Live broadcast content display method and device, electronic equipment and terminal

Abstract

The invention provides a live broadcast content display method and device, electronic equipment and a terminal. The text summary of the live broadcast segment corresponding to the recommended object is displayed under the condition that the first input of the recommended object is received, so that a user can quickly know the main body condition of the recommended object, the user does not need to watch a complete live broadcast video or live broadcast segment, the purchasing time of the user can be effectively saved, and the shopping experience of the user is improved.

Description

Technical Field

[0001] The present invention relates to the field of video live broadcast technology, and in particular to a live broadcast content display method, device, electronic equipment and terminal. Background Art

[0002] Live streaming e-commerce is a new online shopping model that combines e-commerce and live streaming technology. In this model, merchants or individual anchors display products in real time through live streaming platforms, introduce product features, usage methods, discount information, etc. to viewers, and provide instant purchase links or QR codes. Viewers can place orders directly during the live streaming process.

[0003] During the e-commerce live broadcast, the host will explain multiple recommended objects (such as cosmetics and food). After the audience enters the live broadcast room, if they miss the explanation of the recommended objects, they often hope to quickly understand the recommended objects so that they can choose the recommended objects of interest from among the many recommended objects.

[0004] However, in existing e-commerce live broadcast technology, viewers need to replay the explanation video to understand the situation of missing the recommended object, which can easily cause great inconvenience to users. Summary of the invention

[0005] The embodiments of the present invention provide a live content display method, device, electronic device and terminal to solve the problem that the existing live explanation video is not convenient for users to quickly understand the recommended objects.

[0006] In a first aspect, an embodiment of the present invention provides a method for displaying live content, the method comprising:

[0007] Obtain the live clip of explaining the recommended object in the live video;

[0008] Identify the content of the live broadcast segment and obtain a text summary;

[0009] In response to a first input for the recommendation object, the text summary is displayed.

[0010] Optionally, the live content display method further includes:

[0011] In case of receiving a second input for the text summary, hiding the text summary.

[0012] Optionally, in the live content display method, the text summary includes at least one of price, features, discount information, regional selection preference, and power consumption.

[0013] Optionally, in the live content display method, identifying the content of the live segment to obtain a text summary includes:

[0014] Extracting audio data from the live broadcast segment;

[0015] Performing speech recognition on the audio data to obtain text information;

[0016] Extracting core selling points and key data fields from the text information;

[0017] The text summary is obtained according to the core buying points and key data fields.

[0018] Optionally, in the live content display method, before performing speech recognition on the audio data, the method further includes:

[0019] The audio data is subjected to signal processing, wherein the signal processing at least includes noise reduction and speech enhancement processing.

[0020] Optionally, in the live content display method, extracting core selling points and key data fields from the text information includes:

[0021] The text information is analyzed using natural speech processing technology to extract the core selling points and the key data fields.

[0022] Optionally, in the live content display method, obtaining the text summary according to the core selling points and key data fields includes:

[0023] The core selling points and the key data are integrated by using summary generation technology to generate the text summary.

[0024] Optionally, the live content display method further includes:

[0025] In response to a third input for the recommendation object, the live broadcast segment is played.

[0026] Optionally, the live content display method further includes:

[0027] In response to a fourth input for the recommended object, the text information is displayed.

[0028] Optionally, in the live broadcast content display method, displaying the text summary includes:

[0029] The text summary is displayed in the area where the object identifier of the recommended object is located.

[0030] Optionally, the live broadcast content display method, after displaying the text summary, further includes:

[0031] Displaying a comment interface for the recommended object;

[0032] Responding to input on the comment interface, obtaining interactive information;

[0033] According to the interactive information, the display order and explanation strategy of the recommended objects in the live broadcast interface are updated.

[0034] In a second aspect, an embodiment of the present invention provides a live content display device, the device comprising:

[0035] The first acquisition module is used to acquire a live segment explaining the recommended object in the live video;

[0036] A content recognition module, used to recognize the content of the live broadcast segment and obtain a text summary;

[0037] The first display module is used to display the text summary in response to a first input for the recommendation object.

[0038] Optionally, the live content display device further includes:

[0039] The hiding module is used to hide the text summary when receiving a second input for the text summary.

[0040] Optionally, in the live content display device, the text summary includes at least one of price, features, discount information, regional selection preference, and power consumption.

[0041] Optionally, in the live content display device, the content identification module includes:

[0042] A first determining unit, configured to extract audio data from the live broadcast segment;

[0043] A speech recognition unit, used to perform speech recognition on the audio data to obtain text information;

[0044] A second determining unit, configured to extract core selling points and key data fields from the text information;

[0045] The third determining unit is used to obtain the text summary according to the core buying points and key data fields.

[0046] Optionally, in the live content display device, the content identification module further includes:

[0047] The signal processing unit is used to perform signal processing on the audio data before performing speech recognition on the audio data, and the signal processing at least includes noise reduction and speech enhancement processing.

[0048] Optionally, in the live content display device, the second determination unit is specifically used to analyze the text information using natural speech processing technology to extract the core selling points and the key data fields.

[0049] Optionally, in the live content display device, the third determination unit is specifically used to utilize summary generation technology to integrate the core selling points and the key data to generate the text summary.

[0050] Optionally, the live content display device further includes:

[0051] The second display module is used to play the live broadcast segment in response to a second input for the recommended object.

[0052] Optionally, the live content display device further includes:

[0053] The third display module is used to display the text information in response to a third input for the recommended object.

