Intelligent generation method of live data in network live broadcast scene and intelligent decision device

Abstract

The application provides a kind of intelligent generation method and intelligent decision device of live data in network live scene, it is related to computer technology field, the method can more intelligently organize live room.The method comprises: obtaining the demand data of user;According to the demand data of user, determine the live process data, live rule data and live content data corresponding to the demand data of user;Live process data, live rule data and live content data are sent to electronic device, so that electronic device generates live video stream according to live process data, live rule data and live content data, and live broadcast.Application of the present application does not need human intervention, through the cooperation of intelligent decision device and live data generation device, it can more intelligently organize live room.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a method for intelligent generation of live data in a network live streaming scenario and an intelligent decision-making device. BACKGROUND

[0002] With the development of live streaming technology, network live streaming is gradually selected by more and more users to achieve different purposes. For example, real-time live streaming of games, videos or sales of products, etc.

[0003] At present, the live streaming room of network live streaming needs human participation from planning to landing, for example, artificially designing the live streaming process of the live streaming room, artificially organizing the live streaming team, building the background of the live streaming room, collecting the images of anchors and collecting the sounds of anchors, etc. The intelligent degree of the live streaming room is low. SUMMARY

[0004] In order to solve the above technical problems, the present application provides a method for intelligent generation of live data in a network live streaming scenario and an intelligent decision-making device, which can more intelligently organize a live streaming room.

[0005] The technical scheme of the present application is as follows:

[0006] In a first aspect, the present application provides a method for intelligent generation of live data in a network live streaming scenario, applied to a live streaming system, the live streaming system further comprising a live data generation device connected with an intelligent decision-making device, the method comprising: acquiring demand data of a user; determining live streaming process data, live streaming rule data and live streaming content data corresponding to the demand data of the user according to the demand data of the user; sending the live streaming process data, the live streaming rule data and the live streaming content data to the live data generation device, so that the electronic device generates a live video stream according to the live streaming process data, the live streaming rule data and the live streaming content data for live streaming.

[0007] In combination with the first aspect, in another possible implementation manner, the live streaming process data, the live streaming rule data and the live streaming content data corresponding to the demand data of the user are determined according to the demand data of the user, comprising: preprocessing the demand data of the user to obtain live streaming feature data; processing the live streaming feature data by using a first decision-making model to obtain the live streaming process data, the live streaming rule data and the live streaming content data.

[0008] With reference to the first aspect, in a possible implementation manner, the live broadcast feature data comprises live broadcast type data and live broadcast product data, the first decision model is used to process the live broadcast feature data to obtain the live broadcast process data, the live broadcast rule data and the live broadcast content data, and the processing comprises: based on the live broadcast type data, the first decision layer in the first decision model is used to process the live broadcast type data to obtain preset live broadcast process data, preset live broadcast rule data and preset live broadcast content data corresponding to the live broadcast type data; and based on the live broadcast product data, the adjustment layer in the first decision model is used to adjust the preset live broadcast process data, the preset live broadcast rule data and the preset live broadcast content data to obtain the live broadcast process data, the live broadcast rule data and the live broadcast content data.

[0009] With reference to the first aspect, in a possible implementation manner, the method further comprises: in response to playing of the live broadcast video stream, obtaining live broadcast operation data of the live broadcast video stream; calling the second decision model to analyze and process the live broadcast operation data to obtain playing decision data, and sending the playing decision data to the live data generation device, so that the live data generation device displays live broadcast video stream adjustment information for the user according to the playing decision data.

[0010] With reference to the first aspect, in a possible implementation manner, the calling the second decision model to analyze and process the live broadcast operation data to obtain the playing decision data comprises: using the processing layer in the second decision model to process the live broadcast operation data to obtain target playing data corresponding to the live broadcast operation data; the target playing data comprises target process and target content; and using the second decision layer in the second decision model to process the target playing data to obtain the playing decision data.

[0011] With reference to the first aspect, in a possible implementation manner, the live broadcast operation data comprises commodity sales data, watching user retention rate, portrait data of watching users, new watching users and average watching user stay time.

[0012] In a second aspect, the present application provides an intelligent decision device in a network live broadcast scene, which is applied to a live broadcast system, and the live broadcast system further comprises a live data generation device connected with the intelligent decision device. The intelligent decision device comprises: an acquisition module, configured to acquire demand data of a user; a processing module, configured to determine live broadcast process data, live broadcast rule data and live broadcast content data corresponding to the demand data of the user according to the demand data of the user; and a sending module, configured to send the live broadcast process data, the live broadcast rule data and the live broadcast content data to the live data generation device, so that the live data generation device generates a live broadcast video stream according to the live broadcast process data, the live broadcast rule data and the live broadcast content data to live broadcast.

[0013] In a third aspect, an electronic device is provided, comprising a processor and a memory. The memory is configured to store computer instructions, and the processor is configured to execute the computer instructions stored in the memory to cause the electronic device to perform the method for intelligent generation of live streaming data in a network live streaming scenario according to the first aspect.

