Direct broadcasting room processing method and device

Abstract

The embodiment of the invention provides a live broadcast room processing method and device, computer equipment, a computer readable storage medium and a computer program product, and relates to the technical field of live broadcast. The method comprises the following steps: acquiring live broadcast room data of a plurality of live broadcast rooms, and determining an index trend of the corresponding live broadcast room based on the live broadcast room data; determining a first live broadcast room in the plurality of live broadcast rooms according to the index trend of each live broadcast room; obtaining interaction information for the first live broadcasting rooms, and determining a second live broadcasting room and a third live broadcasting room in the plurality of first live broadcasting rooms based on the interaction information; wherein the abnormal probability of the second live broadcast room is greater than that of the third live broadcast room. Through multiple times of screening of the live broadcast rooms, the efficiency and accuracy of processing the abnormal live broadcast rooms are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of live broadcast technology, and in particular to a live broadcast room processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] In live streaming scenarios, live streaming platforms need to monitor content to identify and address anomalous live streaming rooms. However, a platform often has a large number of live streaming rooms simultaneously active. Manual review is inefficient and limited in scope, making it difficult to effectively and promptly address anomalous live streaming rooms.

[0003] It should be noted that the above content is not necessarily prior art, nor is it intended to limit the scope of patent protection of this application. Summary of the Invention

[0004] The embodiments of the present application provide a live broadcast room processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product to solve or alleviate one or more technical problems raised above.

[0005] One aspect of an embodiment of the present application provides a live broadcast room processing method, the method comprising: Acquire live broadcast room data of multiple live broadcast rooms, and determine indicator trends of corresponding live broadcast rooms based on the live broadcast room data; Determine a first live broadcast room from the plurality of live broadcast rooms according to an indicator trend of each live broadcast room; Obtain interaction information for the first live broadcast room, and determine a second live broadcast room and a third live broadcast room from the multiple first live broadcast rooms based on the interaction information; wherein the abnormality probability of the second live broadcast room is greater than that of the third live broadcast room.

[0006] Optionally, obtaining live broadcast room data of multiple live broadcast rooms, and determining an indicator trend of a corresponding live broadcast room based on the live broadcast room data, includes: For each live broadcast room, obtaining live broadcast room data of the live broadcast room at the current moment and the previous moment every first preset time period, wherein the live broadcast room data includes an indicator value of the live broadcast room under a preset indicator; Based on the indicator value at the current moment and the indicator value at the previous moment, determine the indicator trend of the live broadcast room.

[0007] Optionally, determining a first live broadcast room from the multiple live broadcast rooms according to an indicator trend of each live broadcast room includes: Acquire historical supervision information, where the historical supervision information includes a target live broadcast room, where the target live broadcast room includes a live broadcast room determined as the second live broadcast room within a second preset time period; Determine whether the indicator trend of each live broadcast room shows a deterioration trend, and determine the live broadcast room showing a deterioration trend as a candidate live broadcast room; Eliminate the target live broadcast room from the candidate live broadcast rooms to obtain the first live broadcast room.

[0008] Optionally, the interaction information includes first interaction information from a first object, where the first object includes viewers in the first live broadcast room. Correspondingly, obtaining the interaction information for the first live broadcast room includes: Sending a broadcast message to a viewer terminal, the viewer terminal being configured to: receive the broadcast message; display a first interactive panel for the first live broadcast room in the first live broadcast room based on the broadcast message; generating first interactive information for the first live broadcast room in response to an interactive operation of a first object on the first interactive panel, and sending the first interactive information to the server; Obtain the first interactive information for the first live broadcast room provided by the audience terminal.

[0009] Optionally, the interactive information includes second interactive information from a second object, where the second object includes a viewer with monitoring qualifications; correspondingly, obtaining the interactive information for the first live broadcast room includes: In response to a review request from a monitoring platform, the live broadcast room data of the first live broadcast room is sent to the monitoring platform, and the monitoring platform is configured to: display the live broadcast room data of the first live broadcast room; in response to a review operation of the first live broadcast room by a second subject, generate second interaction information for the first live broadcast room, and send the second interaction information to the server; Obtain second interactive information for the first live broadcast room provided by the monitoring platform.

[0010] Optionally, the first interaction information includes multiple copies, each copy of the first interaction information corresponds to a first object; correspondingly, the method further includes: Reporting the live broadcast room data of the second live broadcast room to the review platform, wherein the review platform is configured to determine an abnormal live broadcast room to be processed from the second live broadcast room based on the live broadcast room data; Determining a matching degree between each piece of first interactive information and the abnormal live broadcast room; A first object corresponding to the first interactive information having a matching degree higher than a first preset threshold is obtained, and the monitoring qualification is configured for the first object to convert the first object into the second object.

[0011] Optionally, the second interaction information includes multiple copies, each copy of the second interaction information corresponds to a second object; the method further includes: Determining a matching degree between each piece of second interactive information and the abnormal live broadcast room; A second object corresponding to the second interactive information whose matching degree is lower than a second preset threshold is obtained, and the monitoring qualification of the second object is cancelled.

[0012] Another aspect of an embodiment of the present application provides a live broadcast room processing device, the device comprising: An acquisition module, configured to acquire live broadcast room data of a plurality of live broadcast rooms, and determine an indicator trend of a corresponding live broadcast room based on the live broadcast room data; A determination module, configured to determine a first live broadcast room among the multiple live broadcast rooms based on an indicator trend of each live broadcast room; The acquisition module is also used to obtain interactive information for the first live broadcast room, and determine the second live broadcast room and the third live broadcast room among the multiple first live broadcast rooms based on the interactive information; wherein the abnormal probability of the second live broadcast room is greater than that of the third live broadcast room.

[0013] Another aspect of an embodiment of the present application provides a computer device, including: at least one processor; and a memory communicatively coupled to the at least one processor; Wherein: the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described above.

[0014] Another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method described above is implemented.

[0015] Another aspect of an embodiment of the present application provides a computer program product, including a computer program, which implements the above-mentioned method when executed by a processor.