[0054] Optionally, in the live content display device, a first display module is specifically used to display the text summary in an area where the object identifier of the recommended object is located.

[0055] Optionally, the live content display device further includes:

[0056] A fourth display module, used to display a comment interface for the recommended object after displaying the text summary;

[0057] A second acquisition module, configured to acquire interactive information in response to input on the comment interface;

[0058] An updating module is used to update the display order and explanation strategy of the recommended objects in the live broadcast interface according to the interactive information.

[0059] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a processor, a communication interface, a memory, and a communication bus; wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0060] Memory, used to store computer programs;

[0061] The processor is used to implement the steps in the live content display method described in the first aspect or the second aspect when executing the program stored in the memory.

[0062] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the live content display method described in the first aspect above.

[0063] In a fifth aspect, an embodiment of the present invention provides a terminal, comprising the live content display device as described in the second aspect above.

[0064] Compared with the prior art, the present invention has the following advantages:

[0065] In the embodiment of the present invention, a live segment explaining the recommended object is obtained in the live video; the content of the live segment is identified to obtain a text summary; and in response to a first input for the recommended object, the text summary is displayed. By displaying the text summary of the live segment corresponding to the recommended object when receiving the first input for the recommended object, the user can quickly understand the main situation of the recommended object without the user having to watch the complete live video or live segment, which can effectively save the user's shopping time and improve their shopping experience.

[0066] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for describing the embodiments are briefly introduced below.

[0068] Figure 1 A schematic diagram of a live content display method provided by an embodiment of the present invention;

[0069] Figure 2 A schematic diagram of a live content display method provided by a preferred embodiment of the present invention;

[0070] Figure 3 A complete flow chart for implementing live content display in an embodiment of the present invention;

[0071] Figure 4 A schematic diagram of a live content display device provided by an embodiment of the present invention;

[0072] Figure 5 A block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0073] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can also be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0074] Figure 1 A method for displaying live content is provided by an embodiment of the present invention, and the method includes steps 101 to 103:

[0075] The live content display method provided in the embodiment of the present invention is applied to. Specifically, the live content display method of the embodiment of the present application can be executed by a computer device, wherein the computer device can be a terminal or a server. The terminal can be a terminal device such as a smart phone, a tablet computer, a laptop computer, a touch screen, a personal computer (PC, Personal Computer), a personal digital assistant (PDA, Personal Digital Assistant), etc. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0076] In actual implementation, a client, such as a live broadcast client, is provided on the terminal, and the host can broadcast live through the client; and the audience can watch the live broadcast through the client. Here, the terminal can be located at the host end or at the audience end.

[0077] Among them, the client on the anchor side and the client on the audience side establish a connection through the background server.

[0078] It should be noted that the data acquisition process and related data involved in the embodiments of the present invention are all carried out in compliance with the corresponding data protection laws and policies of the country where they are located, and with the authorization given by the corresponding device owner.

[0079] Step 101: Obtain a live segment in which a recommended object is explained in a live video.

[0080] In the above step 101, the above live video is a video recorded in the current live broadcast session, and the above live clip is a video clip corresponding to the host's explanation of the recommended object. It can be understood that the above live clip and the recommended object are in a one-to-one correspondence.

[0081] In some embodiments, the live video may be an entire live video that has been played or a recorded video of the current live broadcast. Specifically, the user needs to obtain the above live video by clicking on the terminal interface, for example, after the live broadcast ends, obtain the complete live video of this live broadcast; or, when receiving a live video acquisition instruction, obtain the live video that has been played before the current time point.

[0082] In the above step 101, after acquiring the above live video, the live video is intercepted to obtain a live segment for explaining each recommended object.

[0083] In some embodiments, the start time of the explanation of each recommended object can be obtained first, and then the live video can be divided according to the start time point to obtain the live segment corresponding to each recommended object, that is, for each recommended object, the live segment corresponding to the recommended object starts from the start time point of the explanation of the recommended object and ends at the start time point of the explanation of the next recommended object; or, the end time of the explanation of each recommended object can be obtained first, and then the live video can be divided according to the end time point to obtain the live segment corresponding to each recommended object, that is, for each recommended object, the live segment corresponding to the recommended object starts from the end time point of the explanation of the previous recommended object and ends at the end time point of the explanation of the recommended object; or, the start time point and end time point of the explanation of each recommended object can be obtained, and for each recommended object, the live segment corresponding to the recommended object starts from the start time point of the explanation of the recommended object and ends at the end time point of the explanation of the recommended object.

[0084] In practical applications, the start time and / or end time of explaining each recommended object can be determined by identifying the content at each time point of the live video. The above-mentioned content identification can be identification of picture content or identification of voice content.

[0085] In an embodiment of the present invention, the server automatically edits the explanation content corresponding to the above-mentioned recommended object from the live video according to the content recognition result to obtain the corresponding live clip; wherein, the live clip is used for the audience to view the host's explanation content on the corresponding recommended object when replaying the target live clip.

[0086] Step 102: Identify the content of the live broadcast segment and obtain a text summary.

[0087] In the above step 102, the text summary is a text summary after eliminating irrelevant interactive words and repeated words in the host's explanation of the recommended object. The text summary can describe the main selling points of the recommended object without the need for personal integration of information.

[0088] In the above step 102, by identifying the content of the live broadcast segment, the host's explanation content on the corresponding recommended object is obtained, and then the explanation content is summarized in text to obtain the above text summary.