[0014] In a fourth aspect, a computer-readable storage medium is provided, which stores instructions. When the instructions are executed on an electronic device, the electronic device can perform the method for intelligent generation of live streaming data in a network live streaming scenario according to the first aspect.

[0015] In a fifth aspect, a computer program product is provided, which contains computer instructions. When the computer instructions are executed on an electronic device, the electronic device can perform the method for intelligent generation of live streaming data in a network live streaming scenario according to the first aspect.

[0016] In a sixth aspect, an apparatus (for example, the apparatus can be a chip system) is provided, which includes a processor configured to support an electronic device to implement the functions involved in the first aspect. In a possible design, the apparatus further includes a memory configured to store program instructions and data necessary for the electronic device. When the apparatus is a chip system, the apparatus can be composed of a chip or can include a chip and other discrete devices.

[0017] In the present application, the above-mentioned names do not constitute a limitation on the devices or function modules themselves. In actual implementation, these devices or function modules can appear in other names. As long as the functions of each device or function module are similar to those in the present application, they belong to the scope of the claims of the present application and their equivalents.

[0018] These aspects or other aspects of the present application will be more apparent in the following description.

[0019] The technical solutions provided by the present application have the following advantages compared with the prior art: the intelligent decision device obtains the demand data of the user, and then determines the live streaming process data, live streaming rule data and live streaming content data corresponding to the demand device. Then, the intelligent decision device can send the live streaming process data, live streaming rule data and live streaming content data to the live streaming data generation device, so that the live streaming data generation device generates a live streaming video stream. By using the technical solutions of the present application, the live streaming process data, live streaming rule data and live streaming content data required for live streaming are automatically generated by the intelligent decision device, and then the live streaming video stream is successfully generated for live streaming. In this technical solution, no human intervention is required, and the live streaming room can be more intelligently organized through the cooperation of the intelligent decision device and the live streaming data generation device. BRIEF DESCRIPTION OF DRAWINGS

[0020] The accompanying drawings, which are incorporated herein and constitute part of the specification, illustrate embodiments consistent with the application and, together with the description, further serve to explain the principles of the application.

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings required by the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings can also provide other drawings for those skilled in the art based on these drawings without any creative effort.

[0022] Figure 1 A structural schematic diagram of an implementation environment provided for the embodiments of the present application.

[0023] Figure 2 A structural schematic diagram of a live broadcast system provided for the embodiments of the present application.

[0024] Figure 3 A flowchart of a method for intelligent generation of live broadcast data in a network live broadcast scenario provided for the embodiments of the present application.

[0025] Figure 4 A flowchart of a method for intelligent generation of live broadcast data in a network live broadcast scenario provided for the embodiments of the present application.

[0026] Figure 5 A flowchart of a method for intelligent generation of live broadcast data in a network live broadcast scenario provided for the embodiments of the present application.

[0027] Figure 6 A structural schematic diagram of a first decision model provided for the embodiments of the present application.

[0028] Figure 7 A flowchart of a method for intelligent generation of live broadcast data in a network live broadcast scenario provided for the embodiments of the present application.

[0029] Figure 8 A display schematic diagram provided for the embodiments of the present application.

[0030] Figure 9 A flowchart of a method for intelligent generation of live broadcast data in a network live broadcast scenario provided for the embodiments of the present application.

[0031] Figure 10 A structural schematic diagram of a second decision model provided for the embodiments of the present application.

[0032] Figure 11 A structural schematic diagram of an intelligent decision device provided for the embodiments of the present application.

[0033] Figure 12A schematic diagram of a frame of an electronic device is provided. DETAILED DESCRIPTION

[0034] In order to more clearly understand the above objectives, features and advantages of the present application, the solutions of the present application will be further described below. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict, if possible.

[0035] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. The present application may, however, be practiced without the specific details. In other instances, well-known methods, procedures and components have not been described in detail so as not to obscure the present application.

[0036] It should be noted that, in this document, relational terms such as“first” and“second”, and the like, are used solely to distinguish one entity or action from another entity or action, without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms“comprises”,“comprising”, or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by“comprises a...” does not, without more constraints, exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element. The term“live video stream” refers to a sequence of digitally encoded data that is used to transmit from a live system to any live platform or terminal with no significant delay to live video. Thus, as used in this disclosure, a live video stream includes a data transmission from one computing device to another computing device (or to multiple computing devices), including a server or group of servers. A live video stream also includes a one-way broadcast of data from a live system (or group of servers) to a live platform or user terminal (or to multiple viewer devices).

