Live streaming method, device and storage medium

Abstract

The application discloses a live broadcast method, device and storage medium, and belongs to the technical field of live broadcast. The method comprises the following steps: receiving a setting operation of preferential information, wherein the preferential information is used for determining a total preferential range of a first live broadcast session; receiving a setting operation of a live broadcast target, wherein the live broadcast target is used for indicating a target value expected to be achieved by the first live broadcast session in at least one evaluation dimension; and displaying a first preferential activity in a live broadcast process of the first live broadcast session, wherein the first preferential activity is generated based on live broadcast data of the first live broadcast session, the preferential information and the live broadcast target. The method can accurately generate a preferential activity of live broadcast.

Description

TECHNICAL FIELD

[0001] The present application relates to the live broadcast technical field, and particularly relates to a live broadcast method, equipment and storage medium. BACKGROUND

[0002] Digital person live broadcast refers to a live broadcast form in which a virtual character (i.e., a digital person) generated based on artificial intelligence, computer graphics and the like is taken as an anchor, the digital person is projected into a virtual or real scene through real-time rendering and animation technology, and real-time performance and interaction are performed.

[0003] In the related art, when a digital person live broadcast is enabled in a live broadcast room, a live broadcast application program can generate an introduction script of a commodity based on preset commodity information, control a digital person to introduce the commodity according to the introduction script, and can also generate a reply text based on comments of viewers in the live broadcast room, and control the digital person to reply to the comments of the viewers according to the reply text.

[0004] However, the digital person live broadcast in the related art only supports commodity explanation and simple viewer interaction, and lacks the ability to attract viewers to stay and place orders. SUMMARY

[0005] The present application provides a live broadcast method, equipment and storage medium, which can improve the efficiency of digital person live broadcast. The technical solution is as follows:

[0006] According to an aspect of the present application, a live broadcast method is provided, the method is executed by an anchor client, and the method comprises the following steps.

[0007] Receiving a setting operation of discount information, the discount information is used to determine a total discount range of a first live broadcast session;

[0008] Receiving a setting operation of a live broadcast target, the live broadcast target is used to indicate a target value expected to be achieved by the first live broadcast session in at least one evaluation dimension;

[0009] Displaying a first discount activity in a live broadcast process of the first live broadcast session;

[0010] The first discount activity is generated based on live broadcast data of the first live broadcast session, the discount information and the live broadcast target.

[0011] According to another aspect of the present application, a live broadcast method is provided, the method is executed by a server, and the method comprises the following steps.

[0012] Receiving discount information set by an anchor client, the discount information is used to determine a total discount range of a first live broadcast session;

[0013] receive a live broadcast target set by the anchor client, the live broadcast target being used to indicate a target value expected to be achieved by the first live broadcast session in at least one evaluation dimension;

[0014] generate and send a first preferential activity during live broadcast of the first live broadcast session;

[0015] The first preferential activity is generated based on live broadcast data of the first live broadcast session, the preferential information and the live broadcast target.

[0016] According to another aspect of the present application, a live broadcast method is provided, the method being performed by a spectator client, and the method comprising:

[0017] playing a first live broadcast session;

[0018] displaying a first preferential activity of the first live broadcast session;

[0019] The first preferential activity is generated based on live broadcast data of the first live broadcast session, preferential information and a live broadcast target; the preferential information and the live broadcast target are set by a management account of the first live broadcast session; the preferential information is used to determine a total preferential range of the first live broadcast session; and the live broadcast target is used to indicate a target value expected to be achieved by the first live broadcast session in at least one evaluation dimension.

[0020] According to another aspect of the present application, a live broadcast device is provided, the device comprising:

[0021] a first interaction module configured to receive a setting operation of preferential information, the preferential information being used to determine a total preferential range of a first live broadcast session;

[0022] The first interaction module is configured to receive a setting operation of a live broadcast target, the live broadcast target being used to indicate a target value expected to be achieved by the first live broadcast session in at least one evaluation dimension.

[0023] a first display module configured to display a first preferential activity during live broadcast of the first live broadcast session;

[0024] The first preferential activity is generated based on live broadcast data of the first live broadcast session, the preferential information and the live broadcast target.

[0025] According to another aspect of the present application, a live broadcast device is provided, the device comprising:

[0026] a first receiving module configured to receive preferential information set by an anchor client, the preferential information being used to determine a total preferential range of a first live broadcast session;

[0027] The first receiving module is configured to receive a live broadcast target set by the anchor client, the live broadcast target being used to indicate a target value expected to be achieved by the first live broadcast session in at least one evaluation dimension.

[0028] The second generating module is configured to generate and send a first preferential activity during live broadcast of the first live broadcast session.

[0029] The first preferential activity is generated based on live broadcast data of the first live broadcast session, the preferential information, and the live broadcast target.

[0030] According to another aspect of the present application, a live broadcast device is provided, and the device comprises:

[0031] The second display module is configured to play the first live broadcast session.

[0032] The second display module is configured to display the first preferential activity of the first live broadcast session.

[0033] The first preferential activity is generated based on live broadcast data of the first live broadcast session, preferential information, and a live broadcast target; the preferential information and the live broadcast target are set by a management account of the first live broadcast session; the preferential information is used to determine a total preferential range of the first live broadcast session; and the live broadcast target is used to indicate a target value expected to be achieved by the first live broadcast session in at least one evaluation dimension.

[0034] According to another aspect of the present application, a computer device is provided, and the computer device comprises a processor and a memory, the memory storing at least one instruction, at least one program, a code set, or an instruction set, the at least one instruction, the at least one program, the code set, or the instruction set being loaded and executed by the processor to implement the live broadcast method according to the above aspect.

[0035] According to another aspect of the present application, a computer readable storage medium is provided, and the readable storage medium stores at least one instruction, at least one program, a code set, or an instruction set, the at least one instruction, the at least one program, the code set, or the instruction set being loaded and executed by a processor to implement the live broadcast method according to the above aspect.

[0036] According to another aspect of the present application, a computer program product or a computer program is provided, and the computer program product or the computer program comprises computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to enable the computer device to perform the live broadcast method provided in various optional implementation manners of the above aspect.

[0037] The technical scheme provided by the application has at least the following beneficial effects:

[0038] By setting the preferential information and the live broadcast target, the live broadcast application can accurately generate the preferential activity of the live broadcast based on the live broadcast data, the preferential information and the live broadcast target. The live broadcast application can select appropriate preferential time, preferential mode and preferential strength, automatically generate the preferential activity suitable for the current live broadcast situation, reduce the manual operation cost in the live broadcast process, and expand the service capability of the digital person live broadcast. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical scheme in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0040] Figure 1 is a structural schematic diagram of a computer system provided by an exemplary embodiment of the present application;

[0041] Figure 2 is a flowchart of a live broadcast method provided by an exemplary embodiment of the present application;

[0042] Figure 3 is a schematic diagram of a live broadcast method provided by an exemplary embodiment of the present application;

[0043] Figure 4 is a schematic diagram of a live broadcast method provided by an exemplary embodiment of the present application;

[0044] Figure 5 is a schematic diagram of a live broadcast method provided by an exemplary embodiment of the present application;

[0045] Figure 6 is a schematic diagram of a live broadcast method provided by an exemplary embodiment of the present application;

[0046] Figure 7 is a flowchart of a live broadcast method provided by an exemplary embodiment of the present application;

[0047] Figure 8 is a flowchart of a live broadcast method provided by an exemplary embodiment of the present application;

[0048] Figure 9 is a flowchart of a live broadcast method provided by an exemplary embodiment of the present application;

[0049] Figure 10is a schematic diagram of a live broadcast method provided by an example embodiment of the present application;

[0050] Figure 11 is a flowchart of a live broadcast method provided by an example embodiment of the present application;

[0051] Figure 12 is a structural schematic diagram of a live broadcast device provided by an example embodiment of the present application;

[0052] Figure 13 is a structural schematic diagram of a live broadcast device provided by an example embodiment of the present application;

[0053] Figure 14 is a structural schematic diagram of a live broadcast device provided by an example embodiment of the present application;

[0054] Figure 15 is a structural schematic diagram of a computer device provided by an example embodiment of the present application.