[0089] Optionally, in one embodiment, the text summary includes at least one of price, features, preferential information, regional selection preference, and power consumption; wherein the price describes the price of the recommended object, the features describe the product features of the recommended object, the preferential information describes the current promotional strength, the regional selection preference describes the choice of product type or model in different regions, and the power consumption describes the usage cost of the recommended object.

[0090] In this implementation, the above allows users to quickly know the price, product features, discount information, usage in the current area, usage cost and other information of the current recommended object through the above text summary, which can effectively save the user's time cost in understanding the recommended object.

[0091] Step 103: In response to the first input for the recommended object, display the text summary.

[0092] In the above step 103, the first input is to determine the operation of the recommended object that needs to be understood, which can be specifically triggered by voice, gesture operation or touching the recommended object logo in the live video playback screen; therefore, when the above first input is received, the selected recommended object is directly locked, and the text summary corresponding to the recommended object is displayed in the playback screen.

[0093] Optionally, in one implementation, displaying the text summary includes step 1031:

[0094] Step 1031: Display the text summary in the area where the object identifier of the recommended object is located.

[0095] In this implementation manner, the object identifier is an identifier representing the recommended object, and specifically may be an icon of the recommended object.

[0096] In this implementation, the area where the object identifier is located may be at the object identifier, or may be within a preset distance range next to the object identifier.

[0097] In this implementation, when it is determined that the user needs to know about the recommended object, a text summary corresponding to the recommended object is displayed in the area where the object identification mark of the recommended object is located, so that the user can not only quickly know the corresponding recommended object information, but also intuitively know the recommended object corresponding to the recommended object information.

[0098] The above implementation process, by displaying a text summary of the live broadcast clip corresponding to the recommended object upon receiving the first input of the recommended object, allows the user to quickly understand the main situation of the recommended object without the need for the user to watch the complete live video or live broadcast clip, which can effectively save the user's shopping time and enhance their shopping experience.

[0099] In actual applications, the above text summary can be highlighted in the form of bubbles, rainbows, balls, etc. to facilitate user viewing.

[0100] Optionally, in one implementation manner, the live content display method provided in the embodiment of the present invention further includes step 104:

[0101] Step 104: When receiving a second input for the text summary, hide the text summary.

[0102] In the above step 104, the second input is to determine that there is no need to understand the text summary operation of the recommended object, which can be specifically triggered by voice, gesture operation or touching the text summary of the recommended object; therefore, when the above second input is received, the text summary corresponding to the recommended object is not displayed on the playback screen.

[0103] In this implementation, considering that some users do not need or do not like to display the text summary on the page, the text summary can be hidden by touching the text summary, etc., so as to meet the personalized needs of users.

[0104] Optionally, in one embodiment, Figure 2 As shown, the above step 102 specifically includes steps 121 to 124:

[0105] Step 121: extract the audio data in the live broadcast segment.

[0106] In the above step 121, after the live broadcast segment of the recommended object is determined, the audio data corresponding to the live broadcast segment is also the audio data of the host explaining the recommended object.

[0107] Step 122: Perform speech recognition on the audio data to obtain text information.

[0108] In the above step 122, the above audio data is recognized by using speech recognition technology to obtain corresponding text as the above text information.

[0109] Step 123: extract core selling points and key data fields from the text information.

[0110] In the above step 123, the above text information is analyzed to extract the core selling points and key data fields of the recommended object. The above core selling points may include price, features, discount information, power consumption and other information. The key data fields may include the user's emotional inclination towards the recommended object understood through sentiment analysis, such as regional selection preference.

[0111] Step 124: Obtain the text summary based on the core buying points and key data fields.

[0112] In the above step 124, the extracted information is integrated into concise and fluent fields as the above text summary to provide the user with the most direct and key product information.

[0113] In the above implementation, after obtaining the live broadcast segment for the recommended object, the audio data is first extracted, and then the text information carried in the audio data is identified, and then the core selling points and key data fields are extracted, and then the text is integrated to obtain a text summary that can provide users with direct and key product information.

[0114] Optionally, in a specific implementation manner, the live content display method provided in the embodiment of the present invention further includes step 120 before performing speech recognition on the audio data:

[0115] Step 120: Perform signal processing on the audio data, where the signal processing at least includes noise reduction and speech enhancement processing.

[0116] In the above specific implementation, after extracting audio data from the live broadcast segment of the recommended object, the audio is first subjected to signal processing, including pre-processing steps such as noise reduction and voice enhancement, which can effectively improve the accuracy of subsequent voice recognition.

[0117] Optionally, in a specific implementation, extracting core selling points and key data fields from the text information includes step 1231:

[0118] Step 1231: Analyze the text information using natural speech processing technology to extract the core selling points and key data fields.

[0119] In the above specific implementation manner, natural language processing (NPL) is used to analyze and extract information from the text information identified from the audio data in the live broadcast segment of the recommended object, to obtain the core selling points and key data fields of the recommended object, and then to perform text integration to obtain a text summary that can provide users with direct and key product information.

[0120] Among them, NLP technology, as a branch of artificial intelligence and linguistics, combines knowledge from multiple disciplines such as computer science, linguistics, machine learning and cognitive science, enabling computers to understand, interpret and generate human language.

[0121] Optionally, in a specific implementation, obtaining the text summary according to the core selling point and key data fields includes step 1241:

[0122] Step 1241: using summary generation technology, integrate the core selling points and the key data to generate the text summary.

[0123] In this specific implementation, summary generation technology is used to integrate the extracted core buying points and key data into a concise product text summary to provide users with the most direct and key product information.