[0037] To address the problems described in the background technology, this application provides an intelligent method for generating live streaming data and an intelligent decision-making device for network live streaming scenarios. In this method, the intelligent decision-making device, after acquiring user demand data, determines the live streaming process data, live streaming rule data, and live streaming content data corresponding to the demand device. Then, the intelligent decision-making device sends the live streaming process data, live streaming rule data, and live streaming content data to a live streaming data generation device, enabling the live streaming data generation device to generate a live video stream. Applying the technical solution of this disclosure, the intelligent decision-making device automatically generates the live streaming process data, live streaming rule data, and live streaming content data required for live streaming, thereby successfully generating a live video stream for live streaming. This technical solution does not require human intervention; through the cooperation of the intelligent decision-making device and the live streaming data generation device, a more intelligent live streaming room can be created.

[0038] The following describes the intelligent generation method for live streaming data in a network live streaming scenario provided by the embodiments of this application. Those skilled in the art will understand that, with the development of technology and the emergence of new scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0039] This application provides an embodiment of, as follows: Figure 1 The implementation environment shown may include a live streaming system 01, a live streaming platform 02, and a user terminal 03. The live streaming system 01 and the live streaming platform 02 can communicate via wired or wireless communication methods, and the live streaming platform 02 and the user terminal 03 can also communicate via wired or wireless communication methods.

[0040] The live streaming system 01 is mainly used to generate a live video stream and push the live video stream to the live streaming platform 02 for live streaming. In this embodiment of the application, the live streaming platform 02 may be one or more. Figure 1 This example uses only one live streaming platform, 02, and does not impose any specific restrictions.

[0041] The live streaming platform 02 is mainly used to push the live streaming data stream to the user terminal 03 according to specific rules after receiving the live video stream from the live streaming system 01, so that the user terminal 03 can play the live data corresponding to the live video stream for the user to watch. In this embodiment, there may be one or more user terminals 03. The user terminal 03 can be an electronic device with a live streaming application corresponding to the live streaming platform 02 installed.

[0042] like Figure 2 As shown, the live streaming system 01 includes an intelligent decision-making device 21 and a live streaming data generation device 22. The intelligent decision-making device 21 and the live streaming data generation device 22 can communicate with each other via wired or wireless means.

[0043] The intelligent decision-making device 21 can acquire user demand data and, based on this data, determine the corresponding live streaming process data, live streaming rule data, and live streaming content data. Then, the intelligent decision-making device 21 can send the live streaming process data, live streaming rule data, and live streaming content data to the live streaming data generation device 22, enabling the live streaming data generation device 22 to generate a live video stream for broadcasting based on the live streaming process data, live streaming rule data, and live streaming content data.

[0044] It should be noted that the intelligent decision-making device 21 and the live data generation device 22 in this application can be multiple separate devices, different functional parts of the same device, or modules that implement different functions in a data center, depending on actual needs. This application does not impose any specific restrictions on them.

[0045] Based on the aforementioned live streaming system, and referring to Figure 3 This application provides a flowchart of an intelligent method for generating live streaming data in a network live streaming scenario. (See attached flowchart.) Figure 3 As shown, the method may include steps 301-303.

[0046] Step 301: The intelligent decision-making device acquires user demand data.

[0047] User demand data can be used to describe live streaming rooms that meet user needs. For example, a live streaming room that meets user needs could be a product-selling live streaming room, selling small home appliances.

[0048] In some embodiments, users can directly provide their demand data to the intelligent decision-making device. For example, users can input demand data on a terminal or the intelligent decision-making device, allowing the device to acquire that data. Of course, the method by which users input demand data can be any feasible method, such as keyboard input, voice input, etc. This application does not impose specific limitations on this.

[0049] In another possible implementation, refer to Figure 2 As shown, the live streaming system may also include a data sensing device 23. The intelligent decision-making device can acquire user demand data through the data sensing device 23. For example, the data sensing device may include an order system. Users can publish demand data on the order system, and the data sensing device 23 can acquire the user's demand data through the order system.

[0050] Typically, users can enter their requirements in the order system in several different ways. For example, users can enter their requirements as text, as audio, or by selecting from a variety of requirements options provided by the order system.

[0051] Step 302: The intelligent decision-making device determines the live streaming process data, live streaming rule data, and live streaming content data corresponding to the user's demand data.

[0052] After acquiring user demand data, the intelligent decision-making device processes this data to obtain the corresponding live stream flow data, live stream rules data, and live stream content data for the desired live stream. The live stream flow data helps ensure that the live stream segments better meet user expectations, thereby increasing the live stream's popularity. The live stream rules data helps increase the live stream's interactivity and improve user retention. The live stream content data helps enrich the live stream's content, thereby attracting more users to stay in the live stream.

[0053] For example, live streaming process data can correspond to the live streaming flow of a live streaming room. Live streaming rule data can be live streaming rules generated by intelligent decision-making devices based on user demand data. Live streaming content data includes live streaming image data and live streaming audio data. For example, in addition to live streaming image data and live streaming audio data, live streaming content data can also include all content that enables a live streaming room. For example, live streaming content data includes host information, script information, live streaming background information, and product information, etc.

