Live broadcast entrance display method, related equipment and storage medium for voice live broadcast room

Abstract

The present invention discloses a live broadcast entrance display method, related equipment and storage medium of a voice live broadcast room, wherein the live broadcast entrance display method of the voice live broadcast room comprises: obtaining the live broadcast voice of the anchor client in the voice live broadcast room to obtain the live broadcast voice audio; segmenting the live broadcast voice audio to obtain multiple voice audio segments; determining the comprehensive score of each voice audio segment in the multiple voice audio segments according to the popularity information and theme information of the voice live broadcast room; selecting a target voice audio segment from the multiple voice audio segments according to the comprehensive score; and displaying the playback entrance of the target voice audio segment at the live broadcast entrance of the voice live broadcast room. The present invention improves the efficiency of users screening voice live broadcast rooms, and improves the user experience effect.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to a live broadcast entrance display method, related equipment and storage medium for a voice live broadcast room. Background Art

[0002] With the development of Internet technology, live broadcasting provides users with a more intuitive and fast channel to obtain information, and various live broadcasting methods are emerging one after another. Voice live broadcasting is a pure audio live broadcasting method different from video live broadcasting. Voice live broadcasting is similar to a radio station, but different from a radio station. Voice live broadcasting is provided by the host client with a pure audio data stream, which is forwarded by the server and listened to on the audience client. The server usually divides a host client and the corresponding audience client into the same voice live broadcast room. Voice live broadcasting has a relatively strong interactivity, which allows interaction and gift-giving between the host and the audience.

[0003] In the related art, the voice live broadcast platform displays a list of voice live broadcast rooms. When a user searches for a desired voice live broadcast room from the list, the user can only enter each voice live broadcast room in turn and listen to the real-time live broadcast content in each voice live broadcast room, resulting in low screening efficiency for the voice live broadcast room and poor user experience. Summary of the invention

[0004] In order to solve the problems of the prior art, the embodiment of the present invention provides a method for displaying a live broadcast entrance of a voice live broadcast room, related equipment and storage medium. The technical solution is as follows:

[0005] On the one hand, a method for displaying a live broadcast entrance of a voice live broadcast room is provided, the method comprising:

[0006] Get the live voice of the anchor client in the voice live room and get the live voice audio;

[0007] Segmenting the live voice audio to obtain multiple voice audio segments;

[0008] Determine a comprehensive score of each of the plurality of voice audio segments according to the popularity information and theme information of the voice live broadcast room;

[0009] Selecting a target speech audio segment from the plurality of speech audio segments according to the comprehensive score;

[0010] The playback entrance of the target voice audio segment is displayed at the live broadcast entrance of the voice live broadcast room.

[0011] On the other hand, a live broadcast entrance display device for a voice live broadcast room is provided, the device comprising:

[0012] The first acquisition module is used to acquire the live voice of the anchor client in the voice live broadcast room and obtain the live voice audio;

[0013] A segmentation processing module, used for segmenting the live voice audio to obtain multiple voice audio segments;

[0014] A first determination module is used to determine the comprehensive score of each of the multiple voice audio segments according to the popularity information and theme information of the voice live broadcast room;

[0015] A selection module, configured to select a target speech audio segment from the plurality of speech audio segments according to the comprehensive score;

[0016] The display module is used to display the playback entrance of the target voice audio segment at the live broadcast entrance of the voice live broadcast room.

[0017] Optionally, the first acquisition module includes:

[0018] The second acquisition module is used to obtain the start time of the anchor client in the voice live broadcast room;

[0019] The third acquisition module is used to obtain the live broadcast voice provided by the anchor client within a preset time period, taking the broadcast start time as the starting point.

[0020] Optionally, the segmentation processing module is specifically used to: extract voice audio segments from the live voice audio at preset time intervals to obtain multiple voice audio segments.

[0021] Optionally, the first determining module includes:

[0022] The fourth acquisition module is used to obtain the historical popularity information of the voice live broadcast room and the popularity information of the voice live broadcast room corresponding to the broadcast start time;

[0023] A second determination module is used to determine a first score of each of the multiple voice audio segments according to the historical popularity information and the popularity information of the voice live broadcast room corresponding to the start time;

[0024] A third determination module is used to determine the live broadcast theme of the voice live broadcast room and the semantics corresponding to each of the voice audio segments;

[0025] A fourth determination module, used to determine a second score of each of the voice audio segments according to the semantic similarity between the semantics corresponding to the voice audio segment and the semantics of the live broadcast theme;

[0026] The fifth determination module is used to determine the comprehensive score of the speech audio segment according to the first score and the second score.

[0027] Optionally, the second determining module includes:

[0028] A sixth determination module, configured to determine, according to the broadcast start time, first popularity information of the voice live broadcast room corresponding to each voice audio segment in the plurality of voice audio segments;

[0029] A seventh determination module, configured to determine, based on the historical heat information, the historical average heat information within the live broadcast time period corresponding to each of the voice audio segments;

[0030] The eighth determination module is used to determine the first score of each of the voice audio segments based on the comparison between the first heat information and the historical average heat information.

[0031] Optionally, the fifth determining module includes:

[0032] An extraction module, used to extract voiceprint feature information of each of the speech audio segments;

[0033] a ninth determination module, configured to determine the emotional state of the speech audio segment according to the voiceprint feature information;

[0034] a tenth determination module, configured to determine a third score of the voice audio segment according to a matching condition between the emotional state and the live broadcast theme;

[0035] An eleventh determination module is used to determine a comprehensive score of the speech audio segment according to the first score, the second score and the third score.