[0124] Optionally, in one implementation, the live content display method provided in the embodiment of the present invention further includes step 105:

[0125] Step 105: In response to a third input for the recommended object, play the live broadcast segment.

[0126] In the above step 105, the third input is an operation to determine the live broadcast segment of the recommended object that needs to be viewed, which can be specifically triggered by voice, gesture operation or touching the recommended object logo in the live video playback screen; therefore, when the above second input is received, the selected recommended object is directly locked, and the live broadcast segment corresponding to the recommended object is displayed in the playback screen.

[0127] The third input may be the same as or different from the first output.

[0128] Optionally, the third input may be the same as the first input, that is, the text summary and live broadcast clip corresponding to the recommended object may be simultaneously triggered by the same input.

[0129] In this implementation, upon receiving the third input to the recommended object, the live broadcast segment corresponding to the recommended object can be quickly locked and played, so that the user can know the details of the recommended object by watching the live broadcast segment, which can effectively save the user's shopping time and enhance their shopping experience.

[0130] It should be noted that for each recommended object that has been explained, after the host finishes explaining the recommended object, a live clip corresponding to the recommended object will be generated, so that the user can accurately view the explanation content for the recommended object by playing the live clip; for the user side, the playback function item corresponding to the recommended object will be displayed in the position associated with the recommended object in the recommendation list, for playing the live clip corresponding to the recommended object.

[0131] In actual applications, after obtaining the live broadcast segment, the server sends it to the user end, and the user end displays the playback function item of the corresponding recommended object in the recommendation list in the live broadcast interface, so that the user can view the live broadcast segment of the corresponding recommended object by triggering the corresponding playback function item.

[0132] Optionally, in one implementation, the live content display method provided in the embodiment of the present invention further includes step 106:

[0133] Step 106: In response to a fourth input for the recommended object, display the text information.

[0134] In the above step 106, the fourth input is an operation to determine the need to view the text information of the recommended object, which can be specifically triggered by voice, gesture operation or touching the recommended object logo in the live video playback screen; therefore, when the above fourth input is received, the text information corresponding to the audio information in the live clip for the recommended object is displayed in the playback screen, that is, while the system plays the live clip in the playback screen, it can also provide oral audio-to-text service, so that the hearing-impaired can also know the details of the recommended object through the above text information, thereby ensuring barrier-free transmission of information.

[0135] The fourth input may be the same as or different from the third output.

[0136] Optionally, the fourth input may be the same as the third input, that is, the same input may simultaneously trigger the playing of the live segment corresponding to the recommended object and the display of text information.

[0137] In this implementation, when the fourth input to the recommended object is received, the live broadcast segment corresponding to the recommended object can be quickly locked and the corresponding text information can be displayed, so that the hearing-impaired people can know the details of the recommended object by viewing the text information, thereby improving their shopping experience.

[0138] Optionally, in an implementation manner, the live broadcast content display method provided in the embodiment of the present invention further includes steps 107 to 109 after displaying the text summary:

[0139] Step 107: Display a comment interface for the recommended object.

[0140] In the above step 107, in the live video playback screen, after receiving the first input of the recommended object, the recommended object is locked and the text summary of its corresponding live segment is displayed, so that the user can obtain the information of the recommended object, and then the above comment interface is displayed in the live video playback screen, so that the user can provide feedback through the live broadcast platform. The system collects these feedbacks for improving product introductions and interactive methods.

[0141] Step 108: In response to the fifth input to the comment interface, obtain interactive information.

[0142] In the above step 108, the fifth input is an operation for determining the input of interactive information on the recommended object, which can be specifically triggered by voice, gesture operation or touching the recommended object logo in the live video playback screen; therefore, when the above fifth input is received, the information input by the user through the above comment interface is obtained as the above interactive information.

[0143] Step 109: Update the display order and explanation strategy of the recommended objects in the live broadcast interface according to the interactive information.

[0144] In the above step 109, the live broadcast platform analyzes the above interactive information to understand which products users are more interested in, and then adjusts the display order and promotion explanation strategy to improve user experience and purchase conversion rate.

[0145] In the above implementation, after the user obtains the information of the recommended object through text summary, he or she can provide feedback by commenting on the comment interface provided by the live broadcast platform. After collecting the above feedback information, the system analyzes the data and optimizes the product display sequence and explanation strategy, thereby improving the user experience and purchase conversion rate.

[0146] In actual applications, the system links the click action to the background when the user clicks on the product on the terminal screen, understands the recommended objects (products) that the user is more interested in, and then adjusts the display order and promotion explanation strategy of the recommended objects.

[0147] Specifically, after the user clicks on the object identifier of the recommended object on the live broadcast room interface, the front-end JavaScript captures the click event and sends the clicked recommended object information as data to the back-end server; after the back-end server receives the click event data, it stores the click data in the database for subsequent analysis; the back-end server uses real-time data stream platforms such as Apache Kafka to receive and process user click streams; the back-end server applies data analysis algorithms to analyze user click data and identify popular products and user preferences; then the back-end server updates the recommendation algorithm based on the results of user behavior analysis, thereby adjusting the order of product display.

[0148] In actual applications, users usually interact with anchors through online comments. However, if there are many people in the live broadcast room, the comments will often be drowned by the massive amount of information, and it is difficult for the anchor to see the user's demands. In the embodiment of the present invention, the comment data is summarized in real time through the background data, and responses are given to frequently occurring problems, important user questions, and typical questions, thereby reducing the pressure on the anchor and improving the user experience.

