Method, device and system for matching live broadcast objects

Abstract

The present disclosure relates to a matching method and device of live objects, electronic equipment and storage medium, and relates to the field of Internet media. The method comprises: in response to a matching request of a first live object, determining at least one second live object from a plurality of to-be-matched objects, wherein the object association information of the at least one second live object meets a condition; in the case that the matching waiting time length of the first live object is less than a first time length, determining at least one target live object from the at least one second live object based on the capability information of the first live object, the capability information of the at least one second live object and the object association information; and returning the at least one target live object to the first live object. According to the technical scheme of the present disclosure, the target live object has a smaller capability difference with the first live object and has a certain association, is suitable for joint live with the first live object, and the effectiveness of the matching is improved, and the matching effect is better.

Description

Technical Field

[0001] This disclosure relates to the field of internet media, and in particular to a method, apparatus, electronic device, and storage medium for matching live streaming subjects. Background Technology

[0002] With the development of computer technology, live streaming has become a popular technology. Live streaming objects can be combined with other objects to enrich the content of the live stream. How to match live streaming objects with other objects for joint live streaming is a problem that needs to be solved.

[0003] Currently, the common practice is to match the live streaming object with other objects of the same live streaming type for joint live streaming.

[0004] The problem with the above technical solution is that there are often many objects of the same live streaming type as the live streaming object, most of which are not suitable for joint live streaming with the live streaming object. This makes it difficult to match a suitable object for the live streaming object, resulting in poor matching effect. Summary of the Invention

[0005] This disclosure provides a method, apparatus, electronic device, and storage medium for matching live streaming objects. By determining at least one target live streaming object to be jointly streamed with a first live streaming object based on the capability information and object association information of the live streaming object, the method ensures that the capability difference between the at least one target live streaming object and the first live streaming object is small and that they have a certain correlation, making them suitable for joint streaming with the first live streaming object. This improves the effectiveness of the matching and achieves better matching results. The technical solution of this disclosure is as follows:

[0006] According to one aspect of the embodiments of this disclosure, a method for matching live streaming objects is provided, the method comprising:

[0007] In response to a matching request from a first live streaming object, at least one second live streaming object whose object association information meets the conditions is determined from a plurality of objects to be matched. The matching request is used to indicate the result of matching the first live streaming object with other live streaming objects for joint live streaming. The object association information includes at least one of similarity information with the first live streaming object, social relationship information, and historical joint live streaming information. The historical joint live streaming information is used to indicate the live streaming result of joint live streaming with the first live streaming object within a historical time period.

[0008] If the matching waiting time of the first live streaming object is less than the first time, based on the capability information of the first live streaming object, the capability information of the at least one second live streaming object, and the object association information of the at least one second live streaming object, at least one target live streaming object is determined from the at least one second live streaming object. The capability information is used to indicate the live streaming result of the live streaming object performing joint live streaming within the historical time period.

[0009] Return the at least one target live streaming object to the first live streaming object so that the first live streaming object and the at least one target live streaming object can perform joint live streaming.

[0010] According to another aspect of the embodiments of this disclosure, a matching device for live streaming objects is provided, comprising:

[0011] The first determining unit is configured to, in response to a matching request from a first live streaming object, determine at least one second live streaming object whose object association information satisfies a condition from a plurality of objects to be matched. The matching request is used to indicate that other live streaming objects are matched for joint live streaming for the first live streaming object. The object association information includes at least one of similarity information with the first live streaming object, social relationship information, and historical joint live streaming information. The historical joint live streaming information is used to indicate the live streaming results of joint live streaming with the first live streaming object within a historical time period.

[0012] The second determining unit is configured to determine at least one target live streaming object from the at least one second live streaming object based on the capability information of the first live streaming object, the capability information of the at least one second live streaming object, and the object association information of the at least one second live streaming object when the matching waiting time of the first live streaming object is less than the first time. The capability information is used to indicate the live streaming result of the live streaming object performing joint live streaming within the historical time period.

[0013] The object return unit is configured to return the at least one target live streaming object to the first live streaming object, so that the first live streaming object and the at least one target live streaming object can perform joint live streaming.

[0014] In some embodiments, the first determining unit includes:

[0015] The first determining subunit is configured to, in response to a matching request from a first live streaming object, determine a plurality of third live streaming objects from the plurality of objects to be matched based on the capability information of the first live streaming object, wherein the difference between the capability information of the third live streaming object and the capability information of the first live streaming object is within a target difference range.

[0016] The second determining subunit is configured to, when the number of the third live objects is greater than a number threshold, determine at least one second live object from the plurality of third live objects whose object association information satisfies the conditions.

[0017] In some embodiments, the capability information includes a capability mean and a capability standard deviation; the first determining subunit is configured to, for any target object, acquire the capability information of the target object; based on the capability information of the first live streaming object and the capability information of the target object, determine a matching capability mean and a matching capability standard deviation, wherein the matching capability mean is used to indicate the difference between the capability mean of the first live streaming object and the capability mean of the target object, and the matching capability standard deviation is used to indicate the difference between the capability standard deviation of the first live streaming object and the capability standard deviation of the target object; and if the ratio of the matching capability mean to the matching capability standard deviation is within the target difference range, determine the target object as the third live streaming object.

[0018] In some embodiments, the apparatus further includes:

[0019] The range expansion unit is configured to expand the target difference range when the number of the third live objects is not greater than the number threshold.

[0020] The third determining unit is configured to re-determine multiple third live objects from the multiple objects to be matched based on the expanded target difference range.

[0021] The first determining unit is further configured to determine, from the plurality of third live streaming objects, at least one second live streaming object whose object association information satisfies the conditions.

[0022] In some embodiments, the plurality of objects to be matched are updated over time; the first determining unit is further configured to, when the number of the third live objects is not greater than the number threshold, determine a plurality of third live objects from the current plurality of objects to be matched after a preset time interval; and determine at least one second live object from the plurality of third live objects whose object association information satisfies the conditions.

[0023] In some embodiments, the plurality of objects to be matched are updated over time; the first determining unit is further configured to, in the event that the plurality of objects to be matched are updated, re-determine a plurality of third live streaming objects from the updated plurality of objects to be matched; and determine, from the plurality of third live streaming objects, at least one second live streaming object whose object association information satisfies the conditions.

[0024] In some embodiments, the second determining unit is further configured to determine at least one target live streaming object from the at least one second live streaming object based on the capability information of the first live streaming object, the capability information of the at least one second live streaming object, and the object association information of the at least one second live streaming object, when the matching waiting time of the first live streaming object is not less than the first duration and the number of the third live streaming object is greater than the number threshold.

[0025] In some embodiments, the target live streaming objects are multiple, and the apparatus further includes:

[0026] The object determination unit is configured to determine at least one fourth live object from the plurality of objects to be matched, provided that the matching waiting time of the first live object is not less than the first time and the number of the third live objects is not greater than the number threshold. The difference between the capability information of the fourth live object and the capability information of the first live object is outside the target difference range.

[0027] The second determining unit is further configured to determine the plurality of third live streaming objects and the at least one fourth live streaming object as a plurality of target live streaming objects.

[0028] In some embodiments, the second determining unit includes:

[0029] The associated molecular unit is configured to determine the object association score of the second live object based on the object association information of the second live object for any second live object;

[0030] The capability unit is configured to determine the object capability score of the second live object based on the difference between the capability information of the second live object and the capability information of the first live object;

[0031] The molecular unit of the object is configured to weight the object association score and the object capability score to obtain the object score of the second live object;

[0032] The object determination subunit is configured to determine the at least one target live streaming object from the at least one second live streaming object based on the object score of the at least one second live streaming object.

[0033] In some embodiments, the associated molecular unit is configured to determine at least two of the similarity score, social relationship score, and historical joint live broadcast score of the second live broadcast object based on the object association information of the second live broadcast object; and to perform a weighted summation of at least two of the similarity score, social relationship score, and historical joint live broadcast score of the second live broadcast object to obtain the object association score of the second live broadcast object.