[0016] The above technical solution adopted in the embodiments of the present application may have the following advantages: By identifying indicator trends from livestream data, we can filter out potentially abnormal livestreams from a large number of them. By then acquiring interactive information specific to the first livestream, we can further differentiate it into a third livestream with a lower risk of abnormality and a second livestream with a higher risk of abnormality. By performing multiple screenings within livestreams, we can reduce the number of livestreams ultimately submitted to the review platform, thereby expanding the scope of livestream processing and improving the efficiency and accuracy of handling abnormal livestreams. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings illustrate exemplary embodiments and constitute a part of the specification. Together with the description of the specification, they serve to explain exemplary implementation of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. Throughout the drawings, the same reference numerals designate similar, but not necessarily identical, elements.

[0018] Figure 1 The following diagram schematically shows an operating environment diagram of the live broadcast room processing method according to the first embodiment of the present application; Figure 2 The following schematically shows a flow chart of a live broadcast room processing method according to the first embodiment of the present application; Figure 3 The following schematically shows a flow chart of sub-steps of step S200 according to the first embodiment of the present application; Figure 4 Schematically shows another sub-step flow chart of step S202 in the first embodiment of the present application; Figure 5 The following schematically shows a flow chart of sub-steps of step S204 according to the first embodiment of the present application; Figure 6 Schematically shows another sub-step flow chart of step S204 in the first embodiment of the present application; Figure 7 The following schematically shows a newly added flow chart of the live broadcast room processing method according to the first embodiment of the present application; Figure 8 Another newly added flow chart of the live broadcast room processing method according to the first embodiment of the present application is schematically shown; Figure 9 A diagram schematically illustrates an application example of the live broadcast room processing method according to the first embodiment of the present application; Figure 10 A block diagram of a live broadcast room processing device according to the second embodiment of the present application is schematically shown; and Figure 11 The following schematically shows a hardware architecture diagram of a computer device according to the third embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of this application more clear, the present application is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0020] It should be noted that the descriptions of "first", "second", etc. in the embodiments of the present application are for descriptive purposes only and should not be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but this must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0021] In the description of this application, it should be understood that the numerical labels before the steps do not indicate the order in which the steps are executed. They are only used to facilitate the description of this application and to distinguish each step. Therefore, they cannot be understood as limitations on this application.

[0022] First, an explanation of the terms used in this application is provided: Ecological inspection: refers to the live broadcast platform's use of professional reviewers to conduct real-time inspections and interventions on the content of the live broadcast room, and to promptly discover and deal with live broadcast rooms that violate platform regulations or affect the healthy atmosphere of the community, thereby ensuring the compliance of the platform's live broadcast content and the overall ecological health.

[0023] High-hot live broadcast room: refers to the top live broadcast room with high exposure and traffic weight on the live broadcast platform, which usually includes popular anchors, event live broadcasts or live broadcast rooms with high interaction frequency.

[0024] Special governance refers to a centralized rectification action initiated by the live broadcast platform around common problems in a certain type of live broadcast room (such as hanging broadcasts, inducing rewards, misleading information, etc.).

[0025] Potentially abnormal live streaming rooms: These rooms are screened based on negative indicators (such as high instant exit rates, concentrated user reports, and abnormal interaction data). These rooms are not directly identified as abnormal, but have high content risk or low quality risk.

[0026] Live broadcast rooms with high probability of ecological abnormalities: Based on the potential live broadcast rooms with ecological abnormalities, combined with the first interactive information (such as questionnaire feedback), supervision and review and other means for further confirmation, the live broadcast rooms that are more likely to have ecological problems are screened out.

[0027] Second exit rate: refers to the proportion of users who exit the live broadcast room within a very short time after entering the live broadcast room.

[0028] Secondly, to facilitate those skilled in the art to understand the technical solutions provided in the embodiments of the present application, the following describes the relevant technologies: When live streamers broadcast live in their studios, the platform primarily conducts content inspections through manual review, penalizing and restricting those deemed abnormal. However, due to limited reviewer manpower, these inspections prioritize only high-profile studios, making effective oversight difficult. Furthermore, since top studios are less likely to be abnormal, reviewers are also less likely to identify them, resulting in a certain waste of manpower. Alternatively, for less popular studios, targeted inspections can be implemented. For example, when the problem of "hanging broadcasts" is rampant, a machine-based review model and human review can be used to address the issue. However, this approach relies on manual pre-emptive problem detection. Specifically, targeted rectification can only be initiated after a specific issue (such as "hanging broadcasts") has occurred frequently and has been manually identified. This leads to a certain lag and low inspection efficiency.

[0029] To this end, an embodiment of the present application provides a technical solution for processing live broadcast rooms. In this technical solution, a group of potential ecologically abnormal live broadcast rooms are screened out in real time based on data such as the instant exit rate and exposure change trend of the current live broadcast room. Based on the screened potential ecologically abnormal live broadcast rooms, high-probability ecologically abnormal live broadcast rooms are screened out through the real-time form of issuing live broadcast room questionnaires and the non-real-time form of audience monitoring. Combined with the above double-layer screening, the number of live broadcast rooms to be reviewed is greatly reduced, allowing ecological inspections to cover the entire live broadcast market. By covering the live broadcast market, new ecological problems can be further captured in advance to carry out targeted special governance. See below for details.

[0030] Finally, for ease of understanding, an exemplary operating environment is provided below.

[0031] like Figure 1 As shown, the operating environment diagram includes: Host 2, audience terminals (4A, 4B...4N), and server 6. Host 2 can push live broadcast data to audience terminals (4A, 4B...4N) through server 6.

[0032] The host terminal 2 can be used to generate live broadcast data in real time and perform live broadcast data push operations. The live broadcast data can include audio data or video data. The host terminal can be an electronic device such as a smartphone or tablet computer.

[0033] The server 6 can be a single server, a server cluster or a cloud computing service center, used to provide various services. For example: The server 6 can provide content services. The content services can be configured to provide content such as video, audio, text data, and combinations thereof. The content can include content streams (e.g., video streams, audio streams, information streams), content files (e.g., video files, audio files, text files), and / or other data.