[0036] Optionally, the display module includes:

[0037] A judgment module, used to judge whether the semantics corresponding to the target speech audio segment meets the violation requirements;

[0038] a deleting module, configured to delete the target voice audio segment from the multiple voice audio segments when the judgment result of the judging module is yes;

[0039] A reselection module, used for reselecting a target voice audio segment from the deleted multiple voice audio segments according to the comprehensive score, and executing the judging step until the semantics corresponding to the reselected target voice audio segment does not meet the violation requirement;

[0040] The display submodule is used to display the playback entrance of the re-selected target voice audio segment at the live broadcast entrance of the voice live broadcast room.

[0041] On the other hand, a computer device is provided, including a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set are loaded and executed by the processor to implement the above-mentioned live broadcast entrance display method of the voice live broadcast room.

[0042] On the other hand, a computer-readable storage medium is provided, in which at least one instruction, at least one program, a code set or an instruction set is stored. The at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement the live broadcast entrance display method of the voice live broadcast room as described above.

[0043] The embodiment of the present invention performs segmentation processing on the live voice audio of the anchor client of the voice live room, and determines the comprehensive scores of multiple voice audio segments obtained by the segmentation processing based on the popularity information and theme information of the voice live room, determines the target voice audio segment among the multiple voice audio segments according to the comprehensive score, and displays the playback entrance of the target voice audio segment at the live broadcast entrance of the voice live room. Therefore, when browsing the voice live broadcast platform, the user can quickly find the desired voice live room by auditioning the voice audio segments displayed at the live broadcast entrances of each voice live room, thereby improving the efficiency of the user in screening the voice live room and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 is a schematic diagram of an implementation environment provided by an embodiment of the present invention;

[0046] Figure 2 It is a flow chart of a method for displaying a live broadcast entrance of a voice live broadcast room provided by an embodiment of the present invention;

[0047] Figure 3 It is a flow chart of a method for determining a comprehensive score of each voice audio segment in a plurality of voice audio segments according to popularity information and theme information of a voice live broadcast room provided by an embodiment of the present invention;

[0048] Figure 4 It is a flowchart diagram of a method for determining a comprehensive score of a speech audio segment according to a first score and a second score provided by an embodiment of the present invention;

[0049] Figure 5 It is a schematic diagram of displaying a playback entrance of a target voice audio segment at a live broadcast entrance of a voice live broadcast room provided by an embodiment of the present invention;

[0050] Figure 6 It is a flow chart of another method for displaying a live broadcast entrance of a voice live broadcast room provided by an embodiment of the present invention;

[0051] Figure 7 It is a flow chart of another method for displaying a live broadcast entrance of a voice live broadcast room provided by an embodiment of the present invention;

[0052] Figure 8 This is a schematic diagram of feeding back a target voice audio segment to a host provided by an embodiment of the present invention;

[0053] Fig. 9 It is a structural schematic diagram of a live broadcast entrance display device for a voice live broadcast room provided by an embodiment of the present invention;

[0054] Fig.10 It is a hardware structure diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0056] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0057] See also Figure 1 , which is a schematic diagram of an implementation environment provided by an embodiment of the present invention, and the implementation environment may include an anchor client 110, a voice live broadcast server 120 and an audience client 130.

[0058] Among them, the anchor client 110 and the audience client 130 are located in the voice live broadcast room 140, which is a virtual room in the voice live broadcast platform. The voice live broadcast room 140 is established when the anchor client 110 initiates a voice live broadcast. The voice live broadcast room 140 can receive the audience client 130 to enter and listen to the anchor client's voice live broadcast and interact with the anchor client. For example, the audience client 130 can comment on the anchor client 110, send gifts, send barrages, etc.

[0059] The host client 110 and the audience client 130 may be terminal devices such as smart phones, desktop computers, tablet computers, laptop computers, etc. with various operating systems, or they may be software configured in the above terminal devices, such as applications.

[0060] The voice live broadcast server 120 may be a server that provides service support for the voice live broadcast platform, such as providing forwarding of live voice, etc. The voice live broadcast server 120 may include an independently operated server, or a distributed server, or a server cluster consisting of multiple servers.

[0061] The voice live broadcast server 120 and the host client 110 can be connected and communicated through a wired network or a wireless network, and the voice live broadcast server 120 and the audience client 130 can be connected and communicated through a wired network or a wireless network.

[0062] See also Figure 2 , which is a flow chart of a method for displaying a live broadcast entrance of a voice live broadcast room provided by an embodiment of the present invention. The method can be applied to a terminal or a server or a coupling between a terminal and a server. Figure 1 The anchor client 110 in the illustrated implementation environment is used as an example.

[0063] It should be noted that this specification provides method operation steps as described in the embodiments or flow charts, but more or fewer operation steps may be included based on routine or non-creative work. The order of steps listed in the embodiments is only one way of executing the steps among many orders, and does not represent the only order of execution. When the actual system or product is executed, it can be executed in the order of the method shown in the embodiments or the drawings or in parallel (for example, in a parallel processor or multi-threaded processing environment). Specifically, Figure 2 As shown, the method may include:

[0064] S201, obtain the live voice of the anchor client in the voice live room, and obtain the live voice audio.

