taken effect. In some embodiments, in response to a user canceling at least some of the historical machine understanding results, third multimedia content data selected from a third database is displayed based on the remaining historical machine understanding results. That is, the canceled machine understanding results are no longer effective. Based on the uncancelled, historical machine understanding results, the current distribution strategy can be adjusted to generate a third distribution strategy, and the third multimedia content data selected from the third database according to the third distribution strategy can then be displayed to the user. The location of the entry to the history record interface can be configured as needed. In some embodiments, a history record entry control is displayed within the playback interface of the second multimedia content data, and the history record entry control is used to trigger the display of the history record interface. Thus, when a user's natural language instruction takes effect, the history record entry control can be displayed within the interface of the second multimedia content data distributed to the user based on the natural language instruction, allowing the user to view the machine understanding results of the currently effective natural language instruction. The above is the data distribution method provided by an embodiment of the present disclosure. Referring to Figures 3 to 5 , an embodiment of the present disclosure also provides a data distribution device for executing the aforementioned data distribution method. This device can be implemented in software and / or hardware and can be integrated into an electronic device equipped with a front-end search-related application. The electronic device may include, but is not limited to, mobile terminals such as smart phones, laptops, personal digital assistants (PDAs), tablet personal computers (Tablet PCs), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), wearable devices, etc., and fixed terminals such as digital televisions, desktop computers, etc.Figure 3 illustrates a schematic diagram of a data distribution device according to some embodiments of the present disclosure. As shown in Figure 3, the data distribution device 30 of this embodiment includes: a first display module 310 configured to display first multimedia content data selected from a first database according to a first distribution policy; a second display module 320 configured to display a feedback interface in response to a feedback trigger condition being met; a receiving module 330 configured to receive a natural language instruction from a user via the feedback interface; and a third display module 340 configured to display second multimedia content data selected from a second database according to a second distribution policy based on machine understanding of the natural language instruction. The second distribution policy is obtained by adjusting the first distribution policy using the machine understanding. In some embodiments, the first distribution policy includes one or more selection conditions, each of which includes one or more dimensions. The machine understanding includes adjustment information for at least one dimension of at least one selection condition, or includes a new selection condition. In some embodiments, the dimensions of each selection condition include descriptive information and a preference for selecting multimedia content data with the descriptive information. In some embodiments, the dimensions of the selection condition also include at least one of the degree of preference for the preference and the effective time of the selection condition. In some embodiments, the second multimedia content data is selected based on the similarity between the embedding vector of the second distribution strategy and the embedding vector of the multimedia content data in the second database. In some embodiments, the feedback triggering condition includes performing a specified operation on the first multimedia content data. In some embodiments, the specified operation includes triggering an entry control on a feedback interface. In some embodiments, the second display module 320 is further configured to display an interactive panel for the first multimedia content data in response to an interactive operation on the first multimedia content data, wherein the interactive panel includes an entry control on the feedback interface; and display the feedback interface in response to a user triggering the entry control. In some embodiments, the second display module 320 is further configured to display a questionnaire interface in response to a switching operation on the first multimedia content data, wherein the questionnaire interface includes candidate feedback information and an entry control on the feedback interface; and display the feedback interface in response to a user triggering the entry control. In some embodiments, the third display module 340 is further configured to display a machine understanding result of the natural language instruction; and in response to a user confirming the machine understanding result, display the second multimedia content data selected from the second database according to the second distribution strategy.In some embodiments, the data distribution device 30 further includes: a fourth display module 350 configured to display a history interface, wherein the history interface includes one or more historical machine understanding results; and in response to a user canceling at least some of the historical machine understanding results, displaying third multimedia content data selected from a third database based on the uncancelled historical machine understanding results. In some embodiments, the third display module 340 is further configured to display a history entry control in the playback interface of the second multimedia content data, the history entry control being used to trigger the display of the history interface. In some embodiments, the receiving module 330 is configured to receive user input of text or voice including a natural language instruction; or to receive a natural language instruction selected by the user from one or more candidate natural language instructions. In some embodiments, the machine understanding result includes descriptive information and a preference for multimedia content data having the descriptive information. In some embodiments, the machine understanding result also includes at least one of the degree of preference for the preference, the source of the multimedia content data, and the effective time of the natural language instruction. Figure 4 shows a schematic structural diagram of a data distribution device according to other embodiments of the present disclosure. As shown in Figure 4 , the data distribution device 40 of this embodiment includes a memory 410 and a processor 420 coupled to the memory 410. The processor 420 is configured to execute the data distribution method of any of the aforementioned embodiments based on instructions stored in the memory 410. The memory 410 may include, for example, system memory, fixed non-volatile storage media, etc. The system memory may store, for example, an operating system, application programs, a boot loader, and other programs. Figure 5 shows a schematic structural diagram of a data distribution device according to yet other embodiments of the present disclosure. As shown in Figure 5 , the data distribution device 50 of this embodiment includes a memory 510 and a processor 520. It may also include an input / output interface 530, a network interface 540, a storage interface 550, etc. These interfaces 530, 540, 550, as well as the memory 510 and the processor 520, may be connected, for example, via a bus 560. The input / output interface 530 provides a connection interface for input / output devices such as a display, mouse, keyboard, and touch screen. The network interface 540 provides a connection interface for various networked devices. The storage interface 550 provides a connection interface for external storage devices such as SD cards and USB flash drives. Embodiments of the present disclosure also provide a computer-readable storage medium having a computer program stored thereon, characterized in that when the program is executed by a processor, it implements any of the aforementioned data distribution methods.It is understood that before implementing the technical solutions of each embodiment of the present disclosure, the user will be informed of the type, scope, and scenario of the personal information involved through appropriate means, and their authorization will be obtained. For example, in response to a user's active request, a prompt message may be sent to the user to clearly inform them that the requested operation will require the acquisition and use of their personal information. This allows the user to independently choose whether to provide their personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the technical solutions of the present disclosure based on the prompt message. As an optional but non-limiting implementation, in response to a user's active request, the prompt message may be sent to the user in the form of a pop-up window, which may present the prompt message in text format. Furthermore, the pop-up window may also contain a selection control for the user to select "Agree" or "Disagree" to provide their personal information to the electronic device. It is understood that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure. Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable, non-transitory storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code. The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, such that the instructions, executed by the processor of the computer or other programmable data processing device, produce means for implementing the functions specified in one or more processes in the flowcharts and / or one or more blocks in the block diagrams. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in one or more processes in the flowchart and / or one or more blocks in the block diagram.These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing the computer or other programmable device to execute a series of operational steps to produce a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more flow charts and / or one or more blocks in the block diagrams. The foregoing description is merely a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure are intended to be included within the scope of protection of the present disclosure.