[0034] In some embodiments, there are multiple target live streaming objects, and the first determining unit is further configured to determine multiple target live streaming objects from the multiple second live streaming objects based on the capability information of the first live streaming object, the capability information of the multiple second live streaming objects, and the object association information of the multiple second live streaming objects, when the number of the second live streaming objects is not less than the target number.

[0035] In some embodiments, the second determining unit is further configured to determine the at least one second live streaming object as a plurality of target live streaming objects when the number of the plurality of second live streaming objects is less than the target number; and to determine at least one target live streaming object from a plurality of fifth live streaming objects based on the capability information of the first live streaming object, the capability information of the at least one second live streaming object, and the object association information of the at least one second live streaming object, wherein the fifth live streaming object is a live streaming object whose object association information does not meet the conditions among the plurality of third live streaming objects.

[0036] According to another aspect of the embodiments of this disclosure, an electronic device is provided, the electronic device comprising:

[0037] One or more processors;

[0038] Memory used to store the executable program code of the processor;

[0039] The processor is configured to execute the program code to implement the matching method for the live streaming object.

[0040] According to another aspect of the present disclosure, a computer-readable storage medium is provided that, when program code in the computer-readable storage medium is executed by a processor of an electronic device, enables the electronic device to perform the above-described live object matching method.

[0041] According to another aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the above-described live streaming object matching method.

[0042] This disclosure provides a method for matching live streaming objects. By filtering at least one of the following: similarity information, social relationship information, and historical joint live streaming information between the first live streaming object and the second live streaming object, at least one second live streaming object that meets the conditions can be selected. This can improve the object association degree between other objects matched for the first live streaming object and the first live streaming object. Finally, based on the capability information and object association information of the live streaming object, at least one target live streaming object that will eventually conduct joint live streaming with the first live streaming object is determined. This ensures that the capability difference between the at least one target live streaming object and the first live streaming object is small and that they are related to each other, making them suitable for joint live streaming with the first live streaming object. This improves the effectiveness of the matching and results in a better matching effect.

[0043] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0044] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0045] Figure 1 This is a schematic diagram illustrating the implementation environment of a live streaming object matching method according to an exemplary embodiment.

[0046] Figure 2 This is a flowchart illustrating a live streaming object matching method according to an exemplary embodiment.

[0047] Figure 3 This is a flowchart illustrating another method for matching live streaming objects according to an exemplary embodiment.

[0048] Figure 4 This is a schematic diagram illustrating the determination of a target live streaming object according to an exemplary embodiment.

[0049] Figure 5 This is a flowchart illustrating another method for matching live streaming objects according to an exemplary embodiment.

[0050] Figure 6 This is an overall flowchart illustrating a first live streaming object matching a target live streaming object, according to an exemplary embodiment.

[0051] Figure 7 This is a block diagram illustrating a live streaming object matching device according to an exemplary embodiment.

[0052] Figure 8 This is a block diagram illustrating another live streaming object matching device according to an exemplary embodiment.

[0053] Figure 9 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation

[0054] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0055] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0056] It should be noted that all information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in this application have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the capability information involved in this application was obtained with full authorization.

[0057] Figure 1 This is a schematic diagram illustrating an implementation environment for a live streaming object matching method according to an exemplary embodiment. Taking an electronic device provided as a server as an example, see [link to example]. Figure 1 The implementation environment specifically includes: terminal 101 and server 102.

[0058] Terminal 101 can be at least one of the following devices: smartphone, smartwatch, desktop computer, laptop, MP3 player (Moving Picture Experts Group Audio Layer III), MP4 player (Moving Picture Experts Group Audio Layer IV), and laptop computer. An application for live streaming can be installed and run on terminal 101. Terminal 101 can connect to server 102 via a wireless network or wired network.

[0059] Terminal 101 can refer to one of a plurality of terminals; this embodiment uses terminal 101 as an example only. Those skilled in the art will understand that the number of terminals can be more or less. For example, there may be only a few terminals, or dozens or hundreds, or even more. This disclosure does not limit the number of terminals or the type of device.

[0060] Server 102 can be at least one of a single server, multiple servers, a cloud computing platform, and a virtualization center. Server 102 can be connected to terminal 101 and other terminals via a wireless network or a wired network. Optionally, the number of servers can be more or less, and this disclosure does not limit this. Of course, server 102 may also include other functional servers to provide more comprehensive and diversified services.

[0061] Figure 2 This is a flowchart illustrating a live streaming object matching method according to an exemplary embodiment, such as... Figure 2 As shown, this method is executed by the server and includes the following steps.

[0062] In step S201, in response to the matching request of the first live streaming object, the server determines at least one second live streaming object from a plurality of objects to be matched whose object association information meets the conditions. The matching request is used to indicate that other live streaming objects are matched for joint live streaming for the first live streaming object. The object association information includes at least one of similarity information with the first live streaming object, social relationship information, and historical joint live streaming information. The historical joint live streaming information is used to indicate the live streaming results of joint live streaming with the first live streaming object in a historical time period.

[0063] In this embodiment, the first live streaming object is the live streaming object requesting a joint live stream. The joint live stream includes various objectives, such as joint live streams aimed at gaining viewership, joint live streams aimed at showcasing talents, and joint live streams aimed at promoting products. The server provides backend services related to live streaming for the first live streaming object. The multiple objects to be matched are live streaming objects that have sent matching requests to the server but have not yet been successfully matched. For any object to be matched, the server can obtain the object association information of that object. Based on this object association information, further filtering of the multiple objects to be matched is performed to obtain multiple second live streaming objects whose object association information meets the conditions. Since the object association information includes at least one of similarity information with the first live streaming object, social relationship information, and historical joint live stream information, the objects to be matched can be filtered from at least one dimension of similarity with the first live streaming object, social relationship, and historical joint live stream information, so that the filtered second live streaming objects have a high degree of object association with the first live streaming object. It should be noted that the objective of the joint live stream requested by the object to be matched is the same as the objective of the joint live stream requested by the first live streaming object.

[0064] In step S202, if the matching waiting time of the first live streaming object is less than the first time, the server determines at least one target live streaming object from at least one second live streaming object based on the capability information of the first live streaming object, the capability information of at least one second live streaming object, and the object association information of at least one second live streaming object. The capability information is used to represent the live streaming result of the live streaming object performing joint live streaming within the historical time period.

[0065] In this embodiment of the disclosure, the server can determine the capability differences between the first live streaming object and at least one second live streaming object by using the capability information of the first live streaming object and the capability information of at least one second live streaming object. The server can also determine the degree of object association between the at least one second live streaming object and the first live streaming object by using the capability information of the at least one second live streaming object. Based on the aforementioned capability differences and degree of object association, the server determines a more suitable target live streaming object for the first live streaming object.

[0066] In step S203, the server returns at least one target live streaming object to the first live streaming object, so that the first live streaming object and at least one target live streaming object can perform joint live streaming.

[0067] In this embodiment of the disclosure, after determining at least one target live streaming object, the server can return the at least one target live streaming object to the first live streaming object, so that the first live streaming object can perform joint live streaming with at least one target live streaming object.

[0068] This disclosure provides a method for matching live streaming objects. By filtering at least one of the following: similarity information, social relationship information, and historical joint live streaming information between the first live streaming object and the second live streaming object, at least one second live streaming object that meets the conditions can be selected. This can improve the object association degree between other objects matched for the first live streaming object and the first live streaming object. Finally, based on the capability information and object association information of the live streaming object, at least one target live streaming object that will eventually conduct joint live streaming with the first live streaming object is determined. This ensures that the capability difference between the at least one target live streaming object and the first live streaming object is small and that they are related to each other, making them suitable for joint live streaming with the first live streaming object. This improves the effectiveness of the matching and results in a better matching effect.