[0055] The accompanying drawings, which are incorporated herein and form part of the specification, illustrate embodiments consistent with the present application and, together with the description, further serve to explain the principles of the present application. DETAILED DESCRIPTION

[0056] For the purpose of making the objects, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0057] Figure 1 is a schematic diagram of a computer system provided by an example embodiment of the present application, which can include a terminal device 101 and a server 103.

[0058] By way of example, the live broadcast method shown in the embodiments of the present application can be applied in a terminal device or a server, and the terminal device 101 is installed with a live broadcast client. The terminal device can include a mobile phone, a tablet computer, a notebook computer, a laptop computer, a desktop computer, an all-in-one computer, an Internet of Things device, a smart robot workstation, a television, a set-top box, smart glasses, a smart watch, a digital camera, an MP4 player, an MP5 player, a learning machine, a point-reading machine, an electronic paper, an electronic dictionary, a vehicle-mounted device, a virtual reality (VR) player or an augmented reality (AR) player, etc.

[0059] Exemplarily, the live streaming method provided in this application can be executed by a client (anchor client or audience client) in a terminal device. The client can be a client of an application 102 supporting live streaming function. When the live streaming method provided in the embodiments of this application needs to be used, the anchor client receives the operation of setting the preferential information and the live streaming target by the anchor, and reports the preferential information and the live streaming target to the server. The server generates a preferential activity based on the real-time live streaming data of the live streaming room according to the preferential information and the live streaming target set by the anchor.

[0060] The terminal device 101 comprises a first memory and a first processor. The first memory stores a live streaming program; the live streaming program is called and executed by the first processor to implement the live streaming method provided in this application. The first memory can include but is not limited to the following: random access memory (RAM), read only memory (ROM), programmable read only memory (PROM), erasable programmable read only memory (EPROM), and electrically erasable programmable read only memory (EEPROM).

[0061] The first processor can be composed of one or more integrated circuit chips. Optionally, the first processor can be a general-purpose processor, such as a central processing unit (CPU) or a network processor (NP). Optionally, the first processor can implement the live streaming method provided in this application by running programs or codes.

[0062] In an optional embodiment, the terminal device 101 and the server 103 can be connected with each other through a wired or wireless network.

[0063] The server 103 is used to provide background service for the live streaming client of the terminal device 101. Optionally, the server 103 undertakes the main computing work, and the terminal device 101 undertakes the secondary computing work; or the server 103 undertakes the secondary computing work, and the terminal device 101 undertakes the main computing work; or the server 103 and the terminal device 101 adopt a distributed computing architecture for collaborative computing.

[0064] The server 103 can be a server, a server cluster composed of multiple servers, or a cloud computing service center.

[0065] Optionally, the server 103 comprises a second memory and a second processor. The second memory stores a live broadcast program, and the second processor invokes the live broadcast program to implement the live broadcast method provided in the present application. The second memory can include, but is not limited to, RAM, ROM, PROM, EPROM, EEPROM, and the like. The second processor can be a general-purpose processor, such as a CPU or an NP.

[0066] Figure 2 FIG. 1 is a flowchart of a live broadcast method provided in an example embodiment of the present application. The method can be used in a terminal device or a host client in a terminal device as shown in FIG. 2. Figure 1 The method comprises the following steps.

[0067] In step 210, a setting operation of discount information is received, and the discount information is used to determine a total discount range of a first live broadcast session.

[0068] The method can be executed by a host terminal, and the host terminal has a host client of a live broadcast application installed thereon, and the host client has a host account logged in thereon. The host account has a management permission of a first live broadcast room. The first live broadcast session is a live broadcast in the first live broadcast room.

[0069] Optionally, the host client can display a live broadcast management interface of the first live broadcast session, and the live broadcast management interface has a discount information setting control displayed thereon. In response to receiving an operation of triggering the discount information setting control to set discount information, the host client obtains the discount information set by the host account and reports the discount information.

[0070] The host can set the discount information during the live broadcast of the first live broadcast session, or the host can set the discount information in advance before the first live broadcast session starts.

[0071] Optionally, the discount information is used to indicate a discount amount provided by a discount activity in the first live broadcast session. For example, the discount information is used to indicate an upper limit of the discount amount provided by the discount activity in the first live broadcast session. The discount information can include at least one of the following: a discount coupon use threshold range; a discount coupon face value range; a total number of discount coupons; a subsidy rate; and a subsidy upper limit.

[0072] The discount coupon use threshold is used to indicate a minimum order amount or a minimum product price for using the discount coupon. For example, when the discount coupon use threshold is 100 yuan, the discount coupon can only be used when the total order amount is greater than 100 yuan, or the discount coupon can only be used for purchasing a product whose price is higher than 100 yuan.

[0073] The coupon value range indicates the maximum and / or minimum value of coupons issued during a promotional activity. For example, when the coupon value range is from 10 yuan to 100 yuan, the maximum discount amount issued during the promotional activity cannot exceed 100 yuan, and the minimum discount amount cannot be less than 10 yuan. For example, the coupon could be a 20 yuan discount coupon.

[0074] The total number of coupons indicates the maximum number of coupons that can be issued in the first live stream session, or the maximum number of coupons that can be issued in a single promotional activity within the first live stream session. For example, when the total number of coupons is 100, a maximum of 100 coupons can be issued through a promotional activity in the first live stream session; or, a maximum of 100 coupons can be issued for the first promotional activity in the first live stream session.

[0075] The subsidy rate is the ratio of the total discount amount to the total order amount in the first live stream session. Alternatively, it's the ratio of the total discount amount to the total order amount for all orders during the first promotional period. For example, if a total of 1000 yuan in coupons were used in all orders during the first live stream session, and the total order amount was 10000 yuan, then the subsidy rate would be 1000 / 10000 = 10%. When the streamer sets the subsidy rate to be no higher than 20%, the live streaming application can control the subsidy rate for the first live stream session by dynamically adjusting the face value, quantity, and threshold range of the coupons issued in the first promotional activity.

[0076] The subsidy cap is the maximum total discount amount for all orders in the first live stream session, or the maximum total discount amount for all orders during a single promotional event in the first live stream session, or the total face value of all coupons that can be issued in the first live stream session, or the total face value of all coupons that can be issued during a single promotional event in the first live stream session. For example, if the streamer sets the subsidy cap for the first live stream session to 10,000 yuan, then the total face value of all coupons issued in the first live stream session cannot exceed 10,000 yuan.

[0077] For example, such as Figure 3 As shown, the broadcaster's client can display a discount information setting interface 510 for the first live broadcast room. This interface 510 displays controls for setting the coupon's usage threshold, face value range, total quantity, subsidy rate, and subsidy cap, respectively. These controls are used to set the coupon's usage threshold, face value range, total quantity, subsidy rate, and subsidy cap. The broadcaster can edit at least one type of discount information by triggering at least one of these controls. After editing, triggering the first submission control 530 submits the edited discount information to the server.

[0078] For example, the discount information can be configured for the first live broadcast session, and all discount activities in the first live broadcast session need to meet the discount amount indicated by the discount information. Alternatively, the discount information can be configured for a discount activity in the first live broadcast session, and the discount provided by the discount activity in the first live broadcast session needs to meet the discount amount indicated by the discount information.