[0054] In some embodiments, such as Figure 4 As shown above, in the above Figure 3 Based on the illustrated embodiment, step 302 includes the following steps:

[0055] Step 3021: The intelligent decision-making device preprocesses the user's demand data to obtain live broadcast feature data.

[0056] Since users can input their requirements in various formats, the intelligent decision-making device needs to preprocess this data based on its format. For example, if the user inputs text, the device could perform semantic analysis to output the corresponding semantic results, thus obtaining the live stream feature data. Similarly, if the user inputs audio, the device could convert the audio to text, perform semantic analysis, and output the corresponding semantic results, again yielding the live stream feature data. Furthermore, if the user selects from multiple options provided by the device, the device can then obtain the live stream feature data based on the selected option.

[0057] For example, the user inputs the request data as "create a live-streaming room for selling kitchenware." The intelligent decision-making device preprocesses the user's request data and outputs live-streaming feature data as "live-streaming room for selling kitchenware" and "kitchenware." After obtaining the live-streaming feature data, the live-streaming process data, live-streaming rules data, and live-streaming content data can be determined based on this data.

[0058] Step 3022: The intelligent decision-making device receives the live broadcast feature data, processes the live broadcast feature data using the first decision model, and obtains live broadcast process data, live broadcast rule data, and live broadcast content data.

[0059] After receiving live stream feature data, the intelligent decision-making device processes the data using a primary decision-making model, resulting in live stream flow data, live stream rule data, and live stream content data. These data contain all the information required for a live stream to meet user needs. For example, the live stream flow data includes flow information, the live stream rule data includes rule information, and the live stream content data includes host information, script information, live stream background information, and product information.

[0060] The process information in the live stream workflow data can include all information related to the live stream and its workflow. For example, in chronological order, the live stream workflow is as follows: opening, warm-up, product launch, fan appreciation, and closing. Each workflow is strictly limited by time, defining the current live stream workflow. During the live stream, this workflow information serves as a guide for the digital human anchor's speech throughout the entire event, instructing the anchor to use specific phrases within each workflow segment.

[0061] The rule information in the live streaming rule data can include the live streaming rules throughout the entire live streaming process. For example, this rule information can include the timing rules for the digital human anchor to promote products (referred to as promotion rules), the timing rules for the digital human anchor to guide viewers to buy products (referred to as interaction rules), the rules for the digital human anchor to answer viewers' questions (referred to as response rules), the timing rules for the digital human anchor to explain products (referred to as explanation rules), and response rules for events such as bullet screen events and / or traffic events (events such as the number of likes reaching a threshold or the number of bullet screen comments reaching a threshold).

[0062] In this embodiment of the application, to avoid the broadcaster being negatively affected by the external environment, the broadcaster can be a digital human broadcaster. Therefore, the broadcaster information in the live broadcast content data can include the digital human broadcaster's image information and voice information. The image information can include the digital human broadcaster's expressions, movements, clothing, body characteristics, facial features, etc. The voice information can include the digital human broadcaster's voice characteristics (e.g., timbre).

[0063] The script information in the live stream content data can include the scripts spoken by the digital human host in different parts of the live stream and the scripts corresponding to the interaction rules. For example, the scripts corresponding to the live stream process can specifically include opening scripts, warm-up scripts, product introduction scripts, fan appreciation scripts, and closing scripts. The scripts corresponding to the interaction rules can include: promotional scripts (used to promote products), guiding scripts (used to guide users to buy products), explanation scripts (used to explain products), interactive scripts (used to enhance the atmosphere of the live stream), bullet screen response scripts (used to respond to bullet screen questions, etc.), and event response scripts (used to respond to specific live stream events), etc. Taking interactive scripts as an example, when viewers in the live stream request freebies, the digital human host can say something like, "Please like this post a lot. The more likes, the more freebies the host can apply for!"

[0064] The background information of the live streaming room in the live streaming content data can include the background features of the entire live streaming room. For example, the background information of the live streaming room can include: specific background content (such as a textured kitchen background), background lighting parameters (brightness, orientation, etc.), background music, and parameters of the decorations in the background (position, size, etc.).

[0065] The product information in the live stream content data can include content related to the products for sale, such as the corresponding sales pitch and product materials (product images, product videos, product inspection reports, etc.).

[0066] In one feasible approach, as described in this embodiment, the various types of data in the live streaming process data, live streaming rule data, and live streaming content data can be pre-stored. The first decision model can determine the data matching the live streaming feature data based on the pre-stored data to obtain the live streaming process data, live streaming rule data, and live streaming content data.

[0067] In another possible implementation, in this embodiment of the application, the first decision model can be trained based on various live streaming process data, live streaming rule data, live streaming content data, and corresponding live streaming feature data. Therefore, the first decision model can generate corresponding live streaming process data, live streaming rule data, and live streaming content data based on the live streaming feature data.