[0069] In some embodiments, in response to a matching request from a first live streaming object, determining at least one second live streaming object from a plurality of objects to be matched whose object association information satisfies a certain condition includes:

[0070] In response to the matching request of the first live streaming object, multiple third live streaming objects are determined from multiple objects to be matched based on the capability information of the first live streaming object. The difference between the capability information of the third live streaming object and the capability information of the first live streaming object is within the target difference range.

[0071] If the number of third live streaming objects exceeds the number threshold, at least one second live streaming object whose object association information meets the conditions is determined from the multiple third live streaming objects.

[0072] By using the capability information of the first live streaming object, it is possible to identify multiple third live streaming objects whose capability information differences are within the target difference range from multiple objects to be matched, thereby reducing the capability differences between other objects matched for the first live streaming object and the first live streaming object.

[0073] In some embodiments, capability information includes the capability mean and capability standard deviation;

[0074] Based on the capability information of the first live streaming object, multiple third live streaming objects are determined from a pool of potential matching objects, including:

[0075] For any object to be matched, obtain the capability information of the object to be matched;

[0076] Based on the ability information of the first live streaming object and the ability information of the object to be matched, the mean of the matching ability and the standard deviation of the matching ability are determined. The mean of the matching ability is used to indicate the difference between the mean of the ability of the first live streaming object and the mean of the ability of the object to be matched, and the standard deviation of the matching ability is used to indicate the difference between the standard deviation of the ability of the first live streaming object and the standard deviation of the ability of the object to be matched.

[0077] If the ratio of the mean of matching ability to the standard deviation of matching ability is within the target difference range, the object to be matched is determined as the third live streaming object.

[0078] In this embodiment, the difference between the average ability of the first live-streaming object and the average ability of the object to be matched represents the average difference between their abilities. Similarly, the standard deviation of the ability of the first live-streaming object and the standard deviation of the ability of the object to be matched represents the standard deviation of their abilities. Therefore, by using the aforementioned average and standard deviation of matching abilities, the difference in abilities between the two live-streaming objects can be determined relatively accurately.

[0079] In some embodiments, the method further includes:

[0080] If the number of third live stream subjects does not exceed the quantity threshold, expand the target difference range;

[0081] Based on the expanded target difference range, multiple third live streaming objects are re-identified from multiple objects to be matched;

[0082] From multiple third live streaming objects, determine at least one second live streaming object whose object association information meets the conditions.

[0083] In this embodiment of the disclosure, by expanding the target difference range when a sufficient number of third live streaming objects have not been determined, the number of determined third live streaming objects can be increased, thereby obtaining a sufficient number of second live streaming objects and improving matching efficiency.

[0084] In some embodiments, multiple objects to be matched are updated over time; the method further includes:

[0085] If the number of third live streaming objects is not greater than the number threshold, after a preset time interval, multiple third live streaming objects are determined from the current multiple objects to be matched.

[0086] From multiple third live streaming objects, determine at least one second live streaming object whose object association information meets the conditions.

[0087] In this embodiment of the disclosure, when a sufficient number of third live streaming objects are not determined, the server determines a third live streaming object from multiple objects to be matched after a preset time interval, and then determines a second live streaming object that meets the conditions from the third live streaming object. This increases the ways to determine the second live streaming object, increases the probability of determining a sufficient number of second live streaming objects, and thus improves the matching efficiency.

[0088] In some embodiments, multiple objects to be matched are updated over time; the method further includes:

[0089] In the event that multiple objects to be matched are updated, multiple third-party live streaming objects are re-determined from the updated objects to be matched.

[0090] From multiple third live streaming objects, determine at least one second live streaming object whose object association information meets the conditions.

[0091] In this embodiment of the disclosure, by obtaining third live streaming objects from the objects to be matched again when the objects to be matched are updated before a sufficient number of third live streaming objects are determined, and then determining second live streaming objects that meet the conditions from the third live streaming objects, the number of ways to determine second live streaming objects is increased, the probability of determining a sufficient number of second live streaming objects is increased, and thus the matching efficiency is improved.

[0092] In some embodiments, the method further includes:

[0093] If the matching waiting time for the first live streaming object is not less than the first duration and the number of third live streaming objects is greater than the number threshold, at least one target live streaming object is determined from at least one second live streaming object based on the capability information of the first live streaming object, the capability information of at least one second live streaming object, and the object association information of at least one second live streaming object.

[0094] In this embodiment of the disclosure, when the matching waiting time of the first live streaming object is not less than the first time, and a sufficient number of third live streaming objects are determined, a sufficient number of second live streaming objects are obtained. Based on the capability information and object association information, a sufficient number of target live streaming objects can be determined from the second live streaming objects, so as to meet the matching requirements of the first live streaming object and improve the matching success rate.

[0095] In some embodiments, there are multiple target live streaming objects, and the method further includes:

[0096] If the matching waiting time of the first live object is not less than the first time and the number of the third live objects is not greater than the number threshold, at least one fourth live object is determined from multiple objects to be matched, and the difference between the capability information of the fourth live object and the capability information of the first live object is outside the target difference range.

[0097] Multiple third-party live streaming objects and at least one fourth-party live streaming object are identified as multiple target live streaming objects.

[0098] In this embodiment of the disclosure, when the matching waiting time of the first live object exceeds the upper limit of the waiting time and a sufficient number of third live objects are not determined, the server will determine at least one fourth live object outside the target difference range. The at least one third live object within the target difference range and the at least one fourth live object outside the target difference range will be returned to the first live object as multiple target live objects. This avoids the first live object from waiting for too long while meeting the matching requirements of the first live object, thereby improving the matching success rate.

[0099] In some embodiments, determining at least one target live streaming object from at least one second live streaming object based on the capability information of a first live streaming object, the capability information of at least one second live streaming object, and the object association information of at least one second live streaming object includes:

[0100] For any second live streaming object, determine the object association score of the second live streaming object based on the object association information of the second live streaming object;

[0101] Based on the difference between the capability information of the second live streaming object and the capability information of the first live streaming object, determine the object capability score of the second live streaming object;

[0102] The object score of the second live-streaming object is obtained by weighting the object association score and the object capability score.

[0103] Based on the object score of at least one second live object, determine the target number of target live objects from at least one second live object.

[0104] In this embodiment of the disclosure, the target live streaming object is determined based on the object score of the second live streaming object. At the same time, the influence of the degree of correlation and ability difference between the live streaming objects on the first live streaming object is considered. This makes the ability difference between the determined target live streaming object and the first live streaming object small and related, which is suitable for joint live streaming with the first live streaming object.

[0105] In some embodiments, determining the object association score of the second live streaming object based on the object association information of the second live streaming object includes:

[0106] Based on the object association information of the second live streaming object, determine at least two of the following: similarity score, social relationship score, and historical joint live streaming score of the second live streaming object;

[0107] The object association score of the second live stream object is obtained by weighted summing of at least two of the similarity score, social relationship score, and historical joint live stream score.

[0108] In this embodiment of the disclosure, by weighting and summing the scores of different types of association information, different types of association information between live streaming objects have different effects on the degree of association between live streaming objects, so that the object association score can more accurately reflect the degree of association between live streaming objects.

[0109] In some embodiments, there are multiple target live streaming objects. Based on the capability information of a first live streaming object, the capability information of at least one second live streaming object, and the object association information of at least one second live streaming object, at least one target live streaming object is determined from at least one second live streaming object, including:

[0110] If the number of second live streaming objects is not less than the target number, multiple target live streaming objects are determined from the multiple second live streaming objects based on the capability information of the first live streaming object, the capability information of multiple second live streaming objects, and the object association information of multiple second live streaming objects.

[0111] In this embodiment of the disclosure, by determining a sufficient number of second live streaming objects, the server can determine a sufficient number of target live streaming objects based on capability information and object association information, thereby improving the success rate of matching other live streaming objects for the first live streaming object.