Claims

Claims 1. A data distribution method, comprising: displaying first multimedia content data selected from the first database according to the first distribution strategy; In response to the feedback triggering condition being met, displaying a feedback interface; receiving a natural language instruction from a user through the feedback interface; Based on the machine understanding result of the natural language instruction, second multimedia content data selected from the second database according to a second distribution strategy is displayed, wherein the second distribution strategy is obtained by adjusting the first distribution strategy by using the machine understanding result.

2. The data distribution method according to claim 1, wherein: The first distribution strategy includes one or more selection conditions, each selection condition includes one or more dimensions; the machine understanding result includes adjustment information of at least one dimension in at least one selection condition, or includes a new selection condition.

3. The data distribution method according to claim 2, wherein: The dimensions of each selection condition include description information and a preference for selecting multimedia content data having the description information.

4. The data distribution method according to claim 3, wherein: The dimension of the selection condition also includes at least one of the degree of tendency of the preference selection and the effective time of the selection condition.

5. The data distribution method according to any one of claims 1 to 4, wherein: The second multimedia content data is selected based on a similarity between the embedding vector of the second distribution strategy and the embedding vector of the multimedia content data in the second database.

6. The data distribution method according to any one of claims 1 to 5, wherein: The feedback triggering condition includes performing a specified operation on the first multimedia content data.

7. The data distribution method according to claim 6, wherein: The specified operation includes a triggering operation on an entry control of the feedback interface.

8. The data distribution method according to claim 7, wherein: In response to the feedback trigger condition being satisfied, displaying the feedback interface includes: in the playback interface of the first multimedia content data, in response to an interactive operation on the first multimedia content data, displaying an interactive panel of the first multimedia content data, wherein the interactive panel includes an entry control of the feedback interface; and displaying the feedback interface in response to a triggering operation of the user on the entry control.

9. The data distribution method according to claim 7, wherein: In response to the feedback trigger condition being satisfied, displaying the feedback interface includes: in the playback interface of the first multimedia content data, in response to a switching operation on the first multimedia content data, displaying a questionnaire interface, wherein the questionnaire interface includes candidate feedback information and an entry control of the feedback interface; and displaying the feedback interface in response to the user triggering the entry control.

10. The data distribution method according to any one of claims 1 to 9, wherein: The display of second multimedia content data selected from the second database according to a second distribution strategy based on the machine understanding result of the natural language instruction includes: displaying the machine understanding result of the natural language instruction; and in response to the user's confirmation of the machine understanding result, displaying the second multimedia content data selected from the second database according to the second distribution strategy.

11. The data distribution method according to any one of claims 1 to 10, further comprising: displaying a history record interface, wherein the history record interface includes one or more historical machine understanding results; and in response to the user cancelling at least part of the historical machine understanding results, displaying third multimedia content data selected from a third database based on the historical machine understanding results that have not been canceled.

12. The data distribution method according to claim 11, further comprising: In the playback interface of the second multimedia content data, a history record entry control is displayed, and the history record entry control is used to trigger the display of the history record interface.

13. The data distribution method according to any one of claims 1 to 12, wherein: The receiving of the natural language instruction from the user includes: receiving text or voice input by the user including the natural language instruction; or receiving a natural language instruction selected by the user from one or more candidate natural language instructions.

14. The data distribution method according to any one of claims 1 to 13, wherein: The machine understanding result includes description information and a preferred selection of multimedia content data having the description information.

15. The data distribution method according to claim 14, wherein: The machine understanding result also includes at least one of the degree of tendency of the tendency selection, the source of the multimedia content data, and the effective time of the natural language instruction.

16. A data distribution device, comprising: A memory; and a processor coupled to the memory, wherein the processor is configured to execute the data distribution method according to any one of claims 1 to 15 based on instructions stored in the memory.

17. A computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the data distribution method according to any one of claims 1 to 15 is implemented.

18. A computer program comprising: Instructions, which, when executed by a processor, cause the processor to execute the data distribution method according to any one of claims 1 to 15. 16

Images