[0149] Specifically, users submit questions or feedback through the comment function in the live broadcast room, and the front end sends the comment data to the back-end server; the back-end server uses stream processing technology, such as Apache Flink, to process the received comment data in real time, and performs NLP preprocessing on the comment data, including word segmentation, removal of stop words, etc., and uses sentiment analysis technology to identify the emotional tendency of the comments, uses keyword extraction technology to identify high-frequency words in the comments, and then uses pattern recognition technology to identify problem statements from the comments, and groups similar comments through clustering analysis to identify high-frequency and typical problems; the back-end server displays the above analysis results to the anchor and operation team through a visual dashboard, including comment summaries, hot issues and sentiment trends; at the same time, the back-end server generates reply suggestions based on the comment analysis results to assist the anchor to respond to users quickly, and integrates user feedback data into the recommendation system to continuously optimize product recommendation and display strategies.

[0150] Optionally, in one implementation, the live content display method provided in the embodiment of the present invention further includes step 110:

[0151] Step 110: upon receiving a sixth input from the host terminal to the first user terminal, establish a communication connection between the first user terminal and the host terminal.

[0152] In this implementation, the sixth input is an operation of selecting the first user with whom interaction is required, that is, the host opens the linkage authority for the first user, which can be specifically triggered by voice, gesture operation or touching the first user identifier in the live broadcast screen; therefore, when the above-mentioned sixth input is received, a communication connection is established between the host end and the first user end, so that the first user can interact with the host in real time.

[0153] In practical applications, the above communication connection may be a voice communication connection, a video communication connection or a text communication connection.

[0154] Optionally, in a specific implementation, the above step 110 specifically includes steps 1101 to 1102:

[0155] Step 1101: upon receiving a sixth input from the host terminal to a first user terminal, sending a first communication request to the first user terminal;

[0156] Step 1102: upon receiving a seventh input from the first user terminal in response to the first communication request, establishing a communication connection between the first user terminal and the anchor terminal.

[0157] In this specific implementation, the seventh input is an operation to determine establishing a communication connection with the anchor end, which can be specifically triggered by touching the response control for the communication request; when the above-mentioned seventh input is received, it indicates that the first user end is willing to communicate with the anchor end, thereby establishing a communication connection between the two.

[0158] Optionally, in a specific implementation, after sending the first communication request to the first user terminal, the above step 110 further includes step 1103:

[0159] Step 1103: upon receiving the eighth input from the first user terminal in response to the first communication request, reject the communication request from the anchor terminal in response to the first user terminal.

[0160] In this specific implementation, the eighth input is an operation of refusing to establish a communication connection with the anchor end, which can be specifically triggered by touching the rejection control for the communication request; when the above-mentioned eighth input is received, it indicates that the first user end does not want to communicate with the live broadcast end, and thus refuses to establish a communication connection between the two.

[0161] In actual applications, when the first user terminal receives a communication request from the anchor terminal, the first user terminal can choose whether to interact with the anchor terminal in a live broadcast according to its own wishes, rather than being unilaterally screened by the anchor terminal, thereby giving the user terminal more rights of independent choice.

[0162] Optionally, in one implementation, the live content display method provided in the embodiment of the present invention further includes steps 111 to 112:

[0163] Step 111: upon receiving a ninth input from the second user terminal to the host terminal, sending a second communication request to the host terminal;

[0164] Step 112: upon receiving the tenth input from the host terminal in response to the second communication request, establishing a communication connection between the second user terminal and the host terminal.

[0165] In this implementation, the ninth input is an operation in which the user chooses to interact with the anchor, which can be specifically triggered by voice, gesture operation, or touching the anchor logo in the live broadcast screen.

[0166] In this implementation, the tenth input is an operation for the host end to determine to establish a communication connection with the second user end, which can be specifically triggered by the host end by touching the response control for the second communication request; when the above-mentioned tenth input is received, it indicates that the host end is willing to communicate with the second user end, and thus a communication connection is established between the two.

[0167] In actual applications, because different users are concerned about different recommended object information, there is a situation where the information about the recommended object that the user needs to know may not be explained by the anchor in the live broadcast segment, nor recorded in the details page of the recommended object. At this time, the user can send a second communication request to the anchor end according to the above implementation method to request the anchor to give a personalized explanation of the recommended object.

[0168] Optionally, in a specific implementation manner, the live content display method provided in the embodiment of the present invention, after sending the second communication request to the second user terminal, further includes step 113:

[0169] Step 113: When receiving the eleventh input from the host terminal in response to the second communication request, reject the communication request from the second user terminal to the host terminal.

[0170] In this specific implementation, the eleventh input is an operation of refusing to establish a communication connection with the anchor end, which can be specifically triggered by touching the rejection control for the communication request; when the above eleventh input is received, it indicates that the anchor end does not want to communicate with the second user end, and thus refuses to establish a communication connection between the two.

[0171] In actual applications, when the host terminal receives a communication request from the second user terminal, the host terminal can choose whether to interact with the second user terminal in a live broadcast according to its own wishes, thereby ensuring that the live broadcast interaction is carried out in an orderly manner.

[0172] Optionally, in a specific implementation, when receiving second communication requests from multiple second user terminals, the client identification of each second user terminal is simultaneously displayed in the live broadcast screen, and when the anchor terminal touches any client identification through the above-mentioned tenth input, a communication connection between the second user terminal corresponding to the client identification and the anchor terminal is established.