[0065] In the embodiment of the specification, when the host client starts the voice live broadcast, the start time of the host client in the corresponding voice live broadcast room can be obtained, and the live voice provided by the host client within the preset time is obtained with the start time as the starting point, so as to obtain the above-mentioned live voice audio. Among them, the preset time can be set as needed, for example, it can be set to 5 minutes, 10 minutes, etc.

[0066] S203, segmenting the live voice audio to obtain multiple voice audio segments.

[0067] In the embodiment of the present specification, a voice audio segment can be intercepted from the live voice audio obtained in step S201 at preset time intervals, thereby obtaining multiple voice audio segments. The preset time interval is less than the preset duration, and the preset time interval can be set according to actual needs. For example, when the preset duration is 5 minutes, the preset time interval can be 1 minute; when the preset duration is 10 minutes, the preset time interval can be 1 minute or 2 minutes, and so on.

[0068] S205, determining a comprehensive score of each of the multiple voice audio segments according to the popularity information and theme information of the voice live broadcast room.

[0069] The popularity information may include, but is not limited to, data used to characterize the influence and degree of interaction of the voice live broadcast room. For example, the popularity information may include, but is not limited to, the number of comments, the number of listeners, the number of gifts, etc.

[0070] In the embodiments of this specification, it is possible to use Figure 3 The method is implemented to determine the comprehensive score of each voice audio segment in the multiple voice audio segments according to the popularity information and theme information of the voice live broadcast room, such as Figure 3 As shown, the method may include:

[0071] S301, obtaining the historical popularity information of the voice live broadcast room and the popularity information of the voice live broadcast room corresponding to the broadcast start time.

[0072] Among them, the historical popularity information is the popularity information in previous broadcasts relative to the current broadcast. More specifically, the historical popularity information can be the popularity information in previous broadcasts corresponding to the above-mentioned preset duration, that is, the popularity information in previous broadcasts with each broadcast time as the starting point and within the above-mentioned preset duration.

[0073] In a specific implementation, the live voice data of the anchor client in the recent period (such as one month or three months, etc.) can be obtained. The live voice data can include, but is not limited to, the heat information of each live voice broadcast. The heat information of each live voice broadcast corresponds to a corresponding live broadcast time, which is the time relative to each broadcast start time. Then, the heat information within the above preset time length with each broadcast start time as the starting point is obtained from the heat information of each live voice broadcast, thereby obtaining the historical heat information.

[0074] Among them, the popularity information of the voice live broadcast room corresponding to the start time is the popularity information within the above-mentioned preset time length with the current start time as the starting point in this voice live broadcast.

[0075] S303: Determine a first score of each of the multiple voice audio segments according to the historical popularity information and the popularity information of the voice live broadcast room corresponding to the broadcast start time.

[0076] In the embodiments of this specification, each voice audio segment corresponds to a live broadcast start time and a live broadcast end time. According to the live broadcast start time and the live broadcast end time, the sub-historical heat information corresponding to the live broadcast time period can be obtained from the historical heat information, and the first heat information of the voice live broadcast room corresponding to the live broadcast time period in this broadcast can also be determined; the average value of all sub-historical heat information corresponding to the same live broadcast time period is calculated to obtain the historical average heat information in the corresponding live broadcast time period; then the first heat information is compared with the historical average heat information, and the first score of each of the voice audio segments is determined according to the comparison. In a specific implementation, when the first heat information exceeds the historical average heat information, a preset score can be added to the corresponding voice audio segment, for example, the preset score can be 1.

[0077] In the embodiments of this specification, the heat information may include heat data of multiple dimensions. When there is heat data of multiple dimensions, the sub-scores of each voice audio segment in each dimension may be determined first, and then the first score of each voice audio segment may be determined based on the sub-scores of each dimension. In a specific implementation, the sub-scores of each dimension may be directly added up to obtain the first score; the weights of the sub-scores of each dimension may also be determined first, and then the sub-scores of each voice audio segment in each dimension may be weighted and summed, wherein the weights of the sub-scores of each dimension may be set according to actual needs.

[0078] For example, popularity information may include the number of comments, the number of listeners, and the number of gifts. When determining the first score of each voice audio segment, the historical average number of comments corresponding to each voice audio segment can be obtained based on the historical number of comments in previous broadcasts, and the first number of comments corresponding to each voice audio segment can be obtained based on the number of comments in this broadcast. When the first number of comments exceeds the historical average number of comments, the corresponding voice audio segment is increased by 1 point; the historical average number of listeners corresponding to each voice audio segment can be obtained based on the historical number of listeners in previous broadcasts, and the first number of listeners corresponding to each voice audio segment can be obtained based on the number of listeners in this broadcast. When the first number of listeners exceeds the historical average number of listeners, the corresponding voice audio segment is increased by 1 point; the historical average number of gifts corresponding to each voice audio segment can be obtained based on the historical number of gifts in previous broadcasts, and the first number of gifts corresponding to each voice audio segment can be obtained based on the number of gifts in this broadcast. When the first number of gifts exceeds the historical average number of gifts, the corresponding voice audio segment is increased by 1 point. The final first score of the corresponding voice audio segment is 1+1+1=3.

[0079] It can be understood that the above example is only an example and does not constitute a limitation of the present invention. The popularity information may also include popularity data of other dimensions.

[0080] S305, determining the live broadcast theme of the voice live broadcast room and the semantics corresponding to each of the voice audio segments.

[0081] In the embodiment of the present specification, when the host client of the voice live broadcast room starts broadcasting, it can be prompted to enter the live broadcast theme of this voice live broadcast. Correspondingly, the live broadcast theme of the voice live broadcast room can be the live broadcast theme entered by the host client when starting the broadcast.