[0079] In an optional embodiment, the anchor account can configure discount information for the first live broadcast session, and the discount information is used to limit the discount amount of all discount activities in the first live broadcast session. For example, the discount information is used to limit the use threshold, face value, and quantity of the coupons issued by any discount activity in the first live broadcast session; and / or, the discount information is used to limit the subsidy rate and total subsidy amount of the first live broadcast session.

[0080] In another optional embodiment, the anchor account can configure discount information for a discount activity in the first live broadcast session, and the discount information is used to limit the discount amount of the discount activity in the first live broadcast session. For example, the discount information is used to limit the use threshold, face value, and quantity of the coupons issued by the first discount activity in the first live broadcast session; and / or, the discount information is used to limit the subsidy rate and total subsidy amount of the first discount activity.

[0081] Step 220: receiving a setting operation of a live broadcast target, the live broadcast target being used to indicate a target value expected to be achieved by the first live broadcast session in at least one evaluation dimension.

[0082] For example, the anchor client can display a live broadcast management interface of the first live broadcast session, and display a live broadcast target setting control in the live broadcast management interface. In response to receiving an operation of triggering the live broadcast target setting control to set the live broadcast target, the live broadcast target set by the anchor account is acquired and reported.

[0083] For example, the live broadcast target is used to indicate the expected effect of the first live broadcast session to the live broadcast application, so that the live broadcast application generates corresponding discount activities to achieve the expected effect. Optionally, the live broadcast target includes at least one of the following: total transaction amount; transaction times; live broadcast room interaction times; stay duration of participating objects in the live broadcast room; UV (Unique Visitor, independent visitor); and new fan quantity. Alternatively, the evaluation dimension includes at least one of the following: total transaction amount; transaction times; live broadcast room interaction times; stay duration of participating objects in the live broadcast room; UV; and new fan quantity.

[0084] The total transaction amount refers to the total order amount of all completed orders in the first live session. The transaction frequency refers to the total number of orders generated in the first live session. The live room interaction frequency refers to the total number of interaction behaviors in the first live room, and the interaction behaviors include at least one of the following: attention, likes, comments, and sharing. The participation object stay duration can refer to the total duration of all participation objects entering the live room to watch the live broadcast within the first live session, or can refer to the average duration of all participation objects entering the live room to watch the live broadcast within the first live session. The UV refers to the total number of participation objects that enter the first live room for the first time during the first live session, that is, a participation object repeatedly entering the first live room will only be counted once. The number of new fans refers to the number of fans who newly follow the first live room or the store corresponding to the first live room in the first live session.

[0085] For example, as shown in FIG. 5, the live target setting interface 520 of the first live room can be displayed on the anchor client, and the total transaction amount setting control, the transaction frequency setting control, the interaction frequency setting control, the stay duration setting control, the UV setting control, and the number of new fans setting control are displayed in the live target setting interface 520, which are respectively used to set the total transaction amount, the transaction frequency, the live room interaction frequency, the stay duration of the participation object in the live room, the UV, and the number of new fans. The anchor can edit at least one live target by triggering at least one of the controls, and after editing is completed, triggering the second submission control 540 can submit the edited live target to the server. Figure 4

[0086] Optionally, the order of steps 220 and 210 can be arbitrary, and the anchor can set the preferential information and then set the live target, or can set the live target and then set the preferential information.

[0087] Step 230: During the live process of the first live session, the first preferential activity is displayed.

[0088] The first preferential activity is generated based on the live data of the first live session, the preferential information, and the live target.

[0089] The live data is used to indicate the live broadcast of the first live session, so that the live application program can generate a suitable preferential activity based on the live broadcast. The live data includes at least one of real-time data and inherent data.

[0090] ​The real-time data refers to data collected in real time during the live streaming of the first live streaming session. For example, the real-time data includes at least one of the following: a real-time number of participating objects in the first live streaming room, a stay duration of each participating object, a behavior (browsing goods, liking the live streaming room, commenting, following the live streaming room, ordering goods, searching for goods) of each participating object in the live streaming room, a current explanation of goods, a current preferential activity, a coupon collection situation of the current preferential activity, a current live streaming duration of the first live streaming session, and a current time period (for example, the current time period is morning, noon, or night, or the current time period is a holiday or a workday).

[0091] The inherent data refers to data stored by the live streaming application and related to the first live streaming session. For example, the inherent data includes at least one of the following: an object label (for example, the object label can be young, middle-aged, old, a beauty enthusiast, a photography enthusiast, meticulous, and thrifty) and a price preference of a participating object participating in the first live streaming session; an identifier of the first live streaming room and a type (for example, food, beauty, outdoor, and home) of the first live streaming room; a list of goods, a start time, a planned live streaming duration, a predicted end time, and an identifier of a host (for example, host No. 1, host No. 2, and host No. 3, different hosts have different styles) of the first live streaming session.

[0092] The live streaming application (the host client or the server) takes a live streaming target as an expected target of the preferential activity, restricts a preferential policy of the preferential activity by preferential information, combines live streaming data of the first live streaming session, and generates the first preferential activity that fits a current situation of the first live streaming session.

[0093] For example, the live streaming target is to add 100 new fans, and there are currently 30 participating objects in the first live streaming room that do not follow the live streaming room. The live streaming application can generate a follow-to-receive-coupon activity to guide the participating objects to follow the live streaming room and receive a coupon to increase the number of fans.

[0094] Optionally, the host client can display the first preferential activity in various forms.

[0095] For example, when the first live streaming session is live streamed by a digital human, the live streaming application can generate an introduction lip sync of the digital human introducing the first preferential activity, and the host client can play the introduction lip sync of the digital human introducing the first preferential activity. Optionally, the live streaming application (the host client or the server) calls a large language model, generates a lip sync script according to activity information of the first preferential activity, calls a text-to-speech service to generate the introduction lip sync according to the lip sync script, the introduction lip sync includes a human voice audio of the lip sync script, and controls the digital human to broadcast the introduction lip sync.

[0096] And / or, the host client can display a start prompt of the first preferential activity when the first preferential activity starts.

[0097] And / or, the anchor client can display a participation entry of the first preferential activity in the live interface during the validity period of the first preferential activity, so as to facilitate the participation object to participate in the first preferential activity through the participation entry.

[0098] For example, as shown in the live picture of the first live session, a digital human 201 is displayed, and the digital human is introducing the first preferential activity. The live picture can display a subtitle 202 of the digital human, and the digital human is introducing "follow to get a coupon". Figure 5

[0099] Or, as shown in the live interface of the first live session, a participation entry 203 of the first preferential activity is displayed. In response to receiving an operation of triggering the participation entry 203, the live application can display participation guidance in the live interface, for example, display a guidance prompt at a follow control of the first live room, and guide the user to follow the live room to get a coupon. Or, in response to receiving an operation of triggering the participation entry 203, an activity detail page is displayed, and the user can participate in the activity in the activity detail page. Figure 6

[0100] It should be noted that the live application can generate at least one preferential activity during the first live session. The present embodiment only takes the first preferential activity as an example for description. The live application can determine whether it is suitable to generate a preferential activity and what kind of preferential activity to generate in real time according to the live data of the first live session, so as to achieve the live target without exceeding the preferential amount constrained by the preferential information.

[0101] For example, the duration of the first preferential activity is not longer than the live time of the first live session.

[0102] Figure 7 is a flowchart of a live method provided by an exemplary embodiment of the present application. The method can be used in a server as shown in Figure 1 The method includes the following steps.