[0173] Optionally, in another specific implementation, when receiving second communication requests from multiple second user terminals, the second user terminals are sorted in chronological order according to the time of issuing the second communication requests, and the client identifier of the second user terminal that first issues the second communication request is displayed in the live broadcast screen; when the anchor terminal touches the client identifier through the tenth input mentioned above, a communication connection between the second user terminal corresponding to the client identifier and the anchor terminal is established; when the anchor terminal touches the client identifier through the eleventh input mentioned above, the communication connection between the second user terminal corresponding to the client identifier and the anchor terminal is rejected, and the client identifier of the second user terminal that first issues the second communication request among the remaining second user terminals is displayed in the live broadcast screen.

[0174] In this specific implementation, only the client identifier of the second user terminal that sends the communication request earliest is displayed in the live broadcast screen, and the other second user terminals will be suspended, waiting in turn for the host terminal to select or refuse to establish a communication connection, making the live broadcast screen of the host terminal more neat and orderly.

[0175] Optionally, in one implementation, the live content display method provided in the embodiment of the present invention further includes step 114:

[0176] Step 114: When a communication connection has been established between the host end and the target user end, if a twelfth input from the host end or the second user end for the communication connection is received, the communication connection is disconnected.

[0177] In this implementation, the twelfth input is an operation to end the communication connection, which can be specifically triggered by touching the end control of the communication connection, that is, it can be triggered by the host end touching the end control of the host end, or it can be triggered by the second user end touching the end control of the second user end; when the above-mentioned twelfth input is received, it means that the host end wishes to end the communication with the second user end, or the second user end wishes to end the communication with the host end, thereby disconnecting the communication connection established between the two.

[0178] Regarding the interaction between the anchor and the user, the following is a simplified process example:

[0179] Anchor side: The anchor clicks the "Enable linkage permissions" button in the live broadcast software, and then the system sends a permission grant notification to the selected user.

[0180] User side: After receiving the notification, the user can choose to accept or reject. If the user chooses to accept, the system will establish a real-time communication connection, and the user can see the host's screen and interact. If the user chooses to reject, the system will not establish a real-time communication connection between the user and the host, and will notify the host of the rejection so that the host knows. Of course, after receiving the notification, the user can choose to ignore it. In this case, the system will not establish a real-time communication connection between the user and the host, and will feedback the result of the communication failure to the host after waiting for a preset period of time so that the host knows.

[0181] Among them, the interactive functions may include sending messages, drawing, participating in voting or other interactive activities. That is, after the user accepts the permission granting notification sent by the anchor and the system establishes a real-time connection, a chat window can be established on both the anchor side and the user side for the user to send messages through the chat window, and the user can also be allowed to use the brush tool to draw on the anchor screen, and the user can participate in voting or other interactive activities.

[0182] Optionally, in one implementation, the live content display method provided in the embodiment of the present invention further includes step 115:

[0183] Step 115: When the thirteenth input for the recommended object is received, a purchase page for the recommended object is displayed.

[0184] In this implementation, the thirteenth input is an operation to determine the purchase of the recommended object, which can be specifically triggered by the user at the user end by clicking on the object identifier of the object; when the thirteenth input is received, it indicates that the user needs to purchase the recommended object, and thus a link is automatically linked to jump to the purchase page of the recommended object, which can simplify the user's operation process.

[0185] In actual applications, after the user clicks on the recommended object icon in the video playback screen, the live broadcast platform automatically jumps the user interface to the corresponding recommended object page in the virtual showcase without the user having to search manually.

[0186] Figure 2 A live content display method provided by a preferred embodiment of the present invention includes steps 201 to 212:

[0187] Step 201: Obtain a live segment in the live video that explains the recommended object.

[0188] The above step 201 may refer to step 101 for details, and will not be described again here to avoid repetition.

[0189] Step 202: extract the audio data in the live broadcast segment.

[0190] The above step 202 may refer to step 121 for details, and will not be described again to avoid repetition.

[0191] Step 203: perform signal processing on the audio data, wherein the signal processing at least includes noise reduction and speech enhancement processing.

[0192] The above step 203 may be specifically referred to as step 120 , and will not be described again to avoid repetition.

[0193] Step 204: Perform speech recognition on the audio data to obtain text information.

[0194] The above step 204 may be specifically referred to as step 122 , and will not be described again to avoid repetition.

[0195] Step 205: Analyze the text information using natural speech processing technology to extract core selling points and key data fields.

[0196] The above step 205 may be specifically referred to as step 1231 , and will not be described again here to avoid repetition.

[0197] Step 206: using summary generation technology, integrate the core selling points and the key data to generate a text summary.

[0198] The above step 206 may be specifically referred to as step 1241 , and will not be described again here to avoid repetition.

[0199] Step 207: In response to the first input for the recommended object, display the text summary in the area where the object identifier of the recommended object is located.

[0200] The above step 207 may be specifically referred to step 103 and step 1031 , and will not be described again to avoid repetition.

[0201] Step 208: When receiving a second input for the text summary, hide the text summary.

[0202] The above step 208 may be specifically referred to as step 104, and will not be described again to avoid repetition.

[0203] Step 209: In response to a third input for the recommended object, play the live broadcast segment.

[0204] The above step 209 may refer to step 105 for details, and will not be described again to avoid repetition.

[0205] Step 210: In response to a fourth input for the recommended object, display the text information.

[0206] The above step 210 may be specifically referred to as step 106 , and will not be described again here to avoid repetition.

[0207] Step 211: display a comment interface for the recommended object.

[0208] The above step 211 may refer to step 107 for details, and will not be described again to avoid repetition.

[0209] Step 212: In response to input on the comment interface, obtain interactive information.