[0034] The server 6 can be configured to manage messages for various content. Users can browse and access different content to view comments related to a particular content, such as comments posted by other users. Comments from users associated with a particular content can be displayed to other users viewing the content. For example, all users accessing a content (e.g., a video) can view comments associated with the content. Input comments can be displayed in real time or near real time.

[0035] The server 6 can be configured to process multiple messages. For example, various processing operations such as message storage, message filtering, and message push can be performed. Message storage is used to store multiple messages in a data storage system such as a database. Message filtering can include rejecting or marking messages that match filtering criteria. The filtering criteria can specify terms and / or phrases, such as profanity, hate speech, and indecent language. The filtering criteria can also specify characters, such as symbols and fonts. The filtering criteria can also specify languages, computer-readable codes, and the like.

[0036] The server 6 may perform natural language processing, topic identification, pattern recognition, artificial intelligence, etc. to automatically determine characteristics of messages and / or group messages. As an example, frequently occurring phrases or patterns may be identified as topics. As another example, a database of topics associated with content may be maintained. Topics may include genres (e.g., action, drama, comedy), personalities (e.g., actors, actresses, directors), languages, etc. Messages may be further grouped based on characteristics of the client device and / or the user sending the message.

[0037] The viewer terminals (4A, 4B...4N) can be configured to receive live broadcast data from the host terminal 2 in real time. The viewer terminals (4A, 4B...4N) can be any type of computer device, such as a smartphone, tablet device, laptop computer, smart TV, in-vehicle terminal, etc. The viewer terminals (4A, 4B...4N) can have built-in browsers, specialized programs, or players connected via a network. The network can include various network devices, such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, and / or proxy devices. The network can include physical links, such as coaxial cable links, twisted pair cable links, fiber optic links, combinations thereof, and / or the like. The network can also include wireless links, such as cellular links, satellite links, Wi-Fi links, and / or the like.

[0038] It should be noted that the number of host terminals 2, viewer terminals (4A, 4B, ..., 4N), and server terminals 6 in the figure is for illustration only and is not intended to limit the scope of patent protection of this application. Any number of host terminals, viewer terminals, and server terminals may be used depending on the actual situation.

[0039] The following describes the technical solution of the present application through multiple embodiments, taking the server 6 as the execution subject. It should be noted that these embodiments can be implemented in many different forms and should not be construed as being limited to the embodiments described here.

[0040] Example 1 Figure 2 The flowchart of the live broadcast room processing method according to the first embodiment of the present application is schematically shown.

[0041] like Figure 2 As shown, the live broadcast room processing method is used on the server 6, and may specifically include steps S200 to S204, wherein: Step S200: Acquire live broadcast room data of multiple live broadcast rooms, and determine the indicator trend of the corresponding live broadcast room based on the live broadcast room data.

[0042] Step S202: Determine a first live broadcast room among the multiple live broadcast rooms based on the indicator trend of each live broadcast room.

[0043] Step S204: Obtain interaction information for the first live broadcast room, and determine a second live broadcast room and a third live broadcast room from the multiple first live broadcast rooms based on the interaction information; wherein the abnormality probability of the second live broadcast room is greater than that of the third live broadcast room.

[0044] The live broadcast room processing method provided in this embodiment uses live broadcast room data to determine indicator trends, thereby screening out a first live broadcast room that may be abnormal from a large number of live broadcast rooms. By obtaining interactive information about the first live broadcast room, the first live broadcast room can be further divided into a third live broadcast room with a lower abnormality risk and a second live broadcast room with a higher abnormality risk. This multiple screening of live broadcast rooms can reduce the number of live broadcast rooms ultimately submitted to the review platform, thereby expanding the coverage of live broadcast room processing and improving the efficiency and accuracy of handling abnormal live broadcast rooms.

[0045] The following combination Figure 2 , each step in steps S200~S204 and other optional steps are described in detail.

[0046] Step S200 , obtain live broadcast room data of multiple live broadcast rooms, and determine the indicator trend of the corresponding live broadcast room based on the live broadcast room data.

[0047] Live broadcast room data can include multi-dimensional indicator data (such as entry rate, reporting information, stay time, instant exit rate, interaction frequency), live broadcast content data (such as live broadcast recording data), and platform distribution data (such as exposure, click-through rate, recommendation status), etc.

[0048] An indicator trend describes the direction of change in livestream room data (e.g., indicator data) over a period of time. It can reflect whether a specific indicator of a livestream room is trending upward, downward, or experiencing fluctuations. For example, historical changes in the instant exit rate can be used to analyze whether this indicator is trending upward. Indicator trends can reveal potential anomalies in a livestream room or changes in the appeal of its content, providing a dynamic understanding of the livestream room ecosystem.

[0049] Step S202 , according to the indicator trend of each live broadcast room, determine the first live broadcast room among the multiple live broadcast rooms.

[0050] Based on the indicator trends of live streaming rooms, multiple live streaming rooms can be comprehensively evaluated and ranked to identify those with potential ecological anomalies, namely the primary live streaming rooms. For example, a set of weighting models can be set up to assign different weights to each specific indicator in the indicator trend (such as the instant exit rate, interaction volume, and user return rate). Based on the weighted scores, a comprehensive evaluation of the live streaming rooms can be performed to more accurately identify those with potential ecological anomalies. Potential ecological anomalies can also be identified based on pre-set rules. For example, if the instant exit rate of a live streaming room increases by 30% within 5 minutes (exceeding the 10% threshold specified in the rules), and the number of comments and likes decreases by more than preset thresholds, the room is determined to be the primary live streaming room. In this embodiment, the indicator trends of live streaming rooms are used to screen out a portion of live streaming rooms with anomaly risks (the primary live streaming rooms), which can improve the efficiency of subsequent manual review.

[0051] Step S204 , obtaining interaction information for the first live broadcast room, and determining a second live broadcast room and a third live broadcast room from the plurality of first live broadcast rooms based on the interaction information, wherein the abnormality probability of the second live broadcast room is greater than that of the third live broadcast room.