[0082] In the embodiments of the present specification, each of the speech audio segments is identified to determine the semantics corresponding to the speech audio segment. In a specific implementation, the speech audio segment can be firstly speech recognized to obtain the corresponding text, the text can be segmented to obtain a word set, and then the keyword library can be searched to determine the keywords in the word set. Among them, the keyword library is obtained by selecting and collecting a large number of relevant documents and audio materials in the corresponding technical field, analyzing the frequency of occurrence of words in the statistical data, and selecting words with a frequency of occurrence higher than a preset threshold as keywords according to the settings. Then, the semantics of the corresponding speech audio segment is determined based on the above keywords. Specifically, when determining the semantics of the corresponding speech audio segment based on keywords, it can be determined based on the hierarchical relationship between keywords, and specifically, the semantics can be determined based on the keyword with the highest hierarchy, wherein the hierarchical relationship between keywords can be determined by searching the hierarchical relationship library, and the hierarchical relationship library is a database established based on the above keyword library that can reflect the hierarchical relationship between keywords.

[0083] S307: Determine a second score for each of the voice audio segments according to the semantic similarity between the semantics corresponding to the voice audio segment and the semantics of the live broadcast topic.

[0084] Among them, semantic similarity is used to measure the similarity between the semantics corresponding to the voice audio segment and the live broadcast theme. The higher the similarity, the more the voice audio segment fits the current voice live broadcast, and it can be considered as the wonderful content or important content of this voice live broadcast; conversely, the lower the similarity, the more likely the voice audio segment is to deviate from the live broadcast theme.

[0085] In a specific implementation, the semantics corresponding to the speech audio segment and the live broadcast theme can be represented as vectors in space, and the semantic similarity between the two can be obtained by calculating the angle between the vectors. The angle between the vectors can be calculated by the cosine method. The Hamming distance can also be calculated to determine the semantic similarity between the two. The Hamming distance describes the distance between two codewords of length n, and its calculation formula is: Among them, x and y are both n-bit codes, It represents exclusive OR. d(x,y) represents the number of different symbols in codewords x and y, which reflects the difference between codewords x and y. The larger the d(x,y) value is, the lower the similarity between the two codewords is. Conversely, the smaller the d(x,y) value is, the higher the similarity between the two codewords is.

[0086] In the embodiments of the present specification, when the similarity reaches a preset similarity, a preset score can be assigned to the corresponding speech audio segment, and the preset score is greater than 0. When the similarity does not reach the preset similarity, the score of the corresponding speech audio segment can be determined to be 0. Taking the Hamming distance as an example to represent semantic similarity, when the Hamming distance d(x, y) is greater than the preset Hamming distance d'(x, y), it indicates that the similarity does not reach the preset similarity, and the second score of the corresponding speech audio segment is determined to be 0; when the Hamming distance d(x, y) is less than or equal to the preset Hamming distance d'(x, y), it indicates that the similarity reaches the preset similarity, and a preset score greater than 0 can be assigned to the corresponding speech audio segment, and the preset score is the second score. Among them, the preset score can be set according to actual needs, for example, it can be set to 2 or 5, etc.

[0087] In some embodiments, multiple preset semantic similarities can be set, and multiple similarity ranges can be obtained based on the multiple preset semantic similarities. Each similarity range can correspond to a different preset score. For example, according to the similarity from low to high, the preset scores corresponding to the similarity ranges are set to be 1, 2, 5, etc. Subsequently, it can be determined according to the actually calculated semantic similarity that the corresponding similarity falls into which similarity range, and the preset score corresponding to the similarity range it falls into is obtained, and the preset score is used as the second score of the corresponding speech audio segment.

[0088] S309: Determine a comprehensive score of the speech audio segment according to the first score and the second score.

[0089] In practical applications, the sum of the first score and the second score can be directly calculated, and the sum can be used as the comprehensive score of the corresponding voice audio segment. In specific implementations, different weights can be set for the first score and the second score, and the weights can be set according to actual needs. When calculating the sum of the two, the first score and the second score are weighted and summed based on the corresponding weights, and the result of the weighted sum is used as the comprehensive score of the corresponding voice audio.

[0090] In order to make the target voice audio segment selected later more suitable for the live broadcast theme of the voice live broadcast room, so as to improve the efficiency and accuracy of the user's selection of the voice live broadcast room, in one example, Figure 4 As shown, determining the comprehensive score of the speech audio segment according to the first score and the second score may include the following:

[0091] S401, extracting voiceprint feature information of each of the speech audio segments.

[0092] The voiceprint feature information may include, but is not limited to, speech rate, pitch, tone, and pause. In a specific implementation, the speech signal of the speech audio segment may be framed according to a fixed frame length and frame shift, and short-term voiceprint features may be extracted from each frame of the speech signal.

[0093] S403: Determine the emotional state of the speech audio segment according to the voiceprint feature information.

[0094] In actual applications, the speed of speech, the fundamental frequency, the pitch, and the number and duration of pauses can all reflect different emotional states.

[0095] In the embodiments of this specification, emotional state refers to the psychological state of emotion, which is persistent, explicit, situational and personalized. Generally, emotional state can be divided into mood, passion, enthusiasm and stress. Among them, mood is a weak and persistent emotional state, which is characterized by exaggeration and diffusion; passion is a strong and short-lived emotional state, which is characterized by impulsiveness, explosiveness and directionality; enthusiasm is a strong, stable, persistent and profound emotional state, which is not as widespread as the diffusion of mood, but is more powerful and profound than mood, not as fierce as passion, but more persistent and stable than passion; stress is a highly tense emotional state that occurs in unexpected emergency situations, and often has two extreme manifestations, one is panic and dumbfounded, and the other is quick thinking and sudden increase in strength.