[0068] Afterwards, the live streaming process data, live streaming rules data, and live streaming content data can be sent to the live streaming data generation device to create a live streaming room.

[0069] Step 303: The intelligent decision-making device sends live streaming process data, live streaming rule data, and live streaming content data to the live streaming data generation device, so that the live streaming data generation device can generate a live video stream for live streaming based on the live streaming process data, live streaming rule data, and live streaming content data.

[0070] The intelligent decision-making device determines the live streaming process data, live streaming rules data, and live streaming content data, and then sends these data to the live streaming data generation device. After receiving the live streaming process data, rules data, and content data, the live streaming data generation device merges these data to generate a live video stream. By playing this live video stream, the live streaming room is displayed to viewers.

[0071] In another feasible approach, the live streaming data generation device can include a process-driven device and a content expression device. After the intelligent decision-making device processes the live streaming process data, live streaming rule data, and live streaming content data, the process-driven device within the live streaming data generation device can generate the live streaming process and rules based on the process and rule data. The content expression device within the live streaming data generation device can generate the live streaming content based on the content data. Finally, the live streaming data generation device integrates the live streaming process, rules, and content to generate a live video stream.

[0072] Afterwards, the live data generation device can push the live video stream to the live streaming platform 02, so that the live streaming platform 02 can push the live video stream to the user terminal 03 for live streaming, thereby displaying the live room to the viewing users.

[0073] This disclosure provides an intelligent method for generating live streaming data in a network live streaming scenario. An intelligent decision-making device, after acquiring user demand data, determines the corresponding live streaming process data, live streaming rule data, and live streaming content data. Then, the intelligent decision-making device sends the live streaming process data, live streaming rule data, and live streaming content data to a live streaming data generation device, enabling the live streaming data generation device to generate a live video stream. Applying the technical solution of this disclosure, the intelligent decision-making device automatically generates the necessary live streaming process data, live streaming rule data, and live streaming content data, thereby successfully generating a live video stream for live streaming. This technical solution requires no human intervention; through the cooperation of the intelligent decision-making device and the live streaming data generation device, a more intelligent live streaming room can be created.

[0074] In some embodiments, such as Figure 5 As shown above, in the above Figure 3 Based on the embodiment shown, step 3022 above, "processing the live broadcast feature data using the first decision model to obtain live broadcast process data, live broadcast rule data, and live broadcast content data", may include steps 501-502.

[0075] Step 501: Based on the live streaming type data, process the live streaming type data using the first decision layer in the first decision model to obtain the preset live streaming process data, preset live streaming rule data, and preset live streaming content data corresponding to the live streaming type data.

[0076] The live streaming feature data includes live streaming type data and live streaming product data.

[0077] like Figure 6 As shown, the first decision-making model includes a first decision layer and an adjustment layer. The first decision layer generates preset live streaming process data, preset live streaming rule data, and preset live streaming content data corresponding to the live streaming type data. The adjustment layer adjusts the preset live streaming process data, preset live streaming rule data, and preset live streaming content data according to user needs, so that the resulting live streaming process data, live streaming rule data, and live streaming content data better meet user requirements.

[0078] In this embodiment, the first decision model can be trained based on live streaming feature data, live streaming process data, live streaming rule data, and live streaming content data of various types of live streaming rooms. The specific training method can be any feasible method, and this embodiment does not impose any specific restrictions on it.

[0079] For example, live stream type data is used to mark the type of live stream room. Live stream type data can include live stream rooms for e-commerce, chat live stream rooms, educational live stream rooms, etc. When the live stream type data is a live stream room for e-commerce, the first decision layer can generate preset live stream process data, preset live stream rule data, and preset live stream content data corresponding to the live stream room for e-commerce.

[0080] Step 502: Based on the live streaming product data, adjust the preset live streaming process data, preset live streaming rule data, and preset live streaming content data using the adjustment layer in the first decision model to obtain the live streaming process data, live streaming rule data, and live streaming content data.

[0081] After obtaining the preset live streaming process data, preset live streaming rule data, and preset live streaming content data, adjustments can be made to these data based on the live streaming product data by calling the adjustment layer in the first decision model. This process adjusts the preset live streaming process data, preset live streaming rule data, and preset live streaming content data to obtain the final live streaming process data, live streaming rule data, and live streaming content data. The live streaming product data indicates the specific products in the live streaming room, such as rice cookers, frying pans, books, courseware, and e-readers.

[0082] For example, based on the live-streaming product data, you can adjust the sales duration of each live-streaming product in the preset live-streaming process data, and adjust the wording and descriptions of the live-streaming products in the live-streaming content data, etc.