[0052] Interaction information can include subjective user feedback on livestreams, such as the results of livestream questionnaires or evaluations submitted by users with specific identities (e.g., monitoring viewers). In this embodiment, after identifying the first livestream, a questionnaire can be sent to users watching the first livestream, or monitoring viewers can be invited to review the content of the first livestream. After obtaining the interaction information, the first livestream is then divided into a third livestream with a lower risk of abnormality and a second livestream with a higher risk of abnormality by performing statistical analysis, aggregation, and scoring on the interaction information.

[0053] In some embodiments, interactive information may also include audience comments or comments. By analyzing these comments or comments, it's possible to further determine whether viewers have exhibited negative feedback, unusual behavior, or sensitive reactions to the live content, thereby more accurately identifying potential ecosystem issues. For example, after Live Streaming Room A is initially identified as the primary live stream, the probability of ecosystem anomalies in Room A can be further determined based on the comments or comments within Room A. Specifically, a text sentiment analysis model can be used to assign a risk score to the interactive content within Room A. If it is determined that some viewers in Room A have sent a large number of negative comments (e.g., "vulgar," "don't watch," or "disgusting"), the risk score for Room A can be calculated based on the proportion of negative comments in the overall commentary, along with the profile and historical behavior of the users who sent the negative comments. If the risk score exceeds a set threshold, Room A can be determined to have a high probability of ecosystem anomaly and designated as the second live stream, entering the subsequent manual review process. If the risk score does not exceed the set threshold, the probability of ecosystem anomaly in Room A can be determined to be low and designated as the third live stream.

[0054] The following will further introduce the supervision process of the live broadcast room in combination with multiple embodiments.

[0055] In an optional embodiment, if Figure 3 As shown, step S200 includes: Step S300: For each live broadcast room, obtain the live broadcast room data of the live broadcast room at the current moment and the previous moment every first preset time period, and the live broadcast room data includes the indicator value of the live broadcast room under the preset indicator.

[0056] Step S302: Determine the indicator trend of the live broadcast room based on the indicator value at the current moment and the indicator value at the previous moment.

[0057] In actual applications, by regularly obtaining the live broadcast room data of the "current moment" of each live broadcast room at fixed time intervals (i.e., the "first preset time period", such as 5 minutes), as well as the live broadcast room data corresponding to the "previous moment" (i.e., the previous time point, such as 5 minutes ago), and comparing the data at these two moments, it is possible to analyze whether the indicator value has an upward or downward trend during this period (i.e., the "indicator trend"). Preset indicators may include information such as the instant exit rate, exposure, click-through rate, average viewing time, interaction frequency, number of likes, and barrage density. The indicator trend can reflect the performance of the live broadcast room in terms of user experience, content attractiveness, and audience retention. For example, if the interaction frequency and barrage density of a live broadcast room increase significantly in a short period of time, but at the same time, the average viewing time decreases, it may indicate that the live broadcast room has experienced abnormal situations such as fake interactions and inducing audience behavior.

[0058] In this embodiment, by acquiring and calculating indicator trends in real time, the first live broadcast room with abnormal fluctuations in indicator values and possible ecological problems can be identified and screened out in a timely manner as a candidate for subsequent manual review, further improving the efficiency and timeliness of handling abnormal live broadcast rooms.

[0059] In an optional embodiment, if Figure 4 As shown, step S202 includes: Step S400: Obtain historical supervision information, where the historical supervision information includes a target live broadcast room, and the target live broadcast room includes a live broadcast room determined as the second live broadcast room within a second preset time period.

[0060] Step S402: determine whether the indicator trend of each live broadcast room shows a deterioration trend, and determine the live broadcast room showing a deterioration trend as a candidate live broadcast room.

[0061] Step S404: Eliminate the target live broadcast room from the candidate live broadcast rooms to obtain the first live broadcast room.

[0062] Historical regulatory information can be used to record whether a live broadcast room has been identified as an abnormal live broadcast room in the recent period (i.e., the second preset time period, such as three days), what relevant measures have been taken (such as banning, reducing exposure, etc.), and whether it has been submitted to the review platform for review by auditors. Historical regulatory information can be generated and regularly updated based on data such as the live broadcast room's penalty records and the review platform's submission records to reflect the latest processing status of each live broadcast room. For example, when a live broadcast room is identified as an abnormal live broadcast room and relevant measures are taken, the processing event can be bound to the live broadcast room ID and recorded in the historical regulatory information in a timely manner.

[0063] In practical applications, a variety of pre-set rules can be used to determine if a metric is showing a deteriorating trend. For example, key metrics for a livestream (e.g., instant exit rate, average dwell time, interaction drop rate, etc.) continue to decline, exceed a pre-set threshold, or exceed a historical fluctuation range. In this embodiment, to avoid duplicating audit resources for livestreams that have recently been reviewed or processed, and to further improve audit efficiency, livestreams that have recently been processed or reported to the audit platform can be removed from the candidate set of livestreams showing a deteriorating metric trend. For example, if multiple key metrics (e.g., instant exit rate, impression-to-click ratio, dwell time, etc.) for livestreams A, B, and C all show a significant decline, then the metric trends for these three studios can be determined to be deteriorating and they can be included in the candidate set. Further comparison of historical regulatory information reveals that livestream B had been designated as a secondary livestream and penalized (e.g., a 12-hour ban) the previous day, while livestream C had also been designated as a secondary livestream and submitted to the audit platform two days prior, where it was determined to have "no obvious violations." Therefore, if live broadcast rooms B and C are identified as second live broadcast rooms within the second preset time period (such as one week) and then processed or reported to the review platform, then live broadcast rooms B and C can be eliminated from the candidate live broadcast rooms, and only live broadcast room A will be retained as the first live broadcast room to continue the subsequent screening process.

[0064] In this embodiment, by eliminating target live broadcast rooms that have been identified as the second live broadcast room within the second preset time period, repeated review of the same live broadcast room within a short period of time can be effectively avoided, reducing the waste of manual review costs. At the same time, because review resources can be preferentially allocated to live broadcast rooms that have not been processed recently but have shown abnormal trends, the efficiency and accuracy of handling abnormal live broadcast rooms can be further improved.