[0112] In some embodiments, the method further includes:

[0113] If the number of second live streaming objects is less than the target number, at least one second live streaming object will be identified as multiple target live streaming objects.

[0114] Based on the capability information of the first live streaming object, the capability information of at least one second live streaming object, and the object association information of at least one second live streaming object, at least one target live streaming object is determined from multiple fifth live streaming objects. The fifth live streaming object is the live streaming object whose object association information does not meet the conditions among multiple third live streaming objects.

[0115] In this embodiment of the disclosure, by determining at least one target live streaming object from a plurality of fifth live streaming objects, the number of target live streaming objects meets the matching requirements of the first live streaming object, thereby improving matching efficiency.

[0116] Figure 3 This is a flowchart illustrating another method for matching live streaming objects according to an exemplary embodiment, such as... Figure 3 As shown, this method is executed by the server and includes the following steps.

[0117] In step S301, in response to the matching request of the first live streaming object, the server obtains the capability information of the first live streaming object and multiple objects to be matched. The matching request is used to indicate the matching of other live streaming objects for joint live streaming for the first live streaming object. The capability information is used to indicate the live streaming results of the live streaming objects in joint live streaming within the historical time period.

[0118] In this embodiment, in response to a matching request from a first live streaming object, the server determines other live streaming objects that can be used for joint live streaming. The server can obtain the live streaming results of the first live streaming object's joint live streaming within a historical time period, and generate capability information for the first live streaming object based on multiple live streaming results within that historical time period; alternatively, the server can directly obtain the capability information of the first live streaming object. This embodiment does not limit the method of generating the capability information of the first live streaming object. The duration of the historical time period can be 30 days, 7 days, or 1 day, etc., and this embodiment does not impose any restrictions on this.

[0119] It should be noted that the results of a joint live stream are related to its objectives. If the objective of a joint live stream is to gain popularity, the result will be a popularity score; if the objective is to showcase talent, the result will be a talent score; and if the objective is to promote products, the result will be a promotional effect score.

[0120] In some embodiments, the capability information includes a capability mean and a capability standard deviation. The capability mean is the average of the live streaming results of multiple joint live streams conducted by the live streaming object within the historical time period, and the capability standard deviation is the standard deviation of the live streaming results of multiple joint live streams conducted by the live streaming object within the historical time period. Taking the generation of capability information for a first live streaming object by the server as an example: The server obtains the live streaming results of the first live streaming object's joint live streams within the historical time period. Based on the live streaming results of the joint live streams, the server determines the capability mean and capability standard deviation of the first live streaming object participating in joint live streams within the historical time period, and uses the capability mean and capability standard deviation as the capability information of the first live streaming object.

[0121] In step S302, the server obtains capability information for multiple objects to be matched.

[0122] In this embodiment, the method by which the server obtains the capability information of the object to be matched is similar to the method by which it obtains the first live streaming object, and will not be described again here. It should be noted that when the server obtains the capability information of the object to be matched, the historical time period selected may or may not be the same as the historical time period of the first live streaming object, and this embodiment does not impose any restrictions on this.

[0123] In step S303, for any object to be matched, the server determines the mean of matching capabilities and the standard deviation of matching capabilities based on the capability information of the first live streaming object and the capability information of the object to be matched. The mean of matching capabilities is used to indicate the difference between the mean of capabilities of the first live streaming object and the mean of capabilities of the object to be matched, and the standard deviation of matching capabilities is used to indicate the difference between the standard deviation of capabilities of the first live streaming object and the standard deviation of capabilities of the object to be matched.

[0124] In this embodiment of the disclosure, after the server obtains the capability information of the first live streaming object and the aforementioned object to be matched, it can compare the mean capability and standard deviation of the capability of the first live streaming object and the object to be matched, respectively, to determine the mean capability and standard deviation of the matching capability.

[0125] Assuming that the combined live stream results of the first live stream object and multiple objects to be matched within a historical time period all follow a normal distribution, then according to the properties of the normal distribution, the difference between two normal distributions also follows a normal distribution. That is, the difference in the combined live stream results of two live stream objects also follows a normal distribution. Therefore, for any object to be matched, if the combined live stream results can represent the object's capabilities, the difference between the mean capability of the first live stream object and the mean capability of the object to be matched can represent the mean of the difference between their capabilities. Similarly, the standard deviation of the capability of the first live stream object and the standard deviation of the capability of the object to be matched can represent the standard deviation of the difference between their capabilities.

[0126] For example, for any target object, the server obtains the mean capability of the first live stream object from the results of multiple joint live streams within a historical time period, with a capability standard deviation of σ1. The mean capability of the target object is μ2, with a capability standard deviation of σ2. Therefore, the server can obtain the mean matching capability of the first live stream object and the target object as μ1. d The standard deviation of the matching ability is σ. d , where μ d =|μ1-μ2|,

[0127] In step S304, if the ratio of the mean of matching ability to the standard deviation of matching ability is within the target difference range, the server determines the object to be matched as the third live streaming object.

[0128] In this embodiment, the target difference range is used to represent the difference interval from 0 to X. X is a set hyperparameter, and its value can be adjusted according to actual conditions; this embodiment does not impose any limitations on this. The server calculates the ratio of the mean matching ability of the first live stream object to the standard deviation of the matching ability of the objects to be matched. By comparing with X above, objects with a ratio less than X are identified as the third live streaming object, thus achieving the filtering of objects to be matched. It can be used to represent the capability gap between the first live streaming object and the object to be matched.

[0129] If the number of third live streaming objects determined by the server for the first live streaming object is insufficient to meet the requirements for joint live streaming (e.g., a total of 4 live streaming objects are required for joint live streaming, but only two third live streaming objects have been determined), then the server can re-determine the third live streaming objects for the first live streaming object.

[0130] In some embodiments, since multiple objects to be matched are updated over time, the server can determine a third live-streaming object for the first live-streaming object again after a preset time interval. Correspondingly, if the number of third live-streaming objects does not exceed a threshold, the server will re-determine multiple third live-streaming objects from the current multiple objects to be matched after a set time interval. This time interval can be 1 second, 2 seconds, or 3 seconds, etc., and this disclosure does not limit it. By determining the third live-streaming object from multiple objects to be matched again after a preset time interval, the methods for determining the third live-streaming object are increased, the probability of determining a sufficient number of third live-streaming objects is improved, and thus the matching efficiency is improved.

[0131] In some embodiments, when a target object is updated (e.g., a new live stream object joins the matching process or a target object withdraws from the matching process), the server re-determines multiple third-party live stream objects from the updated target objects. Correspondingly, if the number of third-party live stream objects does not exceed a threshold, the server determines multiple third-party live stream objects from the current target objects after a preset time interval. By determining third-party live stream objects from multiple target objects only when they are updated, the methods for determining third-party live stream objects are increased, improving the probability of determining a sufficient number of third-party live stream objects and thus improving matching efficiency.

[0132] In some embodiments, there are multiple target live streaming objects. The server can also set an upper limit for the matching wait time. Taking a first time as an example, the upper limit for the matching wait time can be 1 minute, 2 minutes, or 3 minutes, etc. Accordingly, if the matching wait time of the first live streaming object is not less than the first time and the number of third live streaming objects is greater than the number threshold, the server determines at least one target live streaming object from at least one second live streaming object based on the capability information of the first live streaming object, the capability information of at least one second live streaming object, and the object association information of at least one second live streaming object. See step S306 below. If the matching wait time of the first live streaming object is not less than the first time and the number of third live streaming objects is not greater than the number threshold, the server determines at least one fourth live streaming object from multiple objects to be matched. Multiple third live streaming objects and at least one fourth live streaming object are determined as multiple target live streaming objects. It should be noted that the server no longer executes steps S305 to S306 at this time. Wherein, the difference between the capability information of the fourth live streaming object and the capability information of the first live streaming object is outside the target difference range, that is, greater than the above-mentioned X. The sum of the number of at least one fourth live streaming object and multiple third live streaming objects is equal to the target number. The target number is equal to the number of live streaming objects required for joint live streaming minus one. When the matching wait time for the first live streaming object exceeds the upper limit, at least one fourth live streaming object is identified outside the target difference range. Multiple third live streaming objects within the target difference range and at least one fourth live streaming object outside the target difference range are returned to the first live streaming object. This ensures that the matching requirements of the first live streaming object are met while avoiding excessively long waiting times, thus improving the matching success rate.