[0083] During live streaming, the large volume and variety of data involved make adjustments difficult, hindering the adaptive nature of the process. To improve the live stream's effectiveness by continuously adjusting the content based on operational data, the intelligent decision-making device within the live streaming system can further refine the content based on operational data. Therefore, in some embodiments, such as... Figure 7 As shown above, in the above Figure 3 Based on the illustrated embodiment, the method further includes the following steps:

[0084] Step 701: In response to the playback of the live video stream, the intelligent decision-making device acquires the live operation data of the live video stream.

[0085] After the live video stream is generated, it can be played on the live streaming platform 02. When the intelligent decision-making device detects that the live video stream is playing, it will simultaneously acquire the live streaming operation data of the live video stream. The live streaming operation data of the live video stream is used to characterize the current live streaming status and / or live streaming effect of the live streaming room.

[0086] In some embodiments, the live streaming operation data of the live video stream may include product sales revenue, sales volume data, live stream viewer retention rate, live stream viewer profile data, live stream interaction data, total number of viewers, peak popularity, new viewers, average viewer dwell time, follower growth trend, number of new followers, etc.

[0087] Step 702: The intelligent decision-making device calls the second decision-making model to analyze and process the live broadcast operation data, obtains playback decision data, and transmits the playback decision data to the live broadcast data generation device so that the live broadcast data generation device displays live video stream adjustment information to the user according to the playback decision data.

[0088] The intelligent decision-making device analyzes and processes the live streaming operation data using a second decision-making model to obtain corresponding playback decision data. This playback decision data provides users with better playback options (including adjusting scripts or flow), making the adjusted live stream more suitable for the current live streaming status. Subsequently, the intelligent decision-making device sends this playback decision data to the live streaming data generation device to generate prompts for users to adjust the live video stream.

[0089] For example, playback decision data may include changing product materials, extending a certain live broadcast segment, skipping a certain live broadcast segment, adding interactive dialogue, adding a chatbot, etc.

[0090] After receiving playback decision data, the live streaming data generation device can generate prompts based on that data. These prompts are then displayed on the terminal's screen, scrolling dynamically to guide users in adjusting the current live video stream for a better viewing experience. The prompts specifically advise users to adjust the live video stream according to the playback decision data.

[0091] For example, refer to Figure 8 After generating the prompt message, it can be displayed on the user's terminal. The prompt message reads, "The current live stream's popularity is low. Do you wish to switch to the giveaway process?" Upon receiving the user's confirmation of the prompt message, the terminal can respond to the confirmation and control the live stream to switch to the giveaway process.

[0092] It should be noted that, Figure 8 The example given uses a laptop computer as the user terminal, on which the client software for the live streaming system can be installed to achieve the aforementioned functions. In practice, if the performance of small electronic devices such as mobile phones is sufficient, the user terminal can also be a small electronic device such as a mobile phone; this application does not impose specific restrictions in this regard.

[0093] In some embodiments, such as Figure 9 As shown above, in the above Figure 7 Based on the embodiment shown, step 302 above, "processing the live operation data using the second decision model to obtain playback decision data", may include steps 901-902.

[0094] Step 901: Use the processing layer in the second decision model to process the live streaming operation data to obtain the target playback data corresponding to the live streaming operation data.

[0095] The target playback data includes the target flow and the target content.

[0096] like Figure 10 As shown, the second decision-making model includes a processing layer and a second decision-making layer. The processing layer analyzes the live streaming operation data to determine the target playback data corresponding to the current live streaming operation data.

[0097] In this embodiment, the second decision model can be trained based on live streaming operation data of various types of live streaming rooms, decision data corresponding to the live streaming operation data, adjusted live streaming video stream obtained by adjusting the live streaming content based on the decision data, and live streaming operation data corresponding to the adjusted live streaming video stream. The specific training method can be any feasible method, and this embodiment does not impose any specific restrictions on it.

[0098] The target playback data can be the target flow and content in the live video stream when the live operation data is good. For example, live operation data includes the follower growth trend, which is data that changes continuously based on the live broadcast time. When the follower growth trend in a certain time period reaches the target trend (e.g., 8 new followers every 30 minutes), the playback data corresponding to that time period can be used as the target playback data.

[0099] Step 902: Process the target playback data using the second decision layer in the second decision model to obtain playback decision data.

[0100] After obtaining the target playback data, the second decision-making layer can process it. This includes analyzing the playback flow and wording to determine which flow, wording, or background significantly increases the number of comments or followers. Based on this analysis, playback decision data can then be generated and displayed as a prompt on the user's device, guiding them to adjust their live stream accordingly to improve the overall viewing experience.

[0101] In addition, the second decision-making layer can determine better scripts and content based on the analysis results of the target playback data, and present the better scripts and content to users in the form of playback decision data, so that users can adjust the scripts and content corresponding to the time periods when the live broadcast operation data is not good based on the playback decision data.

[0102] In some other embodiments, after obtaining the analysis results of the target playback data, these results can be stored in a second decision model. When playback decision data needs to be provided for other live streaming rooms, previous analysis data from live streaming rooms of the same type can be referenced.