[0103] Step 310: receiving preferential information set by an anchor client, the preferential information being used to determine a total preferential range of a first live session.

[0104] The method can be executed by a server, and the server is installed with a service end of a live application, and the server is used to provide background service for anchor clients and audience clients.

[0105] Step 320: receiving a live target set by an anchor client, the live target being used to indicate a target value expected to be achieved by the first live session in at least one evaluation dimension.

[0106] ​​Optionally, the order of steps 320 and 310 can be any, the server can receive the discount information first and then receive the live target, or receive the live target first and then receive the discount information, or receive the live target and the discount information synchronously.

[0107] Step 330: generating and sending the first discount activity during the live broadcast of the first live session.

[0108] The first discount activity is generated based on the live data of the first live session, the discount information, and the live target.

[0109] For example, the server generates the first discount activity for the first live session based on the live data of the first live session, the discount information, and the live target. Optionally, the server triggers the digital person to introduce the first discount activity through a voice broadcast, triggers a start prompt of the first discount activity, and generates and sends a participation entry of the first discount activity.

[0110] Figure 8 FIG. 1 is a flowchart of a live method provided by an example embodiment of the present application. The method can be used in a terminal device or a viewer client in a terminal device as shown in FIG. 2. Figure 1 The method includes the following steps.

[0111] Step 410: playing the first live session.

[0112] The method can be executed by a viewer terminal, and the viewer terminal has a viewer client of a live application installed thereon, and the viewer client has a viewer account logged in. The viewer account can enter the first live room to watch the live broadcast as a viewer. For example, the viewer client is a client used by a first participant object, and the first participant object is an object participating in the first live session, or the first participant object is a viewer watching the first live session.

[0113] For example, the viewer client can display a live room lobby interface of the live application, and the live room lobby interface has entry controls of at least two live rooms, and a user can trigger the entry controls to enter the first live room to watch the live broadcast of the first live session.

[0114] Step 420: displaying the first discount activity of the first live session.

[0115] The first discount activity is generated based on the live data of the first live session, the discount information, and the live target; the discount information and the live target are set by a management account of the first live session; the discount information is used to determine a total discount range of the first live session; and the live target is used to indicate a target value expected to be achieved by the first live session in at least one evaluation dimension.

[0116] To sum up, the method provided by the embodiment enables the live streaming application to accurately generate the preferential activity of the current live streaming based on the live streaming data, the preferential information and the live streaming target by setting the preferential information and the live streaming target. The live streaming application can select appropriate preferential time, preferential mode and preferential strength to automatically generate the preferential activity that fits the current live streaming situation for the purpose of achieving the live streaming target, reduce the manual operation cost in the live streaming process and expand the service capability of the digital human live streaming.

[0117] An exemplary embodiment of interaction among the anchor client, the server and the audience client is given.

[0118] Figure 9 is a flowchart of a live streaming method provided by an exemplary embodiment of the present application. The method can be used in a terminal and a server as shown in Figure 1 The method includes the following steps.

[0119] Step 501: The anchor client sends the set preferential information and live streaming target to the server.

[0120] The anchor client receives the editing operation of the user, acquires the preferential information and live streaming target set by the anchor and, in response to the submission operation, reports the preferential information and live streaming target set by the anchor to the server. The server receives the preferential information and live streaming target reported by the anchor client and stores the preferential information and live streaming target in correspondence with the identification of the first live streaming session.

[0121] Step 502: The server acquires live streaming data.

[0122] Subsequently, the first live streaming session starts live streaming. In the live streaming process of the first live streaming session, the server can collect live streaming data in real time, perceive the live streaming environment of the first live streaming session in real time based on the collected live streaming data and, when the server judges that the current live streaming environment of the first live streaming session is suitable for generating the preferential activity for achieving the live streaming target, generate the first preferential activity according to the constraint of the preferential information.

[0123] Step 503: The server issues the first preferential activity to the anchor client and the audience client.

[0124] Exemplarily, the server calls the activity prediction model to generate the activity information of the first preferential activity based on the live streaming data, the preferential information and the live streaming target of the first live streaming session; wherein the activity information includes at least one of the following: a mouth broadcasting triggering time, an activity start time, an activity end time, an activity participation mode, a preferential mode, a coupon face value, a total number of coupons, a coupon use restriction.

[0125] Exemplarily, one promotion event can correspond to at least one voice broadcast triggering time, that is, for one promotion event, multiple voice broadcasts of digital human can be triggered to introduce the promotion event. The start time of the event and the first voice broadcast triggering time can be the same or different. The event participation mode can be at least one of the following: attention coupon, lottery event, comment coupon, sharing coupon, order coupon, and order rebate. The promotion mode can include at least one of the following: discount coupon, full-reduction coupon, deduction coupon, free coupon, and rebate.

[0126] The event prediction model is an artificial intelligence model. Exemplarily, the event prediction model is trained by the following method: obtaining sample live data, sample promotion information, sample live target and sample event information of historical live sessions; calling the event prediction model, based on the input sample live data, sample promotion information and sample live target, outputting predicted event information; training the event prediction model based on the loss of the predicted event information and the sample event information until convergence.

[0127] Optionally, the sample promotion information is calculated based on the promotion data of the historical live sessions; and the sample live target is calculated based on the data of the historical live sessions in at least one evaluation dimension.

[0128] For example, a second promotion event is carried out in a second live session of the historical live, and the event information of the second promotion event is the sample event information. The performance data of the second live session in at least one evaluation dimension is the sample live target. The total amount of the promotion in the second live session is the upper limit of the promotion, and based on the order transaction and order promotion of the second live session, the subsidy rate, the upper limit of the subsidy, the total number of coupons, and the coupon usage restriction can be calculated as the sample promotion information. The live data of the second live session is collected to obtain the sample live data. In this way, a set of training samples can be obtained, and multiple sets of training samples can be obtained through multiple live sessions of the historical live, and then a training sample set is obtained; the event prediction model is trained using the training sample set to have the event generation capability.

[0129] Exemplarily, the live application program can generate personalized promotion events for each participating object participating in the first live session, so that the promotion events meet the needs of each participating object.

[0130] Taking the first participating object as an example, the live data includes the feature data of the first participating object; the server calls the event prediction model to generate the coupon information of the first participating object in the first promotion event based on the feature data, the promotion information and the live target.

[0131] The characteristic data includes at least one of the following: a time when the first participating object enters the first live broadcast session, a comment behavior of the first participating object in the first live broadcast session, a like behavior, a commodity browsing behavior, a commodity transaction behavior, an object label of the first participating object, and a price preference. The coupon information includes at least one of the following: a coupon face value, a discount mode, and a coupon use limit.

[0132] That is, the activity prediction model can generate personalized preferential activities for each participating object according to the input characteristic data of each participating object. It should be noted that in the same preferential activity, the activity modes of all participating objects are the same, for example, all participating objects are lottery activities, when the first participating object prefers a full-reduction activity, a full-reduction coupon is issued to the first participating object; when the second participating object prefers a discount activity, a discount coupon is issued to the second participating object. Alternatively, the live broadcast application program can estimate the expected order price of the participating object, and determine the corresponding coupon face value according to the expected order price of each participating object.

[0133] Step 504: The audience client sends the comment text to the server. The server generates a reply text and / or a reply lip sync based on the comment text.

[0134] For example, the audience client receives the operation of editing and sending the comment text; the comment text is used to inquire about the first preferential activity; the comment text is displayed; the reply text corresponding to the comment text is displayed, and / or the reply lip sync corresponding to the comment text is played; the reply lip sync includes the human voice audio of the reply text; wherein the reply text is a reply to the comment text based on the activity information of the first preferential activity.