[0133] In some embodiments, the server sets a lower limit for the matching wait time. When the matching wait time for the first live streaming object is greater than a second time but less than the first time, the server expands the target difference range to re-determine the third live streaming object within the target difference range. Correspondingly, if the number of determined third live streaming objects is not greater than a quantity threshold, the server can determine the matching wait time for the first live streaming object. If the matching wait time is not less than the second time, the target difference range is expanded. Then, based on the expanded target difference range, the server re-determines multiple third live streaming objects from the multiple objects to be matched. The quantity threshold is the number of objects required for the first live streaming object to perform joint live streaming. The second time can be 30 seconds, 45 seconds, or 1 minute, etc., and this embodiment does not limit this. It should be noted that the server can expand the target difference range by increasing the value of the hyperparameter X, and the server can adjust X multiple times. This embodiment does not limit the size of each adjustment. By expanding the target difference range when a sufficient number of third live streaming objects are not determined, the number of determined third live streaming objects can be increased, thereby reducing the waiting time for the first live streaming object and improving matching efficiency.

[0134] It should be noted that the at least one fourth live streaming object can be randomly selected by the server from multiple objects to be matched, or the server can select at least one object to be matched that has the smallest difference in capability information from the first live streaming object as the at least one fourth live streaming object.

[0135] In step S305, the server determines at least one second live streaming object from multiple third live streaming objects whose object association information meets the conditions. The object association information includes at least one of the following: similarity information between the first live streaming object, social relationship information, and historical joint live streaming information. The historical joint live streaming information is used to represent the live streaming results of joint live streaming with the first live streaming object within a historical time period.

[0136] In this embodiment, for any third live streaming object, if the object association information of the third live streaming object meets the conditions, then the third live streaming object is determined as the second live streaming object. Specifically, when the object association information is similarity information with the first live streaming object, the second live streaming object and the first live streaming object have similar object attributes; this embodiment does not limit the object attributes. When the object association information is social relationship information with the first live streaming object, the second live streaming object and the first live streaming object have a social relationship, such as a friend relationship, a follow relationship, or shared friends; this embodiment does not limit the social relationship. When the object association information is historical joint live streaming information with the first live streaming object, the second live streaming object and the first live streaming object have conducted joint live streaming within a historical time period. The server can filter third live streaming objects from at least one dimension: similar object attributes with the first live streaming object, social relationships, and joint live streaming within a historical time period, so that the filtered second live streaming objects have a high degree of object association with the first live streaming object.

[0137] In step S306, the server determines at least one target live streaming object from at least one second live streaming object based on the capability information of the first live streaming object, the capability information of at least one second live streaming object, and the object association information of at least one second live streaming object.

[0138] In this embodiment of the disclosure, after determining multiple second live streaming objects, the server can determine the capability differences between the first live streaming object and each of the second live streaming objects based on the capability information of the first live streaming object and the capability information of at least one second live streaming object. Based on the object association information of at least one second live streaming object, the server can determine the differences in the degree of association between each second live streaming object and the first live streaming object. Accordingly, the server can use three different methods to determine the target live streaming object.

[0139] In Method 1, the server filters target live stream objects based on the differences between the capability information of at least one second live stream object and the capability information of the first live stream object. Accordingly, if the number of at least one second live stream object is not less than a target number, the server can determine a target number of target live stream objects from among the at least one second live stream object whose capability information differs smallest from that of the first live stream object. The target number is one less than the number of live stream objects required for joint live streaming. Directly determining target live stream objects based on differences in capability information improves the efficiency of target live stream object determination, thereby improving the efficiency of matching other live stream objects to the first live stream object.

[0140] Method Two: The server determines the object score of at least one second live-streaming object based on the capability information of the first live-streaming object, the capability information of at least one second live-streaming object, and the object association information of at least one second live-streaming object. Based on the object score, the server determines the target live-streaming object. Accordingly, if the number of second live-streaming objects is not less than the target number, for any second live-streaming object, the server determines the object association score of the second live-streaming object based on its object association information. The server determines the object capability score of the second live-streaming object based on the difference between the capability information of the second live-streaming object and the capability information of the first live-streaming object. The server weights the object association score and the object capability score to obtain the object score of the second live-streaming object. Based on the object score of at least one second live-streaming object, the server determines the target number of target live-streaming objects from the at least one second live-streaming object. The object score of this target live-streaming object is greater than the object score of any non-target live-streaming object among the at least one second live-streaming object. It should be noted that this disclosure does not restrict the weighting of the two scores. By determining the target live-streaming object based on the object score of the second live-streaming object, the influence of the degree of association and capability differences between live-streaming objects on the first live-streaming object is considered simultaneously. This results in the determined target live-streaming objects having smaller capability differences and a certain degree of association with the first live-streaming object, making them suitable for joint live-streaming with the first live-streaming object.

[0141] In some embodiments, the association information includes at least one of similarity information, social relationship information, and historical joint live streaming information. Different types of association information have different weights, and the similarity information, social relationship information, and historical joint live streaming information of different second live streaming objects are not entirely the same as those of the first live streaming object. Accordingly, the server can determine at least two of the similarity score, social relationship score, and historical joint live streaming score of the second live streaming object based on its object association information. Then, the server performs a weighted summation of at least two of the similarity score, social relationship score, and historical joint live streaming score of the second live streaming object to obtain its object association score. It should be noted that when the association information is any one of similarity information, social relationship information, or historical joint live streaming information, a weighted summation step is not required; the server can directly use the similarity score, social relationship score, or historical joint live streaming score as the object association score of the second live streaming object. By weighting the summation of scores for different types of association information, different types of association information between live streaming objects have different impacts on the degree of association between them, thus allowing the object association score to more accurately reflect the degree of association between live streaming objects.

[0142] For example, the object association information includes the age difference between the live streaming objects, whether they live in the same city, the number of mutual friends, whether they have a friend relationship, and the result of at least one joint live streaming session in the past. The size of the age difference affects the similarity score. For instance, if other similarity information is the same, the similarity score between the second live streaming object and the first live streaming object is greater if the age difference is within one year, than if the age difference is between one and two years. The same applies to social relationship scores and historical joint live streaming scores; this disclosure does not impose limitations on these aspects.

[0143] Method 3: If the number of second live-streaming objects determined by the server for the first live-streaming object does not meet the matching requirements of the first live-streaming object, the server can determine at least one more target live-streaming object for the first live-streaming object. Correspondingly, if the number of second live-streaming objects is less than the target number, the server can determine at least one second live-streaming object as multiple target live-streaming objects; then, based on the capability information of the first live-streaming object, the capability information of at least one second live-streaming object, and the object association information of at least one second live-streaming object, at least one target live-streaming object is determined from multiple fifth live-streaming objects. The multiple target live-streaming objects ultimately determined by the server include all second live-streaming objects and some fifth live-streaming objects. These fifth live-streaming objects are those whose object association information among the multiple third live-streaming objects does not meet the conditions. By determining target live-streaming objects from multiple fifth live-streaming objects, the number of target live-streaming objects meets the matching requirements of the first live-streaming object, improving matching efficiency.