[0103] The foregoing mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, it includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0104] This application embodiment can divide the electronic device into functional modules according to the above method example. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0105] Corresponding to the methods in the foregoing embodiments, this application also provides an intelligent decision-making device. This intelligent decision-making device is used to implement the aforementioned intelligent generation method for live streaming data in a network live streaming scenario. The functions of this intelligent decision-making device can be implemented through hardware or through hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions.

[0106] For example, Figure 11 A schematic diagram of the structure of an intelligent decision-making device in a live streaming scenario is shown, such as... Figure 11As shown, the intelligent decision-making device may include: an acquisition module 1101, a processing module 1102, and a sending module 1103. The acquisition module 1101 is used to acquire user demand data; the processing module 1102 is used to determine live streaming process data, live streaming rule data, and live streaming content data corresponding to the user demand data; the sending module 1103 is used to send the live streaming process data, live streaming rule data, and live streaming content data to a live streaming data generation device, so that the live streaming data generation device can generate a live video stream for live streaming based on the live streaming process data, live streaming rule data, and live streaming content data.

[0107] In some feasible examples, the processing module 1102 is also used to preprocess the user's demand data to obtain live streaming feature data and to process the live streaming feature data using a first decision model to obtain live streaming process data, live streaming rule data, and live streaming content data.

[0108] In some feasible examples, the live streaming feature data includes live streaming type data and live streaming product data. The processing module 1102 is also used to process the live streaming type data based on the live streaming type data using the first decision layer in the first decision model to obtain the preset live streaming process data, preset live streaming rule data, and preset live streaming content data corresponding to the live streaming type data; and to adjust the preset live streaming process data, preset live streaming rule data, and preset live streaming content data based on the live streaming product data using the adjustment layer in the first decision model to obtain the live streaming process data, live streaming rule data, and live streaming content data.

[0109] In some feasible examples, the acquisition module 1101 is also used to acquire live operation data of the live video stream in response to the playback of the live video stream; the processing module 1102 is also used to call the second decision model to analyze and process the live operation data, obtain playback decision data, and play the decision data to the live data generation device so that the live data generation device displays live video stream adjustment information to the user according to the playback decision data.

[0110] In some feasible examples, the processing module 1102 is also used to process the live operation data using the processing layer in the second decision model to obtain the target playback data corresponding to the live operation data; the target playback data includes the target process and the target content; and to process the target playback data using the second decision layer in the second decision model to obtain playback decision data.

[0111] In some feasible examples, live streaming operation data includes product sales data, viewer retention rate, viewer profile data, new viewer, and average viewer dwell time.

[0112] Figure 12A structural diagram of an electronic device provided in this disclosure embodiment, such as... Figure 12 As shown, the electronic device 1200 includes one or more processors 1201 and memory 1202.

[0113] The processor 1201 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 1200 to perform desired functions.

[0114] The memory 1202 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 1201 may execute the program instructions to implement the intelligent generation method for live streaming data in the network live streaming scenario of the various embodiments of this disclosure described above, and / or other desired functions.

[0115] In one example, the electronic device 1200 may also include an input device 1203 and an output device 1204, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0116] Of course, for the sake of simplicity, Figure 12 Only some of the components of the electronic device 1200 relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device 1200 may include any other suitable components depending on the specific application.

[0117] In addition to the methods and devices described above, embodiments of this disclosure may also be computer program products, including computer program instructions that, when executed by a processor, cause the processor to perform the steps in the intelligent generation method for live streaming data in a network live streaming scenario according to various embodiments of this disclosure as described in the "Exemplary Methods" section of this specification.

[0118] Computer program products can be written in any combination of one or more programming languages ​​to perform the operations of embodiments of this disclosure. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0119] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the intelligent generation method for live streaming data in a network live streaming scenario according to various embodiments of this disclosure as described in the "Exemplary Methods" section above.

[0120] Computer-readable storage media may take the form of any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0121] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0122] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0123] It should also be noted that in the apparatus, devices, and methods of this disclosure, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions to this disclosure.