[0065] In an optional embodiment, the interactive information includes first interactive information from a first object, and the first object includes viewers in the first live broadcast room. Figure 5 As shown, step S204 includes: Step S500, sending a broadcast message to the audience terminal, the audience terminal is used to: receive the broadcast message; based on the broadcast message, display a first interactive panel for the first live broadcast room in the first live broadcast room; in response to the interactive operation of the first object on the first interactive panel, generate first interactive information for the first live broadcast room, and send the first interactive information to the server.

[0066] Step S502: Obtain the first interactive information for the first live broadcast room provided by the viewer terminal.

[0067] In actual applications, the first interactive panel can be a questionnaire displayed in the form of a pop-up window or a floating layer, which can specifically include fields such as single-choice, multiple-choice, scoring or text input to collect first interactive information. The first interactive information may include the audience's evaluation of the live broadcast content, their views on the host's behavior, whether there are any reports of illegal content, whether the audience feels uncomfortable during the viewing process, whether they are willing to continue watching, and other information. By collecting the first interactive information filled out by the audience (i.e., the first object) who is watching the live broadcast in the first live broadcast room, it is possible to evaluate in real time from the perspective of user experience whether there are potential ecological problems with the current live broadcast content of the first live broadcast room. In some embodiments, different weight values can be assigned to the first interactive information of different types of first objects by combining the user portrait of the first object, such as the audience's age, viewing history, reporting record, etc., thereby improving the representativeness and credibility of the first interactive information results and achieving a more accurate assessment of the status of the live broadcast room.

[0068] In this embodiment, by collecting the first interactive information from the audience in the first live broadcast room, without relying on manual reporting, the live broadcast room ecological evaluation basis is supplemented from the perspective of user experience in real time, further improving the accuracy and efficiency of handling abnormal live broadcast rooms.

[0069] In an optional embodiment, the interaction information includes second interaction information from a second object. Figure 6 As shown, step S204 includes: Step S600, in response to the review request of the monitoring platform, the live broadcast room data of the first live broadcast room is sent to the monitoring platform, and the monitoring platform is used to: display the live broadcast room data of the first live broadcast room; in response to the review operation of the second object on the first live broadcast room, generate second interactive information for the first live broadcast room, and send the second interactive information to the server.

[0070] Step S602: Obtain the second interactive information for the first live broadcast room provided by the monitoring platform.

[0071] In practical applications, the second interactive information can include information on whether the live broadcast room content violates platform rules, as well as information such as the type of violation (e.g., vulgar content, inducement to reward, insults and attacks), the severity of the violation (mild, moderate, severe), and recommended action (e.g., warning, traffic restriction, ban). The live broadcast room data sent to the monitoring platform can include multi-dimensional data such as the live broadcast recording, comment information, viewer behavior records, and historical violation records of the first live broadcast room, enabling the second party to more comprehensively assess the compliance of the first live broadcast room. In some embodiments, statistical charts can also be generated based on the live broadcast room data of the first live broadcast room, allowing the monitoring platform to more intuitively display relevant information about the first live broadcast room to the second party, speeding up the second party's review of the first live broadcast room. The statistical charts can include trend charts of various indicators of the first live broadcast room (e.g., charts of changes in instant exit rate and exposure rate), or word clouds of high-frequency comment comments with larger, more prominent fonts.

[0072] In this embodiment, by submitting the live broadcast room data of the first live broadcast room to the monitoring platform and receiving the second interactive information returned by a second object with monitoring qualifications, the review burden can be effectively shared in the large-scale live broadcast content supervision. By using the audience group authorized by the platform for pre-review, it is possible to achieve effective supervision of the live broadcast room content without relying on the full participation of human reviewers, thereby improving the execution efficiency and coverage of handling abnormal live broadcast rooms.

[0073] In an optional embodiment, the first interactive information includes multiple copies, each copy of the first interactive information corresponds to a first object. Figure 7 As shown, the method further includes: Step S700: reporting the live broadcast room data of the second live broadcast room to an audit platform, wherein the audit platform is configured to determine an abnormal live broadcast room to be processed from the second live broadcast room based on the live broadcast room data; Step S702: Determine the matching degree between each piece of first interactive information and the abnormal live broadcast room.

[0074] Step S704: obtaining a first object corresponding to the first interactive information having a matching degree higher than a first preset threshold, and configuring the monitoring qualification for the first object to convert the first object into the second object.

[0075] The review platform can be a dedicated system within the live streaming platform for content review and ecosystem governance. It can display live broadcast information from the second live streaming room to reviewers to further identify abnormal live streaming rooms. In some embodiments, a machine review model can first perform intelligent analysis of live streaming room data such as audio and video content, host behavior, and barrage interaction. After identifying illegal behaviors (such as vulgar content, inducement to reward, and abusive behavior) and assigning risk tags, reviewers can then manually verify and judge the second live streaming room based on the risk tags to improve the efficiency and accuracy of the assessment of abnormal live streaming rooms.

[0076] In some embodiments, after the review platform completes its review of the second livestream room and identifies any abnormal livestream rooms to be addressed, it can return structured results to the server regarding confirmed abnormal livestream rooms with ecological anomalies. This structured result can include information such as the livestream room's unique identifier, violation type, review time, risk level, and reviewer recommendations. Based on this structured result, the server can automatically retrieve the abnormal livestream rooms provided by the review platform and perform appropriate processing. Different processing actions can be taken based on the severity of the violation or the livestream room's violation history. For example, for livestream rooms with minor violations, a warning can be issued, prompting the streamer to rectify the situation, and traffic restrictions or reduced exposure can be implemented. For livestream rooms with moderate violations, actions such as temporary bans, removal of livestream content, and restrictions on reward functions can be implemented. For livestream rooms with severe or repeated violations, direct account suspension can be implemented. Furthermore, if the review platform determines that the second livestream room does not exhibit abnormal behavior, the corresponding review results can be returned to optimize the screening strategies for the first and second livestream rooms.