[0096] In a specific implementation, the voiceprint feature information corresponding to each speech audio segment can be input into the emotion analysis model for emotion state analysis processing, so as to obtain the corresponding emotion state output by the emotion analysis model. The emotion analysis model is a machine learning model obtained by machine learning based on the voiceprint feature information of the sample speech audio and the corresponding emotion state label, and the machine learning model can include but is not limited to a deep convolutional neural network.

[0097] Machine Learning (ML) is a multi-disciplinary subject that involves probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all areas of artificial intelligence. Machine learning and deep learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and self-learning.

[0098] S405: Determine a third score of the voice audio segment according to a match between the emotional state and the live broadcast theme.

[0099] In actual applications, a mapping relationship between the live broadcast theme and the emotional state can be established. After the emotional state of the voice audio segment is obtained, the target mapping relationship corresponding to the live broadcast theme of this voice live broadcast can be obtained, and then the target emotional state in the target mapping relationship is obtained to determine whether the target emotional state contains the emotional state of the currently determined voice audio segment. When the result of the judgment is that the target emotional state contains the emotional state of the currently determined voice audio segment, a preset score is assigned to the corresponding voice audio segment. The preset score is greater than 0, and the specific score can be set according to actual needs, for example, it can be set to 2 or 5; when the result of the judgment is that the target emotional state does not contain the emotional state of the currently determined voice audio segment, the third score of the corresponding voice audio segment is determined to be 0.

[0100] S407: Determine a comprehensive score of the speech audio segment according to the first score, the second score, and the third score.

[0101] Specifically, the sum of the first score, the second score and the third score can be directly calculated, and the sum can be used as the comprehensive score of the corresponding voice audio segment. In a specific implementation, different weights can be set for the first score, the second score and the third score, and the weights can be set according to actual needs. When calculating the sum of the above three, the first score, the second score and the third score can be weighted and summed based on the corresponding weights, and the result of the weighted sum can be used as the comprehensive score of the corresponding voice audio segment.

[0102] S207: Select a target speech audio segment from the multiple speech audio segments according to the comprehensive score.

[0103] Specifically, the multiple voice audio segments may be sorted from large to small according to the comprehensive scores, and the voice audio segment ranked first may be used as the target voice audio segment.

[0104] S209, displaying the playback entrance of the target voice audio segment at the live broadcast entrance of the voice live broadcast room.

[0105] Specifically, the playback entrance corresponding to the target voice audio segment is displayed at the live broadcast entrance of the voice live room. The user can listen to the voice content of the target voice audio segment by clicking the playback entrance, thereby quickly determining whether the voice live room is the voice live room they expect. When the voice live room is not the voice live room they expect, they can directly click on the playback entrance of the target voice audio segment at the live broadcast entrance of the next voice live room, avoiding the need to first enter the voice live room to listen to the real-time live content, effectively improving the efficiency of users screening the expected voice live room.

[0106] like Figure 5 A schematic diagram of displaying the playback entrance of a target voice audio segment at the live broadcast entrance of a voice live broadcast room is provided. The voice bar (i.e., the playback entrance) of the target voice audio segment is displayed at the live broadcast entrance of the corresponding voice live broadcast room. The duration of the corresponding target voice audio segment can also be displayed at the voice bar. The user can listen to the corresponding audio by clicking on the voice bar. When the user switches voice bars, clicking on the next voice bar can stop the playback of the previous voice bar and directly start the playback of the next voice bar.

[0107] In the prior art, when a user enters a voice live broadcast room and listens to the real-time voice broadcast to determine whether the voice live broadcast room is the desired voice live broadcast room, it is possible that the host of the voice live broadcast room is not speaking or is not at the main content moment, causing the user to leave the voice live broadcast, which reduces the user experience and the accuracy of the user's selection of the voice live broadcast room.

[0108] The embodiment of the present invention combines the popularity information corresponding to each voice audio segment and the theme information of the live broadcast when determining the comprehensive scores of multiple voice audio segments, so that the most exciting and most suitable voice audio segments can be selected to be presented to the user for audition, thereby improving the user experience and the accuracy of selecting the voice live broadcast room. In addition, for the anchor client, the content of the voice audio that the user auditions is controllable, and there will be no problem of no speech or non-main content, which improves the sense of security, and can better show the characteristics of the anchor and better attract the attention of users.

[0109] In practical applications, in order to avoid the presence of illegal content in the selected target voice audio segment, such as obscene words, prohibited words, etc., the display of the playback entrance of the target voice audio segment at the live broadcast entrance of the voice live broadcast room may include: Figure 6 The steps in the embodiment may include:

[0110] S601, determining whether the target speech audio segment meets the violation requirement.

[0111] Among them, violation requirements refer to the inclusion of illegal content, which may include but is not limited to obscene words, banned words, etc.

[0112] When there is illegal content in the target voice audio segment, the target voice audio segment meets the violation requirements, and step S603 can be executed; when there is no illegal content in the target voice audio segment, the target voice audio segment does not meet the violation requirements, and the playback entrance of the target voice audio segment can be directly displayed at the live broadcast entrance of the voice live broadcast room.