[0124] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0125] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A method for intelligently generating live streaming data in a network live streaming scenario, applied to a live streaming system, wherein the live streaming system further includes a live streaming data generation device connected to an intelligent decision-making device, characterized in that, The live data generation device includes a process-driven device and a content expression device; wherein, the intelligent decision-making device is used to determine the live process data, live rule data, and live content data, and sends the live process data, live rule data, and live content data to the live data generation device; In the live streaming data generation device, the process driving device is used to generate live streaming process and live streaming rules based on live streaming process data and live streaming rule data, and the content expression device is used to generate live streaming content based on live streaming content data. The live streaming data generation device is also used to generate live streaming video stream based on live streaming process, live streaming rules and live streaming content. The method includes: Obtain demand data to describe live streaming rooms that meet user needs; Preprocessing is performed on the demand data to obtain live streaming feature data, which includes live streaming type data and live streaming product data used to mark the type of live streaming room. Based on the live streaming type data, the first decision layer in the first decision model is used to process the live streaming type data to obtain the preset live streaming process data, preset live streaming rule data, and preset live streaming content data corresponding to the live streaming type data. Based on the live streaming product data, the preset live streaming process data, the preset live streaming rule data, and the preset live streaming content data are adjusted using the adjustment layer in the first decision model to obtain the live streaming process data, the live streaming rule data, and the live streaming content data. The live streaming process data, live streaming rule data, and live streaming content data are sent to the live streaming data generation device so that the electronic device can generate a live streaming video stream based on the live streaming process data, live streaming rule data, and live streaming content data. The live video stream is pushed to the user terminal so that the user terminal can play the live video stream. In response to the playback of the live video stream, obtain the live operation data of the live video stream; The second decision model is invoked to analyze and process the live streaming operation data to obtain playback decision data; the playback decision data includes changing product materials, extending the live streaming process, skipping the live streaming process, adding interactive dialogue, or adding a response robot. Based on the playback decision data, a prompt message is generated, which is used to prompt the user to adjust the live video stream of the current live room according to the playback decision data; In response to the user's confirmation operation on the prompt information, the playback decision data is sent to the live streaming data generation device so that the live streaming data generation device can display the target playback data corresponding to the current operation data to the user according to the playback decision data. The target playback data is the target flow and target content in the live streaming video stream when the live streaming operation data is good.

2. The method according to claim 1, characterized in that, The step of calling the second decision model to analyze and process the live streaming operation data to obtain playback decision data includes: The live streaming operation data is processed using the processing layer in the second decision model to obtain the target playback data corresponding to the live streaming operation data; the target playback data includes the target flow and the target content. The target playback data is processed using the second decision layer in the second decision model to obtain the playback decision data.

3. The method according to claim 1, characterized in that, The live streaming operation data includes product sales data, viewer retention rate, viewer profile data, new viewer, and average viewer dwell time.

4. An intelligent decision-making device for a live streaming scenario, applied to a live streaming system, wherein the live streaming system further includes a live streaming data generation device connected to the intelligent decision-making device, characterized in that, The live data generation device includes a process-driven device and a content expression device; wherein, the intelligent decision-making device is used to determine the live process data, live rule data, and live content data, and sends the live process data, live rule data, and live content data to the live data generation device; In the live streaming data generation device, the process driving device is used to generate live streaming process and live streaming rules based on live streaming process data and live streaming rule data, and the content expression device is used to generate live streaming content based on live streaming content data. The live streaming data generation device is also used to generate live streaming video stream based on live streaming process, live streaming rules and live streaming content. The intelligent decision-making device includes: The acquisition module is used to describe the demand data of the live streaming room that meets the user's needs; The processing module is used to perform preprocessing on the demand data to obtain live streaming feature data, which includes live streaming type data and live streaming product data used to mark the type of live streaming room. Based on the live streaming type data, the first decision layer in the first decision model is used to process the live streaming type data to obtain the preset live streaming process data, preset live streaming rule data, and preset live streaming content data corresponding to the live streaming type data. Based on the live streaming product data, the preset live streaming process data, the preset live streaming rule data, and the preset live streaming content data are adjusted using the adjustment layer in the first decision model to obtain the live streaming process data, the live streaming rule data, and the live streaming content data. The sending module is used to send the live streaming process data, live streaming rule data, and live streaming content data to the live streaming data generation device, so that the live streaming data generation device can generate a live video stream for live streaming based on the live streaming process data, live streaming rule data, and live streaming content data; The live video stream is pushed to the user terminal so that the user terminal can play the live video stream. In response to the playback of the live video stream, obtain the live operation data of the live video stream; The second decision model is invoked to analyze and process the live streaming operation data to obtain playback decision data, which includes changing product materials, extending the live streaming process, skipping the live streaming process, adding interactive dialogue, or adding a response robot. Based on the playback decision data, a prompt message is generated, which is used to prompt the user to adjust the live video stream of the current live room according to the playback decision data; In response to the user's confirmation operation on the prompt information, the playback decision data is sent to the live streaming data generation device so that the live streaming data generation device can display the target playback data corresponding to the current operation data to the user according to the playback decision data. The target playback data is the target flow and target content in the live streaming video stream when the live streaming operation data is good.

5. An electronic device, characterized in that, include: A memory and a processor, wherein the memory is used to store a computer program; and the processor is used to cause the electronic device to implement the intelligent generation method for live streaming data in any one of claims 1-3 when executing the computer program.

6. A computer-readable storage medium, characterized in that, Includes computer instructions; When the computer instructions are executed on the electronic device, the electronic device performs the intelligent generation method for live streaming data in the network live streaming scenario as described in any one of claims 1-3.

7. A live streaming system, characterized in that, Including the intelligent decision-making device as described in claim 4.

Images