[0144] For example, Figure 4 This is a schematic diagram illustrating the determination of a target live streaming object according to an exemplary embodiment. For at least one second live streaming object whose object association information satisfies a certain condition: If the number of at least one second live streaming object is not less than a target number, the terminal can perform a forward sorting of the at least one second live streaming object based on the difference in capability information between the second live streaming object and the first live streaming object, placing the second live streaming object with the smaller difference in capability information with the first live streaming object at the top. Then, the terminal obtains the target number of second live streaming objects ranked at the top as the target live streaming object. If the number of at least one second live streaming object is less than the target number, the terminal, based on the forward sorting of the at least one second live streaming object, performs a forward sorting of multiple fifth live streaming objects, thus placing the fifth live streaming object with the smaller difference in capability information with the first live streaming object at the top. Then, the terminal obtains all the second live streaming objects as the target live streaming object, and then obtains the at least one fifth live streaming object ranked at the top as the target live streaming object.

[0145] In step S307, the server returns at least one target live streaming object to the first live streaming object, so that the first live streaming object and at least one target live streaming object can perform joint live streaming.

[0146] In this embodiment of the disclosure, after determining at least one target live streaming object, the server can match the at least one target live streaming object with a first live streaming object, so that the first live streaming object can perform joint live streaming with the at least one target live streaming object.

[0147] It should be noted that the first live streaming object in this application embodiment can represent a single live streaming object or a group of live streaming objects. A group of live streaming objects includes two or more live streaming objects. When the first live streaming object represents a group of live streaming objects, it means that the group of live streaming objects, as a whole, is jointly broadcast with other groups of live streaming objects. Therefore, the capability information of the first live streaming object represents the weighted result of the capability information of multiple live streaming objects within that group.

[0148] It should be noted that when determining the target live streaming object, the server can also directly base its determination on the capability information of the first live streaming object and the capability information of at least one second live streaming object. See also Figure 5 As shown, Figure 5 This is a flowchart illustrating another method for matching live streaming objects according to an exemplary embodiment. For example... Figure 5 As shown, the process includes the following steps: 501. The first live streaming object sends a matching request through a terminal. 502. The server determines multiple objects to be matched. 503. Based on the capability information of the first live streaming object and the capability information of the multiple objects to be matched, the server determines multiple third live streaming objects. 504. From these multiple third live streaming objects, the server determines at least one second live streaming object whose object association information meets the conditions, and sorts the at least one second live streaming object according to the difference between its capability information and that of the first live streaming object. 505. The server returns the target number of second live streaming objects ranked first to the first live streaming object as target live streaming objects, so that the first live streaming object and the at least one target live streaming object can perform joint live streaming.

[0149] It should be noted that, since this disclosure proposes multiple methods to implement the live streaming object matching method, in order to make the above steps S301 to S307 easier to understand, Figure 6 This is an overall flowchart illustrating a process for matching a target live streaming object to a first live streaming object, according to an exemplary embodiment. Figure 6As shown, the process includes the following steps: 601. The server determines multiple third live streaming objects within the target difference range from multiple objects to be matched, based on capability information. 602. The server determines whether the number of third live streaming objects is greater than a quantity threshold. 603. The server determines whether the matching waiting time for the first live streaming object is less than a first duration. 604. If the number of third live streaming objects is not greater than the quantity threshold and the matching waiting time for the first live streaming object is not less than the first duration, the server determines at least one fourth live streaming object whose capability information is outside the target difference range. 605. The server determines the multiple third live streaming objects and at least one fourth live streaming object as the target live streaming object. If the number of third live streaming objects is not greater than the quantity threshold, multiple third live streaming objects are determined again through steps 606, 607, or 608. 606. The server determines multiple third live streaming objects again by expanding the target difference range. 607. After a preset time interval, the server determines multiple third live streaming objects from the current objects to be matched. 608. When the objects to be matched are updated, the server re-determines multiple third live streaming objects from the updated objects to be matched. 609. If the number of third live-streaming objects exceeds a threshold, or if multiple third live-streaming objects were identified in steps 606, 607, or 608, the server determines at least one second live-streaming object from among the multiple third live-streaming objects that meets the object association conditions. 610. The server determines whether the number of second live-streaming objects is less than the target number. 611. If the number of second live-streaming objects is less than the target number, the server determines multiple fifth live-streaming objects from among the multiple third live-streaming objects whose object association information does not meet the conditions. 612. The server identifies at least one second live-streaming object and multiple fifth live-streaming objects as target live-streaming objects. 613. If the number of second live-streaming objects is not less than the target number, the server determines a target number of target live-streaming objects from among at least one second live-streaming object whose capability information differs least from that of the first live-streaming object. 614. If the number of second live-streaming objects is not less than the target number, the server may also determine a target number of target live-streaming objects from among at least one second live-streaming object based on the object score of at least one second live-streaming object.

[0150] This disclosure provides a method for matching live streaming objects. Based on the capability information of a first live streaming object, it can identify multiple third live streaming objects whose capability information differences are within a target difference range from multiple objects to be matched. This reduces the capability differences between other objects matched for the first live streaming object and the first live streaming object. Then, by using at least one of similarity information, social relationship information, and historical joint live streaming information with the first live streaming object, it further filters out at least one second live streaming object that meets the conditions, improving the object association between other objects matched for the first live streaming object and the first live streaming object. Finally, based on the capability information and object association information of the live streaming object, it determines at least one target live streaming object to ultimately conduct joint live streaming with the first live streaming object. This ensures that the capability difference between the at least one target live streaming object and the first live streaming object is small and that they have a certain association, making them suitable for joint live streaming with the first live streaming object, thus improving the effectiveness of the matching and achieving better matching results.

[0151] Figure 7 This is a block diagram illustrating a live streaming object matching device according to an exemplary embodiment. (Refer to...) Figure 7 The device includes a first determining unit 701, a second determining unit 702, and an object returning unit 703.

[0152] The first determining unit 701 is configured to determine at least one second live streaming object whose object association information meets the conditions from a plurality of objects to be matched. The matching request is used to indicate that other live streaming objects are matched for joint live streaming for the first live streaming object. The object association information includes at least one of similarity information between the first live streaming object, social relationship information, and historical joint live streaming information. The historical joint live streaming information is used to indicate the live streaming results of joint live streaming with the first live streaming object within a historical time period.

[0153] The second determining unit 702 is configured to, when the matching waiting time of the first live streaming object is less than the first time, determine at least one target live streaming object from at least one second live streaming object based on the capability information of the first live streaming object, the capability information of at least one second live streaming object, and the object association information of at least one second live streaming object. The capability information is used to represent the live streaming result of the live streaming object performing joint live streaming within the historical time period.

[0154] The object return unit 703 is configured to return at least one target live streaming object to the first live streaming object so that the first live streaming object and at least one target live streaming object can perform joint live streaming.

[0155] In some embodiments, Figure 8 This is a block diagram illustrating another live streaming object matching device according to an exemplary embodiment, see [link to example diagram]. Figure 8 As shown, the first determining unit 701 includes:

[0156] The first determining subunit 7011 is configured to, in response to a matching request from a first live object, determine a plurality of third live objects from a plurality of objects to be matched based on the capability information of the first live object, wherein the difference between the capability information of the third live object and the capability information of the first live object is within a target difference range.

[0157] The second determining subunit 7012 is configured to determine at least one second live object whose object association information satisfies the conditions from multiple third live objects when the number of third live objects is greater than a number threshold.

[0158] In some embodiments, the capability information includes a capability mean and a capability standard deviation; a first determining subunit 7011 is configured to, for any object to be matched, acquire the capability information of the object to be matched; based on the capability information of the first live streaming object and the capability information of the object to be matched, determine a matching capability mean and a matching capability standard deviation, wherein the matching capability mean is used to indicate the difference between the capability mean of the first live streaming object and the capability mean of the object to be matched, and the matching capability standard deviation is used to indicate the difference between the capability standard deviation of the first live streaming object and the capability standard deviation of the object to be matched; if the ratio of the matching capability mean and the matching capability standard deviation is within a target difference range, the object to be matched is determined as a third live streaming object.

