Information processing method and device, electronic equipment, medium and program product

Abstract

The present disclosure relates to an information processing method and device, electronic equipment, medium and program product, applied to the live broadcast technical field, the method comprises the following steps: receiving the live room information, anchor information and reporting resource transfer information of a target live room input through an information input interface; determining first estimated resource transfer information according to the anchor information; determining second estimated resource transfer information according to the live room information; determining the accuracy of the reporting resource transfer information of the target live room according to the first estimated resource transfer information, the second estimated resource transfer information and the reporting resource transfer information. The present disclosure can predict the resource transfer information before the live broadcast starts or during the live broadcast, and can improve the accuracy of resource transfer information prediction.

Description

Technical Field

[0001] This disclosure relates to the field of live streaming technology, and in particular to an information processing method, apparatus, electronic device, medium, and program product. Background Technology

[0002] Currently, the estimation of resource transfer information for a single live broadcast room mainly comes from the self-reporting of resource providers, and there is still a lack of effective prediction for the reported resource transfer information. Summary of the Invention

[0003] In order to solve the above-mentioned technical problems, or at least partially solve the above-mentioned technical problems, this disclosure provides an information processing method, apparatus, electronic device, medium and program product.

[0004] According to a first aspect of this disclosure, an information processing method is provided, comprising:

[0005] Receive the target live stream room information, the streamer information, and the resource transfer request information input through the information input interface;

[0006] Based on the broadcaster information, determine the first estimated resource transfer information;

[0007] The second estimated resource transfer information is determined based on the live stream information;

[0008] Based on the first estimated resource transfer information, the second estimated resource transfer information, and the reported resource transfer information, the accuracy of the reported resource transfer information for the target live streaming room is determined.

[0009] Optionally, determining the first estimated resource transfer information based on the broadcaster information includes:

[0010] Based on the streamer information, obtain the target historical resource transfer information corresponding to the streamer;

[0011] Based on the broadcaster information, obtain the target resource transfer information corresponding to the broadcaster;

[0012] The first estimated resource transfer information is determined based on the target's historical resource transfer information and / or the target's reported resource transfer information.

[0013] Optionally, obtaining the target historical resource transfer information corresponding to the streamer based on the streamer information includes:

[0014] Based on the broadcaster information, obtain the broadcaster's first historical resource transfer information;

[0015] Based on the anchor information, obtain the second historical resource transfer information of the first similar anchor of the anchor;

[0016] The target historical resource transfer information is determined based on the first historical resource transfer information and / or the second historical resource transfer information;

[0017] The step of obtaining the target resource transfer information corresponding to the broadcaster based on the broadcaster information includes:

[0018] Based on the anchor information, obtain the resource transfer information of the second similar anchor of the anchor;

[0019] Based on the resource transfer information submitted by the second similar broadcaster, the target resource transfer information is determined.

[0020] Optionally, obtaining the first historical resource transfer information of the broadcaster based on the broadcaster information includes:

[0021] Based on the broadcaster information, obtain multiple historical resource transfer information of the broadcaster within a first preset historical time period;

[0022] The N1 historical resource transfer information that meet the preset filtering conditions are determined as the first historical resource transfer information of the broadcaster;

[0023] The step of obtaining the second historical resource transfer information of the first similar streamer based on the streamer information includes:

[0024] The M1 streamers with the highest similarity to the streamer among all streamers who meet the first preset condition are identified as the first similar streamers;

[0025] Obtain historical resource transfer information for each of the first similar broadcasters within a second preset historical time period;

[0026] The N2 historical resource transfer information that meet the preset screening conditions are determined as the second historical resource transfer information of the first similar anchor;

[0027] The step of obtaining resource transfer information for a second similar streamer based on the streamer information includes:

[0028] The M2 streamers who are most similar to the streamer among all streamers who meet the second preset condition are selected as the second similar streamers;

[0029] Obtain the resource transfer information submitted by the second similar streamer;

[0030] Where N1, N2, M1, and M2 are all positive integers.