[0113] S603: Delete the target speech audio segment from the multiple speech audio segments.

[0114] S605, reselecting a target voice audio segment from the deleted multiple voice audio segments according to the comprehensive score, and executing step S601 until the reselected target voice audio segment does not meet the violation requirement.

[0115] In an embodiment of the present specification, a speech audio segment with the second highest comprehensive score can be selected from the multiple speech audio segments after deletion, and the speech audio segment with the second highest comprehensive score can be used as the target speech audio segment, and step S601 is continued to be executed to determine whether the target speech audio segment meets the violation requirements until the re-selected target speech audio segment does not meet the violation requirements.

[0116] S607, displaying the playback entrance of the re-selected target voice audio segment at the live broadcast entrance of the voice live broadcast room.

[0117] In actual applications, in order to allow the anchor client to better control the voice content processed by the live broadcast entrance of the voice live broadcast room, such as Figure 7 As shown, before displaying the playback entrance of the target voice audio segment at the live broadcast entrance of the voice live broadcast room in step S209, the method may further include:

[0118] S211, feeding back the target voice audio segment to the anchor;

[0119] S213, determining whether a signal is received from the host agreeing to display the playback entrance of the target voice audio segment at the live broadcast entrance of the voice live broadcast room, and when the result of the determination is yes, executing step S209.

[0120] Specifically, Figure 8 As shown, the anchor client can feed back the playback entrance of the target voice audio segment to the anchor in the form of a pop-up window, and at the same time give a prompt message on the pop-up window whether to agree to display the playback entrance of the target voice audio segment in the live broadcast entrance of its voice live broadcast room and give consent (such as Figure 8 "Confirm" option in the Figure 8 In this way, the anchor can determine whether to agree. When the anchor selects the agree option (such as clicking to confirm), the anchor client receives the agreement signal and can execute step S209 to display the playback entrance of the target voice audio segment at the live broadcast entrance of its voice live broadcast room; when the anchor selects the disagree option (such as clicking to cancel), the anchor client receives the disagreement signal and gives up displaying the playback entrance of the voice audio segment at the live broadcast entrance of its voice live broadcast room, and the method ends.

[0121] It can be seen from the above technical scheme of the embodiment of the present invention that the embodiment of the present invention performs segmentation processing on the live voice audio of the anchor client of the voice live room, and determines the comprehensive scores of multiple voice audio segments obtained by segmentation processing based on the popularity information and theme information of the voice live room, determines the target voice audio segment among the multiple voice audio segments according to the comprehensive score, and displays the playback entrance of the target voice audio segment at the live broadcast entrance of the voice live room, so that when the user browses the voice live platform, the user can quickly find the desired voice live room by auditioning the voice audio segments displayed at the live broadcast entrances of each voice live room, thereby improving the efficiency of users in screening voice live rooms and improving the user experience effect;

[0122] In addition, the target voice audio segment determined based on the popularity information and theme information of the voice live broadcast room can better display the characteristics of the anchor, better attract the user's attention, and also help the anchor to control the voice content displayed at the live broadcast entrance.

[0123] Corresponding to the live broadcast entrance display methods for the voice live broadcast room provided in the above-mentioned embodiments, an embodiment of the present invention further provides a live broadcast entrance display device for the voice live broadcast room. Since the live broadcast entrance display device for the voice live broadcast room provided in the embodiment of the present invention corresponds to the live broadcast entrance display methods for the voice live broadcast room provided in the above-mentioned embodiments, the implementation methods of the live broadcast entrance display methods for the voice live broadcast room are also applicable to the live broadcast entrance display device for the voice live broadcast room provided in this embodiment, and will not be described in detail in this embodiment.

[0124] See also Fig. 9 , which is a schematic diagram of the structure of a live broadcast entrance display device for a voice live broadcast room provided by an embodiment of the present invention, the device has the function of implementing the live broadcast entrance display method for the voice live broadcast room in the above method embodiment, and the function can be implemented by hardware, or by hardware executing corresponding software. Fig. 9 As shown, the device may include:

[0125] The first acquisition module 910 is used to acquire the live voice of the anchor client in the voice live broadcast room and obtain the live voice audio;

[0126] A segment processing module 920 is used to segment the live voice audio to obtain multiple voice audio segments;

[0127] A first determination module 930 is used to determine a comprehensive score of each of the multiple voice audio segments according to the popularity information and theme information of the voice live broadcast room;

[0128] A selection module 940, configured to select a target speech audio segment from the plurality of speech audio segments according to the comprehensive score;

[0129] The display module 950 is used to display the playback entrance of the target voice audio segment at the live broadcast entrance of the voice live broadcast room.

[0130] In a specific embodiment, the first acquisition module 910 may include:

[0131] The second acquisition module is used to obtain the start time of the anchor client in the voice live broadcast room;

[0132] The third acquisition module is used to obtain the live broadcast voice provided by the anchor client within a preset time period, taking the broadcast start time as the starting point.

[0133] Optionally, the segmentation processing module 920 is specifically used to: extract voice audio segments from the live voice audio at preset time intervals to obtain multiple voice audio segments.