[0159] In some embodiments, see Figure 8 As shown, the device also includes:

[0160] The range expansion unit 704 is configured to expand the target difference range when the number of third live objects is not greater than the number threshold.

[0161] The third determining unit 705 is configured to re-determine multiple third live objects from multiple objects to be matched based on the expanded target difference range;

[0162] The first determining unit 701 is further configured to determine, from a plurality of third live objects, at least one second live object whose object association information satisfies the conditions.

[0163] In some embodiments, the multiple objects to be matched are updated over time; the first determining unit 701 is further configured to determine multiple third live objects from the current multiple objects to be matched after a preset time interval, provided that the number of third live objects is not greater than a number threshold; and to determine at least one second live object from the multiple third live objects whose object association information satisfies the conditions.

[0164] In some embodiments, the multiple objects to be matched are updated over time; the first determining unit 701 is further configured to, in the event that the multiple objects to be matched are updated, re-determine multiple third live objects from the updated multiple objects to be matched; and determine at least one second live object from the multiple third live objects whose object association information satisfies the conditions.

[0165] In some embodiments, the second determining unit 702 is further configured to determine at least one target live streaming object from at least one second live streaming object based on the capability information of the first live streaming object, the capability information of at least one second live streaming object, and the object association information of at least one second live streaming object, when the matching waiting time of the first live streaming object is not less than the first time and the number of third live streaming objects is greater than the number threshold.

[0166] In some embodiments, see Figure 8 As shown, the device also includes:

[0167] The object determination unit 707 is configured to determine at least one fourth live object from multiple objects to be matched, provided that the matching waiting time of the first live object is not less than the first duration and the number of the third live objects is not greater than the number threshold. The second duration is greater than the first duration, and the difference between the capability information of the fourth live object and the capability information of the first live object is outside the target difference range.

[0168] The second determining unit 702 is further configured to determine a plurality of third live streaming objects and at least one fourth live streaming object as a plurality of target live streaming objects.

[0169] In some embodiments, see Figure 8 As shown, the second determining unit 702 includes:

[0170] The associated molecular unit 7021 is configured to determine the object association score of the second live object based on the object association information of the second live object for any second live object.

[0171] Capability unit 7022 is configured to determine the object capability score of the second live object based on the difference between the capability information of the second live object and the capability information of the first live object.

[0172] The object's molecular unit 7023 is configured to weight the object's association score and object's capability score to obtain the object score of the second live object;

[0173] The object determination subunit 7024 is configured to determine at least one target live object from at least one second live object based on the object score of at least one second live object.

[0174] In some embodiments, the associated molecule 7021 is configured to determine at least two of the similarity score, social relationship score, and historical joint live broadcast score of the second live broadcast object based on the object association information of the second live broadcast object; and to perform a weighted summation of at least two of the similarity score, social relationship score, and historical joint live broadcast score of the second live broadcast object to obtain the object association score of the second live broadcast object.

[0175] In some embodiments, there are multiple target live streaming objects. The first determining unit 701 is further configured to determine multiple target live streaming objects from the multiple second live streaming objects based on the capability information of the first live streaming object, the capability information of the multiple second live streaming objects, and the object association information of the multiple second live streaming objects, when the number of second live streaming objects is not less than the target number.

[0176] In some embodiments, the second determining unit 702 is further configured to determine at least one second live streaming object as multiple target live streaming objects when the number of multiple second live streaming objects is less than the target number; and to determine at least one target live streaming object from multiple fifth live streaming objects based on the capability information of the first live streaming object, the capability information of at least one second live streaming object, and the object association information of at least one second live streaming object, wherein the fifth live streaming object is a live streaming object whose object association information does not meet the conditions among multiple third live streaming objects.

[0177] This disclosure provides a live streaming object matching device. By filtering at least one of the following: similarity information, social relationship information, and historical joint live streaming information between the first live streaming object and the first live streaming object, at least one second live streaming object that meets the conditions can be selected. This can improve the object association degree between other objects matched for the first live streaming object and the first live streaming object. Finally, based on the ability information and object association information of the live streaming object, at least one target live streaming object that will eventually conduct joint live streaming with the first live streaming object is determined. This ensures that the ability difference between the at least one target live streaming object and the first live streaming object is small and that they are related to each other, making them suitable for joint live streaming with the first live streaming object. This improves the effectiveness of the matching and results in a better matching effect.

[0178] Figure 9 This is a block diagram illustrating an electronic device 900 according to an exemplary embodiment. Typically, the electronic device 900 includes a processor 901 and a memory 902.

[0179] Processor 901 may include one or more processing cores, such as a quad-core processor or an octa-core processor. Processor 901 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 901 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 901 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 901 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0180] The memory 902 may include one or more computer-readable storage media, which may be non-transitory. The memory 902 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 902 are used to store at least one program code, which is executed by the processor 901 to implement the live object matching method provided in the method embodiments of this disclosure.

[0181] In some embodiments, the electronic device 900 may optionally include a peripheral device interface 903 and at least one peripheral device. The processor 901, memory 902, and peripheral device interface 903 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 903 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: a radio frequency circuit 904, a display screen 905, a camera assembly 906, an audio circuit 907, and a power supply 908.

[0182] Peripheral device interface 903 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 901 and memory 902. In some embodiments, processor 901, memory 902 and peripheral device interface 903 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 901, memory 902 and peripheral device interface 903 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0183] The radio frequency (RF) circuit 904 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 904 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 904 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 904 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 904 can communicate with other electronic devices through at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: metropolitan area networks (MANs), various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks (WLANs), and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 904 may also include circuitry related to NFC (Near Field Communication), which is not limited in this disclosure.

[0184] Display screen 905 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 905 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 901 for processing. In this case, display screen 905 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 905, which serves as the front panel of electronic device 900; in other embodiments, there may be at least two display screens 905, respectively disposed on different surfaces of electronic device 900 or in a folded design; in still other embodiments, display screen 905 may be a flexible display screen, disposed on a curved or folded surface of electronic device 900. Furthermore, display screen 905 may be configured as a non-rectangular irregular shape, i.e., a non-rectangular screen. Display screen 905 may be made of materials such as LCD (Liquid Crystal Display) or OLED (Organic Light-Emitting Diode).

[0185] The camera assembly 906 is used to acquire images or videos. Optionally, the camera assembly 906 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the electronic device, and the rear-facing camera is located on the back of the electronic device. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 906 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm-light flash and a cool-light flash, which can be used for light compensation at different color temperatures.

[0186] The audio circuit 907 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting the sound waves into electrical signals that are input to the processor 901 for processing, or input to the radio frequency circuit 904 for voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each located in a different part of the electronic device 900. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert the electrical signals from the processor 901 or the radio frequency circuit 904 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 907 may also include a headphone jack.

[0187] Power supply 908 is used to supply power to the various components in electronic device 900. Power supply 908 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 908 includes a rechargeable battery, the rechargeable battery can support wired or wireless charging. The rechargeable battery can also be used to support fast charging technology.

[0188] Those skilled in the art will understand that Figure 9 The structure shown does not constitute a limitation on the electronic device 900, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0189] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 902 including instructions, which can be executed by a processor 901 of a terminal 900 to complete the live streaming object matching method. Optionally, the computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, or optical data storage device, etc.

[0190] In an exemplary embodiment, a computer program product is also provided, including a computer program that, when executed by a processor, implements the above-described live streaming object matching method.