[0031] Optionally, determining the accuracy of the reported resource transfer information of the target live streaming room based on the first estimated resource transfer information, the second estimated resource transfer information, and the reported resource transfer information of the target live streaming room includes:

[0032] The first relationship data is determined based on the first historical resource transfer information and the resource transfer information submitted by the target live streaming room;

[0033] The second relationship data is determined based on the second historical resource transfer information and the resource transfer information submitted by the target live streaming room;

[0034] The third relationship data is determined based on the target resource transfer information and the target live streaming room's reported resource transfer information;

[0035] The fourth relationship data is determined based on the second estimated resource transfer information and the resource transfer information submitted by the target live streaming room;

[0036] Based on at least one of the first relationship data, the second relationship data, and the third relationship data, and the fourth relationship data, the accuracy of the resource transfer information submitted by the target live streaming room is determined using a target accuracy evaluation model.

[0037] Optionally, based on at least one of the first relationship data, the second relationship data, and the third relationship data, and the fourth relationship data, the accuracy of the reported resource transfer information of the target live streaming room is determined using a target accuracy evaluation model, including:

[0038] The first estimated accuracy is determined based on the first relationship data, at least one first hyperparameter of the target accuracy evaluation model, and the first preset judgment condition.

[0039] The second estimated accuracy is determined based on the second relationship data, at least one second hyperparameter of the target accuracy evaluation model, and the second preset judgment condition.

[0040] The third estimated accuracy is determined based on the third relationship data, at least one third hyperparameter of the target accuracy evaluation model, and the third preset judgment condition.

[0041] The fourth estimated accuracy is determined based on the fourth relationship data, at least one fourth hyperparameter of the target accuracy evaluation model, and the fourth preset judgment condition.

[0042] Based on at least one of the first estimated accuracy, the second estimated accuracy, and the third estimated accuracy, and the fourth estimated accuracy, the accuracy of the resource transfer information reported by the target live streaming room is determined using a preset comprehensive discrimination matrix of the target accuracy evaluation model.

[0043] Optionally, the information processing method further includes:

[0044] An improved genetic algorithm is obtained by modifying the genetic algorithm based on the alarm rate penalty function;

[0045] The hyperparameters of the initial accuracy evaluation model were tuned using the improved genetic algorithm to obtain the optimized target accuracy evaluation model.

[0046] Optionally, the second estimated resource transfer information is determined based on the live stream information, including:

[0047] Based on the live room identifier, obtain multiple historical resource transfer information of the live room corresponding to the live room identifier within a third preset historical time period;

[0048] The second estimated resource transfer information is determined based on multiple historical resource transfer information within a third preset historical time period.

[0049] According to a second aspect of this disclosure, an information processing apparatus is provided, comprising:

[0050] The live stream information receiving module is used to receive the target live stream information, the host information, and the resource transfer information submitted through the information input interface.

[0051] The first estimated resource transfer information determination module is used to determine the first estimated resource transfer information based on the broadcaster information.

[0052] The second estimated resource transfer information determination module is used to determine the second estimated resource transfer information based on the live broadcast room information;

[0053] An accuracy determination module is used to determine the accuracy of the reported resource transfer information of the target live streaming room based on the first estimated resource transfer information, the second estimated resource transfer information, and the reported resource transfer information.

[0054] Optionally, the first estimated resource transfer information determination module includes:

[0055] The target historical resource transfer information acquisition unit is used to acquire the target historical resource transfer information corresponding to the broadcaster based on the broadcaster information.

[0056] The target resource transfer information acquisition unit is used to acquire the target resource transfer information corresponding to the broadcaster based on the broadcaster information.

[0057] The first estimated resource transfer information determination unit is used to determine the first estimated resource transfer information based on the target's historical resource transfer information and / or the target's reported resource transfer information.

[0058] Optionally, the target historical resource transfer information acquisition unit is specifically used to acquire the first historical resource transfer information of the broadcaster based on the broadcaster information; acquire the second historical resource transfer information of the first similar broadcaster based on the broadcaster information; and determine the target historical resource transfer information based on the first historical resource transfer information and / or the second historical resource transfer information.

[0059] The target resource transfer information acquisition unit is specifically used to acquire the resource transfer information of the second similar anchor based on the anchor information; and to determine the target resource transfer information based on the resource transfer information of the second similar anchor.