[0077] In practical applications, the match between the first interactive information and the abnormal livestream can be assessed by combining the first subject's profile information and the content quality of the first interactive information. This profile information may include the first subject's account age, viewing behavior, historical feedback history, and reporting success rate. The content quality of the first interactive information can be comprehensively scored based on factors such as the level of detail provided by the first subject. For example, if subject A is a highly active, long-term viewer whose account has been registered for over a year and whose past reports have been accepted by the platform, their profile information can be considered highly reliable. Furthermore, the first interactive information submitted by subject A has clear logic and is highly consistent with the evaluation of the abnormal livestream returned by the review platform. Therefore, subject A's first interactive information can be deemed highly credible and highly compatible with the abnormal livestream. If the matching degree exceeds a first preset threshold (e.g., 80%), subject A can be assigned corresponding monitoring permissions, allowing them to access the monitoring platform to review the first livestream.

[0078] In some embodiments, in order to motivate viewers with monitoring authority (i.e., second subjects) to continuously participate in ecological assessments and maintain a high accuracy rate, a monitoring points data table can be configured for the second subject to record the progress of the second subject's review task completion. Specifically, monitoring points can be redeemed for virtual rewards, such as live broadcast platform membership experience qualifications, barrage special effects, avatar pendants, exclusive titles, or physical prize redemption codes. When the second subject completes a certain number (e.g., 100 times) of review tasks and has a high accuracy rate (e.g., over 90%), he or she can obtain the title of "senior monitoring audience" and his or her account can be displayed with a special logo in the live broadcast room.

[0079] In this embodiment, based on the matching degree between the first interactive information and the abnormal live broadcast room, the second object is screened out from the first object and the monitoring qualification is configured for the second object. This allows viewers with monitoring capabilities to be discovered as part of the review human resources, thereby further improving the efficiency and accuracy of handling abnormal live broadcast rooms.

[0080] In an optional embodiment, the second interactive information includes multiple copies, each copy of the second interactive information corresponds to a second object, such as Figure 8 As shown, the method further includes: Step S800: Determine the matching degree between each piece of second interactive information and the abnormal live broadcast room.

[0081] Step S802: obtaining a second object corresponding to the second interactive information whose matching degree is lower than a second preset threshold, and canceling the monitoring qualification of the second object.

[0082] In practical applications, the match between the second interactive information and the abnormal live broadcast room can be evaluated based on the second subject's historical review performance. This match can be used to reflect the accuracy and professionalism of the second subject's judgment of abnormal live broadcast content. The second subject's historical review performance may include: the number of previously submitted review conclusions, review accuracy, and historical qualification changes. For example, if second subject B submits a large number of second interactive information within a certain period of time, but many of these submissions are inconsistent with the final review conclusions of the review platform, the credibility of second subject B's second interactive information will be significantly reduced. For second subject B with reduced credibility, the match value calculated when calculating the match between the second interactive information submitted by the second subject B and the abnormal live broadcast room can be appropriately reduced based on second subject B's review accuracy. When the match falls below a second preset threshold (e.g., 80%), the platform can automatically revoke second subject B's monitoring qualification to prevent its second interactive information from interfering with the overall review quality.

[0083] In some embodiments, to achieve fairer and more reasonable management of supervisory qualifications, a phased management approach of "warning-observation-cancellation" may be adopted, allowing for gradual qualification adjustments when a decline in the second subject's review accuracy is detected. Specifically, when the second subject's review accuracy first falls below a threshold, only a warning is issued, and an observation period is initiated. If, during the observation period, the second subject's review accuracy has not returned to a preset standard (e.g., 80%), and there are still multiple instances of low matching between the second interaction information and the audit platform's determination, the qualification cancellation phase begins.

[0084] In this embodiment, whether to cancel the second object's supervisory qualification is determined based on the matching degree between the second interactive information and the abnormal live broadcast room, which can ensure the continued reliability of the overall review quality of the monitoring platform and further improve the efficiency and accuracy of handling abnormal live broadcast rooms.

[0085] In order to make this application easier to understand, the following Figure 9 An exemplary application is provided.

[0086] S11, obtaining indicator data such as live broadcast room instant exit / report information reported by viewers.

[0087] S12, based on the indicator data, screen out potential ecological abnormal live broadcast rooms whose indicator data show a deterioration trend from multiple live broadcast rooms.

[0088] S13, sending a questionnaire about the ecological problems of the live broadcast room to the audience in the live broadcast room with potential ecological abnormality, and obtaining the first interactive information result.

[0089] S14, obtaining the second interaction information of the monitored audience regarding the live broadcast room with potential ecological anomalies.

[0090] S15. Based on the first interactive information result and the second interactive information, screen out the high-probability ecological abnormal live broadcast rooms with more feedback issues.

[0091] S16, the live broadcast rooms with high probability of ecological anomalies will be sent to the review platform for review by professional reviewers.

[0092] S17, obtain the final audit result returned by the audit platform.

[0093] S18, comparing the final audit result with the first interactive information result, and granting monitoring qualifications to viewers whose final audit result has a high consistency with the first interactive information result.

[0094] In this exemplary application, based on the indicator data reported by the audience, potential ecological abnormal live broadcast rooms are screened out from a large number of live broadcast rooms. Then, by obtaining the first interactive information results of the audience in the potential ecological abnormal live broadcast room and monitoring the second interactive information of the audience for the potential ecological abnormal live broadcast room, high-probability ecological abnormal live broadcast rooms with a higher abnormal probability are further screened out. Finally, the screened high-probability ecological abnormal live broadcast rooms are sent to the review platform for review by professional reviewers. By performing multiple screenings in the live broadcast room, the number of live broadcast rooms submitted to the review platform can be reduced, the coverage of the live broadcast room processing can be expanded, and the efficiency and accuracy of handling abnormal live broadcast rooms can be improved.

[0095] Example 2 Figure 10 The block diagram of the live broadcast room processing device according to the second embodiment of the present application is schematically shown. The device can be divided into one or more program modules, one or more program modules are stored in a storage medium and executed by one or more processors to complete the embodiment of the present application. The program module referred to in the embodiment of the present application refers to a series of computer program instruction segments that can complete specific functions. The following description will specifically introduce the functions of each program module in this embodiment. Figure 10 As shown, the apparatus 1000 may include: an acquisition module 1010 and a determination module 1020, wherein: An acquisition module 1010 is configured to acquire live broadcast room data of a plurality of live broadcast rooms, and determine an indicator trend of a corresponding live broadcast room based on the live broadcast room data; A determination module 1020 is configured to determine a first live broadcast room from among the multiple live broadcast rooms based on an indicator trend of each live broadcast room; The acquisition module 1010 is further used to obtain interactive information for the first live broadcast room, and determine a second live broadcast room and a third live broadcast room among the multiple first live broadcast rooms based on the interactive information; wherein the abnormal probability of the second live broadcast room is greater than that of the third live broadcast room.