[0210] The above step 212 may be specifically referred to as step 108, and will not be described again to avoid repetition.

[0211] Step 213: Update the display order and explanation strategy of the recommended objects in the live broadcast interface according to the interactive information.

[0212] The above step 213 may be specifically referred to as step 109 , and will not be described again to avoid repetition.

[0213] In an embodiment of the present invention, when a first input to a recommended object is received, a text summary of a live broadcast segment corresponding to the recommended object is displayed, so that the user can quickly understand the main situation of the recommended object without the user having to watch the complete live video or live broadcast segment, which can effectively save the user's shopping time and improve their shopping experience; when a second input to the text summary is received, the text summary is hidden; at the same time, when a third input to the recommended object is received, the live broadcast segment corresponding to the recommended object can be quickly locked and played, so that the user can know the details of the recommended object by watching the live broadcast segment, which can effectively save the user's shopping time and improve their shopping experience; in addition, when a fourth input to the recommended object is received, the live broadcast segment corresponding to the recommended object can be quickly locked and the corresponding text information can be displayed, so that the hearing-impaired can know the details of the recommended object by watching the text information, thereby improving their shopping experience; finally, after the user obtains the information of the recommended object through the text summary, the user can provide feedback by commenting on the comment interface provided by the live broadcast platform. The system collects the above feedback information and analyzes the data, thereby optimizing the product display sequence and explanation strategy, thereby improving the user experience and purchase conversion rate.

[0214] See also Figure 3 , showing a complete flow chart for implementing live content display.

[0215] In step 301, the user registers an account on the live broadcast platform using a mobile phone number or email address, and sets a personal password to log in so that the system can record the user's shopping history and preferences.

[0216] In step 302, before the live broadcast begins, the anchor sets linkage permissions through the management interface of the live broadcast platform, including opening and closing permissions and authorization of specific users.

[0217] In step 303, when watching the live broadcast, the user clicks on the product of interest on the screen, and the action is sent to the anchor end through the interactive system of the live broadcast platform.

[0218] In step 304, after the host-side client receives the user's selection signal, the system automatically highlights the product on the host's screen and provides product information and inventory status.

[0219] In step 305, the host marks and identifies the product according to the user's selection, and the system records this action for subsequent automatic jumps and information aggregation.

[0220] In step 306, after the user clicks on a product, the live streaming platform system automatically redirects the user interface to the corresponding product page in the shared cart without the need for the user to search manually.

[0221] In step 307, the host explains the marked product in detail and can interact with the user in real time through linkage permissions, such as answering questions or providing additional information.

[0222] In step 308, if the user misses the product introduction, the user can click on the product icon in the live broadcast room, and the system will provide a text summary of the core selling points of the product.

[0223] In step 309, the system automatically generates a text summary of the product based on the host's explanation, including but not limited to price, features, discount information, and some user relationship information that may not be displayed on the product details page, such as the choice of air conditioner performance in different regions, the approximate power consumption of air conditioners, etc., so that users can quickly understand the selling points without the need to personally integrate information.

[0224] In step 310, when the user is replaying, the system displays a text summary next to the product to help the user quickly understand the product information and improve decision-making efficiency.

[0225] In step 311, for hearing-impaired users, the system can provide not only a text summary but also a spoken audio-to-text service to ensure barrier-free transmission of information.

[0226] In step 312, after obtaining product information, the user can provide feedback through the live broadcast platform, and the system collects this feedback to improve product introduction and interaction methods.

[0227] In step 313, the live broadcast platform analyzes the user interaction data, optimizes the product display sequence and explanation strategy, and improves the user experience and purchase conversion rate.

[0228] In step 314, the live broadcast platform regularly maintains and updates the functions of the intelligent interactive system to ensure system stability and user satisfaction.

[0229] In an embodiment of the present invention, through the above steps, users can interact with the anchor more intuitively and efficiently through the client on terminals such as mobile phones and tablets, thereby improving the user experience, reducing the time users spend searching for products, and providing convenience for the hearing impaired, thereby ensuring accurate transmission of information and the user's shopping experience.

[0230] Figure 4 is a schematic diagram of a live content display device provided by an embodiment of the present invention, the device comprising:

[0231] The first acquisition module 41 is used to acquire a live segment explaining the recommended object in the live video;

[0232] A content recognition module 42 is used to recognize the content of the live broadcast segment and obtain a text summary;

[0233] The first display module 43 is used to display the text summary in response to the first input for the recommended object.

[0234] Optionally, the live content display device further includes:

[0235] The hiding module is used to hide the text summary when receiving a second input for the text summary.

[0236] Optionally, in the live content display device, the text summary includes at least one of price, features, discount information, regional selection preference, and power consumption.

[0237] Optionally, in the live content display device, the content identification module includes:

[0238] A first determining unit, configured to extract audio data from the live broadcast segment;

[0239] A speech recognition unit, used to perform speech recognition on the audio data to obtain text information;

[0240] A second determining unit, configured to extract core selling points and key data fields from the text information;

[0241] The third determining unit is used to obtain the text summary according to the core buying points and key data fields.

[0242] Optionally, in the live content display device, the content identification module further includes:

[0243] The signal processing unit is used to perform signal processing on the audio data before performing speech recognition on the audio data, and the signal processing at least includes noise reduction and speech enhancement processing.

[0244] Optionally, in the live content display device, the second determination unit is specifically used to analyze the text information using natural speech processing technology to extract the core selling points and the key data fields.