[0134] In a specific embodiment, the first determining module 930 may include:

[0135] The fourth acquisition module is used to obtain the historical popularity information of the voice live broadcast room and the popularity information of the voice live broadcast room corresponding to the broadcast start time;

[0136] A second determination module is used to determine a first score of each of the multiple voice audio segments according to the historical popularity information and the popularity information of the voice live broadcast room corresponding to the start time;

[0137] A third determination module is used to determine the live broadcast theme of the voice live broadcast room and the semantics corresponding to each of the voice audio segments;

[0138] A fourth determination module, used to determine a second score of each of the voice audio segments according to the semantic similarity between the semantics corresponding to the voice audio segment and the semantics of the live broadcast theme;

[0139] The fifth determination module is used to determine the comprehensive score of the speech audio segment according to the first score and the second score.

[0140] In a specific embodiment, the second determining module may include:

[0141] A sixth determination module, configured to determine, according to the broadcast start time, first popularity information of the voice live broadcast room corresponding to each voice audio segment in the plurality of voice audio segments;

[0142] A seventh determination module, configured to determine, based on the historical heat information, the historical average heat information within the live broadcast time period corresponding to each of the voice audio segments;

[0143] The eighth determination module is used to determine the first score of each of the voice audio segments based on the comparison between the first heat information and the historical average heat information.

[0144] In a specific embodiment, the fifth determining module may include:

[0145] An extraction module, used to extract voiceprint feature information of each of the speech audio segments;

[0146] a ninth determination module, configured to determine the emotional state of the speech audio segment according to the voiceprint feature information;

[0147] a tenth determination module, configured to determine a third score of the voice audio segment according to a matching condition between the emotional state and the live broadcast theme;

[0148] An eleventh determination module is used to determine a comprehensive score of the speech audio segment according to the first score, the second score and the third score.

[0149] In a specific embodiment, the display module 950 may include:

[0150] A judgment module, used to judge whether the semantics corresponding to the target speech audio segment meets the violation requirements;

[0151] a deleting module, configured to delete the target voice audio segment from the multiple voice audio segments when the judgment result of the judging module is yes;

[0152] A reselection module, used for reselecting a target voice audio segment from the deleted multiple voice audio segments according to the comprehensive score, and executing the judging step until the semantics corresponding to the reselected target voice audio segment does not meet the violation requirement;

[0153] The display submodule is used to display the playback entrance of the re-selected target voice audio segment at the live broadcast entrance of the voice live broadcast room.

[0154] It should be noted that the device provided in the above embodiment, when implementing its functions, is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, 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 device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0155] The live broadcast entrance display device of the voice live broadcast room of the embodiment of the present invention performs segmentation processing on the live voice audio of the anchor client of the voice live broadcast room, and determines the comprehensive score of multiple voice audio segments obtained by the segmentation processing based on the popularity information and theme information of the voice live broadcast room, determines the target voice audio segment among the multiple voice audio segments according to the comprehensive score, and displays the playback entrance of the target voice audio segment at the live broadcast entrance of the voice live broadcast room. Therefore, when the user browses the voice live broadcast platform, the user can quickly find the desired voice live broadcast room by auditioning the voice audio segments displayed at the live broadcast entrances of each voice live broadcast room, thereby improving the efficiency of the user in screening the voice live broadcast room and improving the user experience effect.

[0156] An embodiment of the present invention provides a computer device, which includes a processor and a memory, in which at least one instruction, at least one program, a code set or an instruction set is stored. The at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the live broadcast entrance display method of the voice live broadcast room provided in the above-mentioned method embodiment.

[0157] The memory can be used to store software programs and modules. The processor executes various functional applications and the live broadcast entrance display of the voice live broadcast room by running the software programs and modules stored in the memory. The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, application programs required for functions, etc.; the data storage area may store data created according to the use of the device, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide the processor with access to the memory.

[0158] The method embodiments provided in the embodiments of the present invention may be executed in a computer terminal, a server or a similar computing device, that is, the above-mentioned computer device may include a computer terminal, a server or a similar computing device. Fig.10 is a hardware structure block diagram of a computer device for running a live broadcast entrance display method for a voice live broadcast room provided by an embodiment of the present invention, such as Fig.10 As shown, the internal structure of the computer device may include but is not limited to: a processor, a network interface and a memory. The processor, network interface and memory in the computer device may be connected via a bus or other means. Fig.10 The example of connecting through bus is taken in the following.

[0159] Among them, the processor (or CPU (Central Processing Unit)) is the computing core and control core of the computer device. The network interface may optionally include a standard wired interface, a wireless interface (such as WI-FI, a mobile communication interface, etc.). The memory is a memory device in a computer device for storing programs and data. It is understandable that the memory here can be a high-speed RAM storage device or a non-volatile memory device (non-volatile memory), such as at least one disk storage device; optionally, it can also be at least one storage device located away from the aforementioned processor. The memory provides a storage space, which stores the operating system of the electronic device, which may include but is not limited to: Windows system (an operating system), Linux (an operating system), Android (Android, a mobile operating system) system, IOS (a mobile operating system) system, etc., and the present invention is not limited to this; and, in the storage space, one or more instructions suitable for being loaded and executed by the processor are also stored, and these instructions may be one or more computer programs (including program codes). In the embodiment of this specification, the processor loads and executes one or more instructions stored in the memory to implement the live broadcast entrance display method of the voice live broadcast room provided in the above method embodiment.

[0160] An embodiment of the present invention also provides a computer-readable storage medium, which can be set in a computer device to store at least one instruction, at least one program, code set or instruction set related to the method for displaying the live broadcast entrance of a voice live broadcast room. The at least one instruction, the at least one program, the code set or instruction set is loaded and executed by the processor to implement the method for displaying the live broadcast entrance of a voice live broadcast room provided in the above-mentioned method embodiment.