[0096] In an optional embodiment, obtaining live broadcast room data of a plurality of live broadcast rooms, and determining an indicator trend of a corresponding live broadcast room based on the live broadcast room data, includes: For each live broadcast room, obtaining live broadcast room data of the live broadcast room at the current moment and the previous moment every first preset time period, wherein the live broadcast room data includes an indicator value of the live broadcast room under a preset indicator; Based on the indicator value at the current moment and the indicator value at the previous moment, determine the indicator trend of the live broadcast room.

[0097] In an optional embodiment, determining a first live broadcast room from the plurality of live broadcast rooms according to an indicator trend of each live broadcast room includes: Acquire historical supervision information, where the historical supervision information includes a target live broadcast room, where the target live broadcast room includes a live broadcast room determined as the second live broadcast room within a second preset time period; Determine whether the indicator trend of each live broadcast room shows a deterioration trend, and determine the live broadcast room showing a deterioration trend as a candidate live broadcast room; Eliminate the target live broadcast room from the candidate live broadcast rooms to obtain the first live broadcast room.

[0098] In an optional embodiment, the interactive information includes first interactive information, and the first object includes viewers in the first live broadcast room. Correspondingly, obtaining the interactive information for the first live broadcast room includes: Sending a broadcast message to a viewer terminal, the viewer terminal being configured to: receive the broadcast message; display a first interactive panel for the first live broadcast room in the first live broadcast room based on the broadcast message; generating first interactive information for the first live broadcast room in response to an interactive operation of a first object on the first interactive panel, and sending the first interactive information to the server; Obtain the first interactive information for the first live broadcast room provided by the audience terminal.

[0099] In an optional embodiment, the interactive information includes second interactive information from a second object, where the second object includes a viewer with monitoring qualifications; correspondingly, obtaining the interactive information for the first live broadcast room includes: In response to a review request from a monitoring platform, the live broadcast room data of the first live broadcast room is sent to the monitoring platform, and the monitoring platform is configured to: display the live broadcast room data of the first live broadcast room; in response to a review operation of the first live broadcast room by a second subject, generate second interaction information for the first live broadcast room, and send the second interaction information to the server; Obtain second interactive information for the first live broadcast room provided by the monitoring platform.

[0100] In an optional embodiment, the first interaction information includes multiple copies, each copy of the first interaction information corresponds to a first object; correspondingly, the apparatus 1000 further includes a qualification configuration module, which is configured to: Reporting the live broadcast room data of the second live broadcast room to the review platform, wherein the review platform is configured to determine an abnormal live broadcast room to be processed from the second live broadcast room based on the live broadcast room data; Determining a matching degree between each piece of first interactive information and the abnormal live broadcast room; A first object corresponding to the first interactive information having a matching degree higher than a first preset threshold is obtained, and the monitoring qualification is configured for the first object to convert the first object into the second object.

[0101] In an optional embodiment, the second interaction information includes multiple copies, each copy of the second interaction information corresponds to a second object; the apparatus 1000 further includes a qualification cancellation module, configured to: Determining a matching degree between each piece of second interactive information and the abnormal live broadcast room; A second object corresponding to the second interactive information whose matching degree is lower than a second preset threshold is obtained, and the monitoring qualification of the second object is cancelled.

[0102] Example 3 Figure 11 The following schematically shows a hardware architecture diagram of a computer device 10000 suitable for implementing a live broadcast room processing method according to the third embodiment of the present application. In some embodiments, the computer device 10000 may be a terminal device such as a smart phone, a wearable device, a tablet computer, a personal computer, a vehicle-mounted terminal, a game console, a virtual device, a workbench, a digital assistant, a set-top box, a robot, etc. In other embodiments, the computer device 10000 may be a rack server, a blade server, a tower server, or a cabinet server (including an independent server, or a server cluster composed of multiple servers), etc. Figure 11 As shown, the computer device 10000 includes but is not limited to: a memory 10010, a processor 10020, and a network interface 10030 that can communicate with each other via a system bus. Memory 10010 includes at least one type of computer-readable storage medium, including flash memory, a hard disk, a multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic storage, a magnetic disk, an optical disk, and the like. In some embodiments, memory 10010 may be an internal storage module of computer device 10000, such as a hard disk or memory of computer device 10000. In other embodiments, memory 10010 may also be an external storage device of computer device 10000, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, and the like equipped on computer device 10000. Of course, memory 10010 may also include both internal storage modules and external storage devices of computer device 10000. In this embodiment, the memory 10010 is generally used to store an operating system and various application software installed on the computer device 10000, such as program code of a live broadcast room processing method, etc. In addition, the memory 10010 can also be used to temporarily store various data that have been output or are about to be output.

[0103] In some embodiments, processor 10020 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other chips. Processor 10020 is typically used to control the overall operation of computer device 10000, such as performing control and processing related to data exchange or communication with computer device 10000. In this embodiment, processor 10020 is used to execute program code stored in memory 10010 or process data.

[0104] Network interface 10030 may include a wireless network interface or a wired network interface. Network interface 10030 is typically used to establish a communication link between computer device 10000 and other computer devices. For example, network interface 10030 is used to connect computer device 10000 to an external terminal via a network, establishing a data transmission channel and a communication link between computer device 10000 and the external terminal. The network may be a wireless or wired network such as an intranet, the Internet, the Global System of Mobile Communications (GSM), Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, Bluetooth, or Wi-Fi.

[0105] It should be pointed out that Figure 11 Only a computer device having components 10010 - 10030 is shown, but it should be understood that implementing all of the shown components is not a requirement, and more or fewer components may alternatively be implemented.

[0106] In this embodiment, the live broadcast room processing method stored in the memory 10010 can also be divided into one or more program modules and executed by one or more processors (such as processor 10020) to complete the embodiment of the present application.