[0135] For example, the server receives the comment text sent by the audience client, the comment text is used to inquire about the first preferential activity; the reply text to the comment text is generated based on the activity information of the first preferential activity; at least one of the reply text and the reply lip sync is sent; the reply lip sync includes the human voice audio of the reply text.

[0136] For example, the host client displays the comment text, the comment text is used to inquire about the first preferential activity; the reply text corresponding to the comment text is displayed, and / or the reply lip sync corresponding to the comment text is played; the reply lip sync includes the human voice audio of the reply text; wherein the reply text is a reply to the comment text based on the activity information of the first preferential activity.

[0137] Exemplarily, the server invokes the large language model to generate the reply text of the comment text. The prompt word is generated based on the comment text and the activity information of the first preferential activity, and the prompt word is input into the large language model to output the reply text of the comment text. The prompt word can include a first sentence and a second sentence, the first sentence is used to describe the task purpose of giving a reply according to a question, and the second sentence is used to indicate that the comment text is a question and the activity information is reference information.

[0138] For example, as shown in FIG. 2, when the audience account posts a comment 204 "How to participate in the activity" in the comment area of the first live broadcast session, the server invokes the artificial intelligence driven digital person to generate the reply text "Follow the live broadcast room to participate in the activity" to the comment 204. The reply text generates a reply lip-sync of the reply text. The anchor account sends the reply text 205 "@ audience, follow the live broadcast room to participate in the activity" in the comment area, and the reply lip-sync is played at the same time. The subtitle 206 "Follow the live broadcast room to participate in the activity" of the reply lip-sync can be displayed synchronously in the live broadcast video. Figure 10

[0139] The server receives the comment text sent by the audience client in the first live broadcast room, generates the reply text based on the artificial intelligence driven digital person according to the comment text and the activity information, and synthesizes the reply lip-sync based on the artificial intelligence driven digital person according to the reply text. The server sends the reply text and / or the reply lip-sync to the anchor client and / or the audience client.

[0140] Step 505: The server sends the reply text and the reply lip-sync to the anchor client and the audience client.

[0141] The anchor client and / or the audience client display the reply text sent by the anchor account in the comment area of the first live broadcast room, and display the reply lip-sync broadcasted by the digital person.

[0142] Exemplarily, steps 501 to 503 can be implemented as an embodiment alone, and steps 504 and 505 can also be implemented as an embodiment alone.

[0143] In summary, the method provided by the embodiment can generate and launch accurate preferential activities in real time by sensing live broadcast data in the live broadcast room in the live broadcast process, combining live broadcast targets and preferential information. The digital person introduces the preferential activities and answers questions through the introduction lip-sync, so as to realize the automation of the digital person creating the preferential activities, and the human intervention is not required, thereby saving the labor cost of the digital person live broadcast. Moreover, the preferential activities generated by the method can accurately fit the live broadcast, and the accurate launching of the preferential activities is realized.

[0144] ​The method provided in the embodiment trains an artificial intelligence model, so that the artificial intelligence model can learn the automatic generation logic of preferential activities in historical live broadcast sessions, determine the delivery time and promotion time of preferential activities according to live broadcast data of a live broadcast room, and generate corresponding preferential activities according to a live broadcast target as an expected result according to a preferential limit indicated by preferential information. The automatic generation of preferential activities is realized, and the generation efficiency and accuracy of preferential activities are improved.

[0145] The method provided in the embodiment can generate personalized preferential activities for each participating object based on feature data of the participating object, in combination with preferences and demands of the participating object, so as to attract the participating object to actively participate in the preferential activities and improve the participation rate of the preferential activities.

[0146] For example, the server can be divided into a live broadcast service, a content generation service, an activity system, and a digital person backstage, and an embodiment of the live broadcast method provided in the application is implemented by combining four services of the server.

[0147] Figure 11 is a flowchart of a live broadcast method provided in an example embodiment of the application. The method can be used in a server as shown in Figure 1 The method includes the following steps.

[0148] In step 601, the activity system creates a coupon in response to a coupon operation of the anchor client and records a coupon ID (Identity Document, ID).

[0149] In step 602, the digital person backstage receives the coupon ID and configures the digital person activity type and the live broadcast target.

[0150] In step 603, the digital person backstage submits a content generation request to the content generation service based on the coupon ID, the activity type, and the live broadcast target, and the content generation service generates an activity voiceover script, an interactive reply question and answer, and synthesizes a digital person.

[0151] In step 604, after the live broadcast starts, the live broadcast service synchronizes live broadcast data to the digital person backstage. The digital person backstage perceives the live broadcast environment in real time based on the live broadcast data, triggers the generation of an activity scheme. The digital person backstage submits a coupon pricing to the activity system according to the generated activity scheme, and operates the coupon distribution. The digital person backstage synchronizes the coupon distribution to the activity system, and the activity system synchronously modifies the coupon inventory according to the coupon distribution. The digital person backstage triggers an activity introduction voiceover based on real-time perception of the live broadcast data, the content generation service generates an introduction voiceover, and updates the live broadcast audio and video to control the digital person to introduce the preferential activities.

[0152] At step 605, the digital human background receives the audience public screen comment on the preferential activity sent by the live service, takes the reply text of the public screen comment as the question, and generates the reply text by the content generation service. On one hand, the reply text is written into the live room interface by the digital human background for text reply. On the other hand, the digital human reply audio and video of the reply text are generated by the content generation service for audio and video reply.

[0153] For example, the anchor configures the live target of the digital human live broadcast in this session as increasing fans and promoting live room watching UV, the activity type is task coupon, and the subsidy rate and the subsidy upper limit are configured. During the live broadcast, when the watching UV experiences a rapid increase at a certain time point, the real-time perception module of the digital human background perceives the watching volume growth and the main audience is new customers, and then generates the attention coupon activity based on the live target and the activity type, and generates the coupon face value and inventory of the attention coupon activity according to the subsidy rate, the subsidy upper limit and the total inventory. Subsequently, the operation activity system generates and issues the coupon, and operates the live room to display the activity. Subsequently, the digital human broadcasts the preferential activity, and replies to the relevant questions of the audience on the activity.

[0154] In summary, compared with the digital human live broadcast method in the related art, the real-time live data of the live room is perceived by the live application program, and the live preferential activity is dynamically generated, which complements the marketing capability of the digital human. The method generates the preferential activity by using an artificial intelligence model, and the generated preferential activity is more accurate than the design of a real anchor.

[0155] It should be noted that before collecting the relevant data of the user (for example, the operation data and the game data in the present application) and during the collection of the relevant data of the user, a prompt interface, a pop-up window or a voice prompt information can be displayed, the prompt interface, the pop-up window or the voice prompt information being used to prompt that the relevant data of the user is currently being collected, so that the present application starts to perform the related steps of acquiring the relevant data of the user only after the confirmation operation of the user on the prompt interface or the pop-up window is acquired, otherwise (i.e., when the confirmation operation of the user on the prompt interface or the pop-up window is not acquired), the related steps of acquiring the relevant data of the user are ended, that is, the relevant data of the user is not acquired. In other words, all the user data collected by the present application is collected under the condition that the user agrees and authorizes, and the collection, use and processing of the relevant user data need to comply with the relevant laws, regulations and standards of the country and region.

[0156] It should be noted that the sequence of the method steps provided by the embodiments of the present application can be appropriately adjusted, and the steps can be correspondingly increased or decreased according to the situation. Any person skilled in the art can easily think of changes within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application, and therefore will not be described in detail.