[0245] Optionally, in the live content display device, the third determination unit is specifically used to utilize summary generation technology to integrate the core selling points and the key data to generate the text summary.

[0246] Optionally, the live content display device further includes:

[0247] The second display module is used to play the live broadcast segment in response to a third input for the recommended object.

[0248] Optionally, the live content display device further includes:

[0249] The third display module is used to display the text information in response to a fourth input for the recommended object.

[0250] Optionally, in the live content display device, a first display module is specifically used to display the text summary in an area where the object identifier of the recommended object is located.

[0251] Optionally, the live content display device further includes:

[0252] A fourth display module, used to display a comment interface for the recommended object after displaying the text summary;

[0253] A second acquisition module, configured to acquire interactive information in response to input on the comment interface;

[0254] An updating module is used to update the display order and explanation strategy of the recommended objects in the live broadcast interface according to the interactive information.

[0255] An embodiment of the present invention further provides a terminal, comprising the live content display device as described above.

[0256] As for the above-mentioned device and terminal embodiments, since they are basically similar to the live content display method embodiments, the relevant parts can be referred to the partial description of the method embodiments.

[0257] The live content display device and terminal provided by the embodiments of the present invention, by displaying a text summary of the live broadcast segment corresponding to the recommended object upon receiving the first input of the recommended object, allows the user to quickly understand the main situation of the recommended object without the user having to watch the complete live video or live broadcast segment, which can effectively save the user's shopping time and enhance their shopping experience.

[0258] The embodiment of the present invention further provides an electronic device, such as Figure 5 As shown, it includes a processor 501 , a communication interface 502 , a memory 503 and a communication bus 504 , wherein the processor 501 , the communication interface 502 , and the memory 503 communicate with each other via the communication bus 504 .

[0259] The memory 503 is used to store computer programs.

[0260] When the processor 501 is used to execute the program stored in the memory 503, the following steps are implemented:

[0261] Obtain the live clip of explaining the recommended object in the live video;

[0262] Identify the content of the live broadcast segment and obtain a text summary;

[0263] In response to a first input for the recommendation object, the text summary is displayed.

[0264] Among them, the processor 501 can also implement other steps in the above-mentioned live content display method, which will not be repeated here.

[0265] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus or a Controller Area Network (CAN) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0266] The communication interface is used for communication between the above electronic device and other devices.

[0267] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Alternatively, the memory may also be at least one storage device located away from the aforementioned processor.

[0268] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0269] In another embodiment of the present invention, a computer-readable storage medium is provided, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the live content display method described in the above embodiment.

[0270] In another embodiment provided by the present invention, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute the live content display method described in the above embodiment.

[0271] In another embodiment of the present invention, a terminal is provided. The terminal includes the above-mentioned electronic device.

[0272] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0273] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0274] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. For the embodiments of the device, electronic device, computer-readable storage medium and computer program products containing instructions, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0275] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A method for displaying live content, characterized in that: The method comprises: Obtain the live clip of explaining the recommended object in the live video; Identify the content of the live broadcast segment and obtain a text summary; In response to a first input for the recommendation object, the text summary is displayed.

2. The method for displaying live content according to claim 1, characterized in that: The method further comprises: In case of receiving a second input for the text summary, hiding the text summary.

3. The live content display method according to claim 1, characterized in that: The text summary includes at least one of price, features, discount information, region selection preference, and power consumption.

4. The live content display method according to claim 1, characterized in that: The content of the live broadcast segment is identified to obtain a text summary, including: Extracting audio data from the live broadcast segment; Performing speech recognition on the audio data to obtain text information; Extracting core selling points and key data fields from the text information; The text summary is obtained according to the core buying points and key data fields.

5. The method for displaying live content according to claim 4, characterized in that: Before performing speech recognition on the audio data, the method further includes: The audio data is subjected to signal processing, wherein the signal processing at least includes noise reduction and speech enhancement processing.

6. The method for displaying live content according to claim 4, characterized in that: Extract the core selling points and key data fields from the text information, including: The text information is analyzed using natural speech processing technology to extract the core selling points and the key data fields.

7. The method for displaying live content according to claim 4, characterized in that: According to the core buying points and key data fields, the text summary is obtained, including: The core selling points and the key data are integrated by using summary generation technology to generate the text summary.

8. The live content display method according to claim 1, characterized in that: The method further comprises: In response to a third input for the recommendation object, the live broadcast segment is played.

9. The method for displaying live content according to claim 1, characterized in that: The method further comprises: In response to a fourth input for the recommended object, the text information is displayed.

10. The method for displaying live content according to claim 1, characterized in that: Display the text summary, including: The text summary is displayed in the area where the object identifier of the recommended object is located.

11. The method for displaying live content according to claim 1, characterized in that: After displaying the text summary, the method further includes: Displaying a comment interface for the recommended object; Responding to input on the comment interface, obtaining interactive information; According to the interactive information, the display order and explanation strategy of the recommended objects in the live broadcast interface are updated.

12. A live content display device, characterized in that: include: The first acquisition module is used to acquire a live segment explaining the recommended object in the live video; A content recognition module, used to recognize the content of the live broadcast segment and obtain a text summary; The first display module is used to display the text summary in response to a first input for the recommendation object.

13. An electronic device, characterized in that: include: A processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; The processor is used to implement the steps in the live content display method as described in any one of claims 1 to 10 when executing the program stored in the memory.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the live content display method as described in any one of claims 1 to 11 are implemented.

15. A terminal, characterized in that: It includes the live content display device as described in claim 12 or the electronic device as described in claim 13.

Images