[0107] Example 4 An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the live broadcast room processing method in the embodiment are implemented.

[0108] In this embodiment, computer-readable storage media include flash memory, hard disks, multimedia cards, card-type memories (e.g., SD or DX memories), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic storage, magnetic disks, optical disks, and the like. In some embodiments, the computer-readable storage medium may be an internal storage unit of a computer device, such as the computer device's hard disk or memory. In other embodiments, the computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, and the like. Of course, the computer-readable storage medium may also include both the internal storage unit and external storage devices of the computer device. In this embodiment, the computer-readable storage medium is typically used to store the operating system and various application software installed on the computer device, such as the program code of the live broadcast room processing method described in the embodiment. Furthermore, the computer-readable storage medium may also be used to temporarily store various types of data that has been output or is about to be output.

[0109] Example 5 An embodiment of the present application further provides a computer program product, including a computer program, which implements the method in the above embodiment when executed by a processor.

[0110] Obviously, those skilled in the art should understand that the modules or steps of the above-mentioned embodiments of the present application can be implemented using general-purpose computer devices. They can be concentrated on a single computer device or distributed on a network composed of multiple computer devices. Alternatively, they can be implemented using program codes executable by the computer device, so that they can be stored in a storage device and executed by the computer device. In some cases, the steps shown or described can be performed in a different order than herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0111] It should be noted that the above are only preferred embodiments of the present application and do not limit the scope of patent protection of the present application. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of this application, or directly or indirectly applied in other related technical fields, are also included in the scope of patent protection of the present application.

Claims

1. A live broadcast room processing method, characterized in that: For the server, the method includes: Acquire live broadcast room data of multiple live broadcast rooms, and determine indicator trends of corresponding live broadcast rooms based on the live broadcast room data; Determine a first live broadcast room from the plurality of live broadcast rooms according to an indicator trend of each live broadcast room; Obtain interaction information for the first live broadcast room, and determine a second live broadcast room and a third live broadcast room from the multiple first live broadcast rooms based on the interaction information; wherein the abnormality probability of the second live broadcast room is greater than that of the third live broadcast room.

2. The method according to claim 1, characterized in that Acquiring live broadcast room data of multiple live broadcast rooms, and determining indicator trends of corresponding live broadcast rooms based on the live broadcast room data, including: For each live broadcast room, obtaining live broadcast room data of the live broadcast room at the current moment and the previous moment every first preset time period, wherein the live broadcast room data includes an indicator value of the live broadcast room under a preset indicator; Based on the indicator value at the current moment and the indicator value at the previous moment, determine the indicator trend of the live broadcast room.

3. The method according to claim 1, characterized in that Determining a first live broadcast room from the multiple live broadcast rooms according to an indicator trend of each live broadcast room includes: Acquire historical supervision information, where the historical supervision information includes a target live broadcast room, where the target live broadcast room includes a live broadcast room determined as the second live broadcast room within a second preset time period; Determine whether the indicator trend of each live broadcast room shows a deterioration trend, and determine the live broadcast room showing a deterioration trend as a candidate live broadcast room; Eliminate the target live broadcast room from the candidate live broadcast rooms to obtain the first live broadcast room.

4. The method according to claim 1, wherein The interactive information includes first interactive information from a first object, where the first object includes an audience in the first live broadcast room; Correspondingly, obtaining interactive information for the first live broadcast room includes: Sending a broadcast message to a viewer terminal, the viewer terminal being configured to: receive the broadcast message; display a first interactive panel for the first live broadcast room in the first live broadcast room based on the broadcast message; generating first interactive information for the first live broadcast room in response to an interactive operation of a first object on the first interactive panel, and sending the first interactive information to the server; Obtain the first interactive information for the first live broadcast room provided by the audience terminal.

5. The method according to claim 4, characterized in that The interactive information includes second interactive information from a second object, where the second object includes a viewer with monitoring qualifications. Correspondingly, obtaining the interactive information for the first live broadcast room includes: In response to a review request from a monitoring platform, the live broadcast room data of the first live broadcast room is sent to the monitoring platform, and the monitoring platform is configured to: display the live broadcast room data of the first live broadcast room; in response to a review operation of the first live broadcast room by a second subject, generate second interaction information for the first live broadcast room, and send the second interaction information to the server; Obtain second interactive information for the first live broadcast room provided by the monitoring platform.

6. The method according to claim 5, characterized in that The first interactive information includes multiple copies, each copy of the first interactive information corresponds to a first object; correspondingly, the method further includes: Reporting the live broadcast room data of the second live broadcast room to the review platform, wherein the review platform is configured to determine an abnormal live broadcast room to be processed from the second live broadcast room based on the live broadcast room data; Determining a matching degree between each piece of first interactive information and the abnormal live broadcast room; A first object corresponding to the first interactive information having a matching degree higher than a first preset threshold is obtained, and the monitoring qualification is configured for the first object to convert the first object into the second object.

7. The method according to claim 6, characterized in that The second interactive information includes multiple copies, each copy of the second interactive information corresponds to a second object; the method further includes: Determining a matching degree between each piece of second interactive information and the abnormal live broadcast room; A second object corresponding to the second interactive information whose matching degree is lower than a second preset threshold is obtained, and the monitoring qualification of the second object is cancelled.

8. A live broadcast room processing device, characterized in that: The device comprises: An acquisition module, configured to acquire live broadcast room data of a plurality of live broadcast rooms, and determine an indicator trend of a corresponding live broadcast room based on the live broadcast room data; A determination module, configured to determine a first live broadcast room among the multiple live broadcast rooms based on an indicator trend of each live broadcast room; The acquisition module is also used to obtain interactive information for the first live broadcast room, and determine the second live broadcast room and the third live broadcast room among the multiple first live broadcast rooms based on the interactive information; wherein the abnormal probability of the second live broadcast room is greater than that of the third live broadcast room.

9. A computer device, characterized in that: include: at least one processor; and a memory communicatively coupled to the at least one processor; wherein: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, which, when executed by a processor, implement the method according to any one of claims 1 to 7.

11. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to claims 1 to 7 are implemented.

Images