[0157] Figure 12 is a structural schematic diagram of a live broadcast device provided by an exemplary embodiment of the present application. The device is used to implement a terminal installed with a host client, and the device comprises:

[0158] The first interaction module 801 is configured to receive a setting operation of preferential information, wherein the preferential information is used to determine a total preferential range of a first live broadcast session;

[0159] The first interaction module 801 is configured to receive a setting operation of a live broadcast target, wherein the live broadcast target is used to indicate a target value expected to be achieved by the first live broadcast session in at least one evaluation dimension;

[0160] The first display module 804 is configured to display a first preferential activity during a live broadcast process of the first live broadcast session.

[0161] The first preferential activity is generated based on live broadcast data of the first live broadcast session, the preferential information and the live broadcast target.

[0162] In an optional embodiment, the first display module 804 is configured to perform at least one of the following:

[0163] Play a digital human to introduce an introduction voice-over of the first preferential activity;

[0164] Display a start prompt of the first preferential activity;

[0165] Display a participation entry of the first preferential activity.

[0166] In an optional embodiment, the device further comprises:

[0167] The first generation module 803 is configured to call a large language model and generate an introduction voice-over script according to activity information of the first preferential activity;

[0168] The first generation module 803 is configured to call a text-to-speech service and generate the introduction voice-over according to the introduction voice-over script, wherein the introduction voice-over comprises human voice audio of the introduction voice-over script;

[0169] The first display module 804 is configured to control a digital human to broadcast the introduction voice-over.

[0170] In an optional embodiment, the device further comprises:

[0171] The first generation module 803 is configured to call an activity prediction model to generate the activity information of the first preferential activity based on live broadcast data of the first live broadcast session, the preferential information and the live broadcast target;

[0172] The activity information includes at least one of the following: a mouth broadcast triggering time, an activity start time, an activity end time, an activity participation mode, a preferential mode, a coupon face value, a total number of coupons, and a coupon use limit.

[0173] In an optional embodiment, the device further includes:

[0174] The first training module 802 is configured to obtain sample live broadcast data, sample preferential information, sample live broadcast targets, and sample activity information of historical live broadcast sessions.

[0175] The first training module 802 is configured to call the activity prediction model, and output predicted activity information based on the input sample live broadcast data, sample preferential information, and sample live broadcast targets.

[0176] The first training module 802 is configured to train the activity prediction model based on a loss of the predicted activity information and the sample activity information until the activity prediction model converges.

[0177] The sample preferential information is calculated based on preferential data of the historical live broadcast sessions, and the sample live broadcast targets are calculated based on data of the historical live broadcast sessions in the at least one evaluation dimension.

[0178] In an optional embodiment, the live broadcast data includes feature data of a first participating object.

[0179] The first generation module 803 is configured to call the activity prediction model to generate coupon information of the first participating object in the first preferential activity based on the feature data, the preferential information, and the live broadcast targets.

[0180] The feature data includes at least one of the following: a time at which the first participating object enters the first live broadcast session, a comment behavior of the first participating object in the first live broadcast session, a like behavior, a product browsing behavior, a product transaction behavior, an object label of the first participating object, and a price preference.

[0181] The coupon information includes at least one of the following: a coupon face value, a preferential mode, and a coupon use limit.

[0182] In an optional embodiment, the preferential information includes at least one of the following: a coupon use threshold range, a coupon face value range, a total number of coupons, a subsidy rate, and a subsidy upper limit.

[0183] In an optional embodiment, the live broadcast targets include at least one of the following: a total transaction amount, a transaction frequency, a live broadcast room interaction frequency, a stay duration of a participating object in a live broadcast room, an independent visitor UV, and a number of newly added fans.

[0184] In an optional embodiment, the first display module 804 is configured to display a comment text, the comment text being configured to inquire about the first preferential activity;

[0185] The first display module 804 is configured to display reply text corresponding to the comment text and / or play reply audio corresponding to the comment text, the reply audio including human voice audio of the reply text.

[0186] The reply text is a reply to the comment text based on activity information of the first preferential activity.

[0187] Figure 13 FIG. 1 is a structural schematic diagram of a live streaming device according to an example embodiment of the present application. The device is configured to implement a server, and the device includes:

[0188] The first receiving module 805 is configured to receive preferential information set by a host client, the preferential information being configured to determine a total preferential range of a first live streaming session.

[0189] The first receiving module 805 is configured to receive a live streaming target set by the host client, the live streaming target being configured to indicate a target value expected to be achieved by the first live streaming session in at least one evaluation dimension.

[0190] The second generation module 807 is configured to generate and send a first preferential activity during a live streaming process of the first live streaming session.

[0191] The first preferential activity is generated based on live streaming data of the first live streaming session, the preferential information, and the live streaming target.

[0192] In an optional embodiment, the generation and sending of the first preferential activity includes at least one of the following:

[0193] The generation and sending of an introduction audio of a digital human introducing the first preferential activity.

[0194] The generation and sending of a start prompt of the first preferential activity.

[0195] The generation and sending of a participation portal of the first preferential activity.

[0196] In an optional embodiment, the device further includes:

[0197] The second generation module 807 is configured to call a large language model and generate audio script based on activity information of the first preferential activity.

[0198] The second generation module 807 is configured to call a text-to-speech service to generate the introduction voice broadcast according to the voice broadcast script, and the introduction voice broadcast includes human voice audio of the voice broadcast script.

[0199] The first sending module 806 is configured to send the introduction voice broadcast.

[0200] In an optional embodiment, the second generation module 807 is configured to call an activity prediction model to generate activity information of the first preferential activity based on live broadcast data of the first live broadcast session, the preferential information, and the live broadcast target.

[0201] The activity information includes at least one of a voice broadcast triggering time, an activity start time, an activity end time, an activity participation mode, a preferential mode, a coupon face value, a total number of coupons to be distributed, and a coupon use restriction.

[0202] In an optional embodiment, the apparatus further includes:

[0203] The second training module 808 is configured to obtain sample live broadcast data, sample preferential information, sample live broadcast targets, and sample activity information of historical live broadcast sessions.

[0204] The second training module 808 is configured to call the activity prediction model to output predicted activity information based on the input sample live broadcast data, sample preferential information, and sample live broadcast targets.

[0205] The second training module 808 is configured to train the activity prediction model based on a loss of the predicted activity information and the sample activity information until the activity prediction model converges.

[0206] The sample preferential information is calculated based on preferential data of the historical live broadcast sessions, and the sample live broadcast target is calculated based on data of the historical live broadcast sessions in the at least one evaluation dimension.

[0207] In an optional embodiment, the live broadcast data includes feature data of a first participating object.

[0208] The second generation module 807 is configured to call an activity prediction model to generate coupon information of the first preferential activity of the first participating object based on the feature data, the preferential information, and the live broadcast target.

[0209] The feature data includes at least one of a time when the first participating object enters the first live broadcast session, a comment behavior of the first participating object in the first live broadcast session, a like behavior, a product browsing behavior, a product transaction behavior, an object label of the first participating object, and a price preference.

[0210] The coupon information includes at least one of the following: coupon face value, discount mode, and coupon use restriction.

[0211] In an optional embodiment, the apparatus further includes:

[0212] The first receiving module 805 is configured to receive a comment text sent by the audience client, the comment text being used to inquire about the first preferential activity;

[0213] The first generating module 803 is configured to generate a reply text for the comment text based on activity information of the first preferential activity;

[0214] The first sending module 806 is configured to send at least one of the reply text and a reply voiceover; the reply voiceover includes human voice audio of the reply text.