[0191] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0192] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for matching live streaming objects, characterized in that, The method includes: In response to a matching request from a first live streaming object, multiple third live streaming objects are determined from a plurality of objects to be matched based on the capability information of the first live streaming object. The difference between the capability information of the third live streaming object and the capability information of the first live streaming object is within a target difference range. The plurality of objects to be matched are updated over time. The matching request is used to indicate that other live streaming objects for joint live streaming are matched for the first live streaming object. The capability information is used to represent the live streaming results of joint live streaming of the live streaming objects within a historical time period. If the number of third live streaming objects is not greater than a number threshold: determine the matching waiting time of the first live streaming object; if the matching waiting time is greater than a second time but less than a first time, expand the target difference range, and based on the expanded target difference range, re-determine multiple third live streaming objects from multiple objects to be matched; if the matching waiting time is not less than the first time, determine at least one fourth live streaming object from multiple objects to be matched, and determine the multiple third live streaming objects and the at least one fourth live streaming object as multiple target live streaming objects, wherein the difference between the capability information of the fourth live streaming object and the capability information of the first live streaming object is outside the target difference range; and, after a preset time interval, re-determine multiple third live streaming objects from the current multiple objects to be matched. If the number of current third-party live streaming objects exceeds a threshold: At least one second-party live streaming object whose object association information satisfies the conditions is determined from the current third-party live streaming objects. The object association information includes at least one of the following: similar object attribute information, social relationship information, and historical joint live streaming information with the first live streaming object. The historical joint live streaming information represents the live streaming results of joint live streaming with the first live streaming object within the historical time period. If the number of second-party live streaming objects is not less than the target number, at least one target live streaming object is determined from the at least one second-party live streaming object based on the capability information of the first live streaming object, the capability information of the at least one second-party live streaming object, and the object association information of the at least one second-party live streaming object. If the number of second-party live streaming objects is less than the target number, multiple fifth-party live streaming objects whose object association information does not satisfy the conditions are determined from the current third-party live streaming objects, and the at least one second-party live streaming object and the multiple fifth-party live streaming objects are determined as target live streaming objects. At least one target live streaming object is returned to the first live streaming object so that the first live streaming object and the returned at least one target live streaming object can perform joint live streaming.

2. The live streaming object matching method according to claim 1, characterized in that, The capability information includes the capability mean and capability standard deviation; The step of determining multiple third live streaming objects from multiple objects to be matched based on the capability information of the first live streaming object includes: For any object to be matched, obtain the capability information of the object to be matched; Based on the capability information of the first live streaming object and the capability information of the object to be matched, a matching capability mean and a matching capability standard deviation are determined. The matching capability mean is used to indicate the difference between the capability mean of the first live streaming object and the capability mean of the object to be matched, and the matching capability standard deviation is used to indicate the difference between the capability standard deviation of the first live streaming object and the capability standard deviation of the object to be matched. If the ratio of the mean of the matching ability to the standard deviation of the matching ability is within the target difference range, the object to be matched is determined as the third live streaming object.

3. The live streaming object matching method according to claim 1, characterized in that, The method further includes: If the multiple objects to be matched are updated, multiple third live streaming objects are re-determined from the updated multiple objects to be matched; From the plurality of third live streaming objects, determine at least one second live streaming object whose object association information satisfies the conditions.

4. The live streaming object matching method according to claim 1, characterized in that, The method further includes: If the matching waiting time of the first live streaming object is not less than the first duration and the number of the third live streaming objects is greater than the number threshold, at least one target live streaming object is determined from the at least one second live streaming object based on the capability information of the first live streaming object, the capability information of the at least one second live streaming object, and the object association information of the at least one second live streaming object.

5. The live streaming object matching method according to claim 1, characterized in that, The step of determining at least one target live stream object from the at least one second live stream object based on the capability information of the first live stream object, the capability information of the at least one second live stream object, and the object association information of the at least one second live stream object includes: For any second live streaming object, determine the object association score of the second live streaming object based on the object association information of the second live streaming object; Based on the difference between the capability information of the second live streaming object and the capability information of the first live streaming object, the object capability score of the second live streaming object is determined; The object score of the second live streaming object is obtained by weighting the object association score and the object capability score. Based on the object score of the at least one second live streaming object, the at least one target live streaming object is determined from the at least one second live streaming object.

6. The live streaming object matching method according to claim 5, characterized in that, The step of determining the object association score of the second live streaming object based on the object association information of the second live streaming object includes: Based on the object association information of the second live streaming object, at least two of the following are determined: the similar object attribute score, the social relationship score, and the historical joint live streaming score of the second live streaming object. The object association score of the second live streaming object is obtained by weighted summing of at least two of the similarity attribute score, social relationship score, and historical joint live streaming score.

7. The live streaming object matching method according to claim 1, characterized in that, The target live streaming objects are multiple. The step of determining at least one target live streaming object from the at least one second live streaming object based on the capability information of the first live streaming object, the capability information of the at least one second live streaming object, and the object association information of the at least one second live streaming object includes: If the number of second live streaming objects is not less than the target number, multiple target live streaming objects are determined from the multiple second live streaming objects based on the capability information of the first live streaming object, the capability information of multiple second live streaming objects, and the object association information of the multiple second live streaming objects.

8. The live streaming object matching method according to claim 7, characterized in that, The method further includes: If the number of second live streaming objects is less than the target number, the at least one second live streaming object is determined as the target live streaming object; Based on the capability information of the first live streaming object, the capability information of the at least one second live streaming object, and the object association information of the at least one second live streaming object, at least one target live streaming object is determined from the plurality of fifth live streaming objects.

9. A matching device for live streaming objects, characterized in that, include: The first determining unit is configured as follows: In response to a matching request from a first live streaming object, multiple third live streaming objects are determined from a plurality of objects to be matched based on the capability information of the first live streaming object. The difference between the capability information of the third live streaming object and the capability information of the first live streaming object is within a target difference range. The plurality of objects to be matched are updated over time. The matching request is used to indicate that other live streaming objects for joint live streaming are matched for the first live streaming object. The capability information is used to represent the live streaming results of joint live streaming of the live streaming objects within a historical time period. If the number of the third live streaming object is not greater than the number threshold: determine the matching waiting time of the first live streaming object; If the matching waiting time is greater than the second time but less than the first time, the target difference range is expanded, and based on the expanded target difference range, multiple third live streaming objects are re-determined from multiple objects to be matched. If the matching waiting time is not less than the first time, at least one fourth live streaming object is determined from multiple objects to be matched, and the multiple third live streaming objects and the at least one fourth live streaming object are determined as multiple target live streaming objects. The difference between the capability information of the fourth live streaming object and the capability information of the first live streaming object is outside the target difference range. In addition, after a preset time interval, multiple third-party live streaming objects are re-determined from the current multiple objects to be matched; When the number of current third live streaming objects exceeds a threshold: determine at least one second live streaming object whose object association information meets the conditions from the current third live streaming objects. The object association information includes at least one of similar object attribute information, social relationship information, and historical joint live streaming information with the first live streaming object. The historical joint live streaming information is used to represent the live streaming results of joint live streaming with the first live streaming object within the historical time period. The second determining unit is configured to, when the number of the second live streaming objects is not less than the target number, determine at least one target live streaming object from the at least one second live streaming object based on the capability information of the first live streaming object, the capability information of the at least one second live streaming object, and the object association information of the at least one second live streaming object; and when the number of the second live streaming objects is less than the target number, determine a plurality of fifth live streaming objects from the current plurality of third live streaming objects whose object association information does not meet the conditions, and determine the at least one second live streaming object and the plurality of fifth live streaming objects as target live streaming objects. The object return unit is configured to return at least one target live streaming object to the first live streaming object, so that the first live streaming object and the returned at least one target live streaming object can perform joint live streaming.

10. An electronic device, characterized in that, The electronic device includes: One or more processors; Memory used to store the executable program code of the processor; The processor is configured to execute the program code to implement the live object matching method as described in any one of claims 1 to 8.

11. A computer-readable storage medium, wherein instructions in the computer-readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform a live object matching method as described in any one of claims 1 to 8.

Images