[0161] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0162] It should be noted that the sequence of the embodiments of the present invention described above is for description only and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0163] Each embodiment in this specification is described in a progressive 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. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0164] A person skilled in the art will appreciate that all or part of the steps for implementing the above embodiments may be accomplished by hardware or by hardware associated with program instructions, and the program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk, or an optical disk, etc.

[0165] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for displaying a live broadcast entrance of a voice live broadcast room, characterized in that: The method comprises: Get the live voice of the anchor client in the voice live room and get the live voice audio; Segmenting the live voice audio to obtain multiple voice audio segments; Determine the first score of each voice audio segment according to the comparison between the historical average heat information of each voice audio segment in its corresponding live broadcast time period and the first heat information; the historical average heat information is the average value of each sub-historical heat information corresponding to the live broadcast time period in the historical heat information of previous broadcasts, and the first heat information is the heat information corresponding to the live broadcast time period in the heat information of this broadcast; Determine the live broadcast theme of the voice live broadcast room and the semantics corresponding to each of the voice audio segments; determine the second score of each of the voice audio segments according to the semantic similarity between the semantics corresponding to each of the voice audio segments and the semantics of the live broadcast theme; determine the comprehensive score of each of the voice audio segments according to the first score and the second score of each of the voice audio segments; Selecting a target voice audio segment from the multiple voice audio segments according to the comprehensive scores; the target voice audio segment is a voice audio segment with the largest comprehensive score among the multiple voice audio segments; The playback entrance of the target voice audio segment is displayed at the live broadcast entrance of the voice live broadcast room.

2. The method for displaying the live broadcast entrance of the voice live broadcast room according to claim 1, characterized in that: The method of obtaining the live voice of the anchor client in the voice live broadcast room includes: Get the start time of the host client in the voice live broadcast room; Taking the broadcast start time as the starting point, the live broadcast voice provided by the anchor client within a preset time length is obtained.

3. The method for displaying the live broadcast entrance of the voice live broadcast room according to claim 2, characterized in that: The segmenting of the live voice audio to obtain a plurality of voice audio segments comprises: A voice audio segment is intercepted from the live voice audio at every preset time interval to obtain a plurality of voice audio segments.

4. The method for displaying the live broadcast entrance of the voice live broadcast room according to claim 1, characterized in that: Determining the first score of each of the voice audio segments according to a comparison between the historical average heat information of each of the voice audio segments in its corresponding live broadcast time period and the first heat information includes: For each of the voice audio segments, if the first heat information of the voice audio segment in its corresponding live broadcast time period exceeds the historical average heat information in the live broadcast time period, a preset score is added to the voice audio segment to obtain a first score.

5. The method for displaying the live broadcast entrance of the voice live broadcast room according to claim 1, characterized in that: Determining the comprehensive score of each of the speech audio segments according to the first score and the second score of each of the speech audio segments comprises: Extracting voiceprint feature information of each of the speech audio segments; Determining the emotional state of the speech audio segment according to the voiceprint feature information; Determining a third score of the voice audio segment according to a match between the emotional state and the live broadcast theme; A comprehensive score of the speech audio segment is determined based on the first score, the second score and the third score.

6. The method for displaying the live broadcast entrance of the voice live broadcast room according to claim 1, characterized in that: The step of displaying the playback entrance of the target voice audio segment at the live broadcast entrance of the voice live broadcast room comprises: Determining whether the target voice audio segment meets the violation requirement; When the result of the judgment is yes, deleting the target voice audio segment from the multiple voice audio segments; Reselecting a target voice audio segment from the deleted multiple voice audio segments according to the comprehensive score, and performing the judging step until the reselected target voice audio segment does not meet the violation requirement; The playback entrance of the reselected target voice audio segment is displayed at the live broadcast entrance of the voice live broadcast room.

7. A live broadcast entrance display device for a voice live broadcast room, characterized in that: The device comprises: The first acquisition module is used to acquire the live voice of the anchor client in the voice live broadcast room and obtain the live voice audio; A segmentation processing module, used for segmenting the live voice audio to obtain multiple voice audio segments; A first determination module is used to determine the first score of each of the voice audio segments according to the comparison between the historical average heat information of each of the voice audio segments in the corresponding live broadcast time period and the first heat information; the historical average heat information is the average value of each sub-historical heat information corresponding to the live broadcast time period in the historical heat information of previous broadcasts, and the first heat information is the heat information corresponding to the live broadcast time period in the heat information of this broadcast; determine the live broadcast theme of the voice live broadcast room, and the semantics corresponding to each of the voice audio segments; determine the second score of each of the voice audio segments according to the semantic similarity between the semantics corresponding to each of the voice audio segments and the semantics of the live broadcast theme; determine the comprehensive score of each of the voice audio segments according to the first score and the second score of each of the voice audio segments; A selection module, configured to select a target voice audio segment from the multiple voice audio segments according to the comprehensive score; the target voice audio segment is a voice audio segment with the largest comprehensive score among the multiple voice audio segments; The display module is used to display the playback entrance of the target voice audio segment at the live broadcast entrance of the voice live broadcast room.

8. A computer device, characterized in that: It includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set are loaded and executed by the processor to implement the live broadcast entrance display method of the voice live broadcast room as described in any one of claims 1 to 6.

9. A computer-readable storage medium, wherein at least one instruction, at least one program, a code set or an instruction set is stored in the storage medium, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement the live broadcast entrance display method of the voice live broadcast room as described in any one of claims 1 to 6.

Images