[0215] Figure 14 FIG. 1 is a structural schematic diagram of a live broadcast apparatus provided by an exemplary embodiment of the present application. The apparatus is used to implement a terminal installed with an audience client, and the apparatus includes:

[0216] The second display module 810 is configured to play a first live broadcast session;

[0217] The second display module 810 is configured to display a first preferential activity of the first live broadcast session;

[0218] The first preferential activity is generated based on live broadcast data of the first live broadcast session, preferential information, and a live broadcast target; the preferential information and the live broadcast target are set by a management account of the first live broadcast session; the preferential information is used to determine a total preferential range of the first live broadcast session; and the live broadcast target is used to indicate a target value expected to be achieved by the first live broadcast session in at least one evaluation dimension.

[0219] In an optional embodiment, the second display module 810 is configured to perform at least one of the following:

[0220] playing a digital human introduction to an introduction voiceover of the first preferential activity;

[0221] displaying a start prompt of the first preferential activity;

[0222] displaying a participation entry of the first preferential activity.

[0223] In an optional embodiment, the activity information of the first preferential activity is generated based on live broadcast data of the first live broadcast session, preferential information, and a live broadcast target;

[0224] The activity information includes at least one of a time of a voice broadcast trigger, a start time of the activity, an end time of the activity, a participation mode of the activity, a discount mode, a coupon face value, a total number of coupons to be distributed, and a coupon use restriction.

[0225] In an optional embodiment, the account of the first participant is logged in on the audience client; the live broadcast data includes feature data of the first participant; and the apparatus further includes:

[0226] The second interaction module 809 is configured to receive an activity participation operation.

[0227] The second display module 810 is configured to display a first coupon obtained by the first participant in the first discount activity; the first coupon is generated based on the feature data, the discount information, and the live broadcast target.

[0228] The feature data includes at least one of a time when the first participant enters the first live broadcast session, a comment behavior of the first participant in the first live broadcast session, a like behavior, a product browsing behavior, a product transaction behavior, an object label of the first participant, and a price preference.

[0229] The coupon information of the first coupon includes at least one of a coupon face value, a discount mode, and a coupon use restriction.

[0230] In an optional embodiment, the apparatus further includes:

[0231] The second interaction module 809 is configured to receive an operation of editing and sending a comment text; and the comment text is used to inquire about the first discount activity.

[0232] The second display module 810 is configured to display the comment text.

[0233] The second display module 810 is configured to display a reply text corresponding to the comment text, and / or play a reply voice broadcast corresponding to the comment text; and the reply voice broadcast includes a human voice audio of the reply text.

[0234] The reply text is a reply to the comment text, which is generated based on activity information of the first discount activity.

[0235] It should be noted that the live broadcast device provided in the above embodiments is only used for example and division of the above functional modules, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the live broadcast device and the live broadcast method provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0236] Embodiments of the present application also provide a computer device, comprising a processor and a memory, the memory storing at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, at least one program, code set or instruction set being loaded and executed by the processor to implement the live broadcast method provided by the above method embodiments. The computer device can be implemented as a terminal device or a server.

[0237] For example, Figure 15 FIG. 1 is a structural schematic diagram of a computer device provided by an example embodiment of the present application.

[0238] Generally, the computer device 1700 includes a processor 1701 and a memory 1702.

[0239] The processor 1701 can include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 1701 can be implemented in at least one of a hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 1701 can also include a main processor and a coprocessor, the main processor being a processor for processing data in an awake state, also known as a CPU (Central Processing Unit), and the coprocessor being a low-power processor for processing data in a standby state. In some embodiments, the processor 1701 can be integrated with a GPU (Graphics Processing Unit) that is responsible for rendering and drawing the content to be displayed by the display screen. In some embodiments, the processor 1701 can also include an AI (Artificial Intelligence) processor for processing machine learning-related computing operations.

[0240] The memory 1702 can include one or more computer-readable storage media. The computer-readable storage media can be non-transitory storage media. In addition, the memory 1702 can include high-speed random access memory and can also include non-volatile memory, such as one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid-state storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 1702 is used to store at least one instruction for being executed by the processor 1701 to implement the live streaming method provided by the method embodiments in the present application.

[0241] In some embodiments, the computer device 1700 can further optionally include a peripheral device interface 1703 and at least one peripheral device. The processor 1701, the memory 1702, and the peripheral device interface 1703 can be connected through a bus or a signal line. Each peripheral device can be connected to the peripheral device interface 1703 through a bus, a signal line, or a circuit board. Specifically, the peripheral device includes at least one of a radio frequency circuit 1704, a display screen 1705, a camera assembly 1706, an audio circuit 1707, and a power supply 1708.

[0242] The peripheral device interface 1703 can be used to connect at least one peripheral device related to input / output (I / O) to the processor 1701 and the memory 1702. In some embodiments, the processor 1701, the memory 1702, and the peripheral device interface 1703 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 1701, the memory 1702, and the peripheral device interface 1703 can be implemented on a separate chip or circuit board, and the embodiments of the present application are not limited thereto.

[0243] The radio frequency circuit 1704 is configured to receive and send RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 1704 communicates with communication networks and other communication devices through electromagnetic signals. The radio frequency circuit 1704 converts electrical signals to electromagnetic signals for transmission, or vice versa. Optionally, the radio frequency circuit 1704 includes an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and the like. The radio frequency circuit 1704 can communicate with other computer devices through at least one wireless communication protocol. The wireless communication protocol includes, but is not limited to, the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G, and 5G), a wireless local area network, and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 1704 can also include NFC (Near Field Communication) related circuitry, which is not limited in the present application.

[0244] The display screen 1705 is configured to display a UI (User Interface). The UI can include graphics, text, icons, video, and any combination thereof. When the display screen 1705 is a touch display screen, the display screen 1705 also has the ability to collect touch signals on or above the surface of the display screen 1705. The touch signals can be input as control signals to the processor 1701 for processing. At this time, the display screen 1705 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen 1705 can be one, arranged on the front panel of the computer device 1700; in other embodiments, the display screen 1705 can be at least two, arranged on different surfaces of the computer device 1700 or in a folding design; in still other embodiments, the display screen 1705 can be a flexible display screen, arranged on a curved surface or a folding surface of the computer device 1700. Even, the display screen 1705 can also be arranged in an irregular shape other than a rectangle, i.e., a special-shaped screen. The display screen 1705 can be made of materials such as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), and the like.

[0245] The camera component 1706 is configured to capture images or videos. Optionally, the camera component 1706 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is disposed on the front panel of the computer device 1700, and the rear-facing camera is disposed on the back of the computer device. In some embodiments, the rear-facing camera is at least two, which are any one of a main camera, a depth-of-field camera, a wide-angle camera, and a telephoto camera, to realize the background blur function by fusing the main camera and the depth-of-field camera, the panorama shooting and VR (Virtual Reality) shooting function by fusing the main camera and the wide-angle camera, or other fusion shooting functions. In some embodiments, the camera component 1706 can further include a flash. The flash can be a single-color-temperature flash or a dual-color-temperature flash. The dual-color-temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0246] The audio circuit 1707 can include a microphone and a speaker. The microphone is configured to capture sound waves of a user and an environment, and convert the sound waves into an electrical signal input to the processor 1701 for processing or to the radio frequency circuit 1704 to realize voice communication. For the purpose of stereo sound collection or noise reduction, the microphone can be multiple, which are respectively disposed at different parts of the computer device 1700. The microphone can also be an array microphone or an omnidirectional collection microphone. The speaker is configured to convert an electrical signal from the processor 1701 or the radio frequency circuit 1704 into sound waves. The speaker can be a traditional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert an electrical signal into a sound wave audible to humans, but also convert an electrical signal into an inaudible sound wave to humans for ranging purposes. In some embodiments, the audio circuit 1707 can further include a headphone jack.

[0247] The power supply 1708 is configured to supply power to various components in the computer device 1700. The power supply 1708 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 1708 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. The wired rechargeable battery is a battery that is charged through a wired line, and the wireless rechargeable battery is a battery that is charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0248] In some embodiments, the computer device 1700 further includes one or more sensors 1709. The one or more sensors 1709 include, but are not limited to, an acceleration sensor 1710, a gyroscope sensor 1711, a pressure sensor 1712, an optical sensor 1713, and a proximity sensor 1714.

[0249] The acceleration sensor 1710 can detect the acceleration magnitude in three coordinate axes of the coordinate system established by the computer device 1700. For example, the acceleration sensor 1710 can be used to detect the components of the gravitational acceleration in three coordinate axes. The processor 1701 can control the touch display screen 1705 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signals collected by the acceleration sensor 1710. The acceleration sensor 1710 can also be used for game or user motion data collection.

[0250] The gyroscope sensor 1711 can detect the body orientation and rotation angle of the computer device 1700, and the gyroscope sensor 1711 can collect the 3D motion of the user to the computer device 1700 in cooperation with the acceleration sensor 1710. The processor 1701 can implement the following functions according to the data collected by the gyroscope sensor 1711: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization when shooting, game control, and inertial navigation.

[0251] The pressure sensor 1712 can be arranged on the side frame of the computer device 1700 and / or the lower layer of the touch display screen 1705. When the pressure sensor 1712 is arranged on the side frame of the computer device 1700, the user's holding signal to the computer device 1700 can be detected, and the left-hand or right-hand recognition or shortcut operation can be performed by the processor 1701 according to the holding signal collected by the pressure sensor 1712. When the pressure sensor 1712 is arranged on the lower layer of the touch display screen 1705, the processor 1701 can control the operable control on the UI interface according to the user's pressure operation to the touch display screen 1705. The operable control includes at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0252] The optical sensor 1713 is used to collect the ambient light intensity. In one embodiment, the processor 1701 can control the display brightness of the touch display screen 1705 according to the ambient light intensity collected by the optical sensor 1713. Specifically, when the ambient light intensity is high, the display brightness of the touch display screen 1705 is increased; when the ambient light intensity is low, the display brightness of the touch display screen 1705 is decreased. In another embodiment, the processor 1701 can also dynamically adjust the shooting parameters of the camera assembly 1706 according to the ambient light intensity collected by the optical sensor 1713.

[0253] The proximity sensor 1714, also called a distance sensor, is usually arranged on the front panel of the computer device 1700. The proximity sensor 1714 is used to collect the distance between the user and the front of the computer device 1700. In an embodiment, when the proximity sensor 1714 detects that the distance between the user and the front of the computer device 1700 gradually decreases, the touch display screen 1705 is switched from the bright screen state to the off-screen state under the control of the processor 1701; when the proximity sensor 1714 detects that the distance between the user and the front of the computer device 1700 gradually increases, the touch display screen 1705 is switched from the off-screen state to the bright screen state under the control of the processor 1701.

[0254] Those skilled in the art can understand that the structure shown in the foregoing embodiments is not a limitation on the computer device 1700, and the computer device 1700 can include more or fewer components than those shown in the figure, or combine certain components, or adopt a different component arrangement. Figure 15

[0255] The embodiment of the present application further provides a computer readable storage medium, and the readable storage medium stores at least one instruction, at least one program, a code set or an instruction set. When the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor of the computer device, the live broadcast method provided in each method embodiment is implemented.

[0256] The present application further provides a computer program product or a computer program, and the computer program product or the computer program includes computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the live broadcast method provided in each method embodiment.

[0257] Those skilled in the art can understand that all or part of the steps of the above-mentioned embodiments can be completed by hardware, or by a program instructing related hardware, and the program can be stored in a computer readable storage medium. The readable storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk.

[0258] The above description is only optional embodiments of the present application, and does not limit the present application. Any modification, equivalent switching, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.​

Claims

1. A live streaming method, characterized in that, The method is executed by a host client, and the method comprises: receiving a setting operation of preferential information, the preferential information being used to determine a total preferential range of a first live broadcast session; receiving a setting operation of a live broadcast target, the live broadcast target being used to indicate a target value expected to be achieved by the first live broadcast session in at least one evaluation dimension; displaying a first preferential activity in a live broadcast process of the first live broadcast session; wherein the first preferential activity is generated based on live broadcast data of the first live broadcast session, the preferential information and the live broadcast target.

2. The method of claim 1, wherein, The displaying of the first preferential activity comprises at least one of the following: playing an introduction voice-over of a digital human introducing the first preferential activity; displaying a start prompt of the first preferential activity; displaying a participation entry of the first preferential activity.

3. The method of claim 2, wherein, The playing of the introduction voice-over of the digital human introducing the first preferential activity comprises: calling a large language model to generate a voice-over script according to activity information of the first preferential activity; calling a text-to-speech service to generate the introduction voice-over according to the voice-over script, the introduction voice-over comprising human voice audio of the voice-over script; controlling a digital human to broadcast the introduction voice-over.

4. The method according to any one of claims 1 to 3, characterized in that, The method further comprises: calling an activity prediction model to generate the activity information of the first preferential activity based on the live broadcast data of the first live broadcast session, the preferential information and the live broadcast target; wherein the activity information comprises at least one of the following: a voice-over triggering time, an activity start time, an activity end time, an activity participation mode, a preferential mode, a coupon face value, a total number of coupons to be put in, and a coupon use restriction.

5. The method of claim 4, wherein, The live broadcast data comprises feature data of a first participating object; The calling of the activity prediction model comprises: calling an activity prediction model to generate coupon information of the first participating object in the first preferential activity based on the feature data, the preferential information and the live broadcast target; wherein the feature data comprises at least one of the following: a time when the first participating object enters the first live broadcast session, a comment behavior of the first participating object in the first live broadcast session, a like behavior, a product browsing behavior, a product transaction behavior, an object label of the first participating object, and a price preference; The coupon information comprises at least one of the following: a coupon face value, a preferential mode, and a coupon use restriction.

6. A live streaming method, characterized in that, The method is executed by a server, and the method comprises: receiving preferential information set by a host client, the preferential information being used to determine a total preferential range of a first live broadcast session; receiving a live broadcast target set by the host client, the live broadcast target being used to indicate a target value expected to be achieved by the first live broadcast session in at least one evaluation dimension; generating and sending a first preferential activity in a live broadcast process of the first live broadcast session; wherein the first preferential activity is generated based on live broadcast data of the first live broadcast session, the preferential information and the live broadcast target.

7. A live broadcasting method, characterized by, The method is executed by a viewer client, and the method comprises: playing a first live broadcast session; displaying a first preferential activity of the first live broadcast session; The first preferential activity is generated based on live data of the first live broadcast session, preferential information and a live broadcast target; the preferential information and the live broadcast target are set by a management account of the first live broadcast session; the preferential information is used to determine a total preferential range of the first live broadcast session; and the live broadcast target is used to indicate a target value expected to be achieved by the first live broadcast session in at least one evaluation dimension.

8. A computer device, comprising: The computer device comprises a processor and a memory, and the memory stores at least one program, which is loaded and executed by the processor to implement the live broadcast method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The readable storage medium stores at least one program, which is loaded and executed by the processor to implement the live broadcast method according to any one of claims 1 to 7.

10. A computer program product, characterised in that, The computer program product comprises computer instructions stored in a computer readable storage medium, and the processor of the computer device reads the computer instructions from the computer readable storage medium, and executes the computer instructions, so that the computer device executes the live broadcast method according to any one of claims 1 to 7.

Images