[0060] Optionally, the target historical resource transfer information acquisition unit acquires the first historical resource transfer information of the broadcaster based on the broadcaster information through the following steps:

[0061] Based on the broadcaster information, obtain multiple historical resource transfer information of the broadcaster within a first preset historical time period;

[0062] The N1 historical resource transfer records that meet the preset filtering conditions are determined as the first historical resource transfer records of the broadcaster; and

[0063] The following steps are used to obtain the second historical resource transfer information of the first similar broadcaster based on the broadcaster information:

[0064] The M1 streamers with the highest similarity to the streamer among all streamers who meet the first preset condition are identified as the first similar streamers;

[0065] Obtain historical resource transfer information for each of the first similar broadcasters within a second preset historical time period;

[0066] The N2 historical resource transfer information that meet the preset screening conditions are determined as the second historical resource transfer information of the first similar anchor;

[0067] The target resource transfer information acquisition unit obtains resource transfer information of a second similar streamer based on the streamer information through the following steps:

[0068] The M2 reporting anchors with the greatest similarity to the anchor among all anchors that meet the second preset condition are selected as the second similar anchors;

[0069] Obtain the resource transfer information submitted by the second similar streamer;

[0070] Where N1, N2, M1, and M2 are all positive integers.

[0071] Optionally, the accuracy determination module is specifically configured to: determine first relationship data based on the first historical resource transfer information and the resource transfer information submitted by the target live streaming room; determine second relationship data based on the second historical resource transfer information and the resource transfer information submitted by the target live streaming room; determine third relationship data based on the target resource transfer information and the resource transfer information submitted by the target live streaming room; determine fourth relationship data based on the second estimated resource transfer information and the resource transfer information submitted by the target live streaming room; and determine the accuracy of the resource transfer information submitted by the target live streaming room using a target accuracy evaluation model based on at least one of the first relationship data, the second relationship data, and the third relationship data, and the fourth relationship data.

[0072] Optionally, the accuracy determination module determines the accuracy of the reported resource transfer information using a target accuracy evaluation model based on at least one of the first relationship data, the second relationship data, and the third relationship data, along with the fourth relationship data, through the following steps:

[0073] The first estimated accuracy is determined based on the first relationship data, at least one first hyperparameter of the target accuracy evaluation model, and the first preset judgment condition.

[0074] The second estimated accuracy is determined based on the second relationship data, at least one second hyperparameter of the target accuracy evaluation model, and the second preset judgment condition.

[0075] The third estimated accuracy is determined based on the third relationship data, at least one third hyperparameter of the target accuracy evaluation model, and the third preset judgment condition.

[0076] The fourth estimated accuracy is determined based on the fourth relationship data, at least one fourth hyperparameter of the target accuracy evaluation model, and the fourth preset judgment condition.

[0077] Based on at least one of the first estimated accuracy, the second estimated accuracy, and the third estimated accuracy, and the fourth estimated accuracy, the accuracy of the resource transfer information reported by the target live streaming room is determined using a preset comprehensive discrimination matrix of the target accuracy evaluation model.

[0078] Optionally, the information processing device further includes:

[0079] The genetic algorithm improvement module is used to improve the genetic algorithm based on the alarm rate penalty function to obtain the improved genetic algorithm;

[0080] The target accuracy evaluation model generation module is used to fine-tune the hyperparameters of the initial accuracy evaluation model based on the improved genetic algorithm, so as to obtain the optimized target accuracy evaluation model.

[0081] Optionally, the second estimated resource transfer information determination module is used to obtain multiple historical resource transfer information of the live room corresponding to the live room identifier within a third preset historical time period based on the live room identifier; and to determine the second estimated resource transfer information based on the multiple historical resource transfer information within the third preset historical time period.

[0082] According to a third aspect of this disclosure, an electronic device is provided, comprising: a processor configured to execute a computer program stored in a memory, wherein the computer program, when executed by the processor, implements the method described in the first aspect.

[0083] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect.

[0084] According to a fifth aspect of this disclosure, a computer program product is provided that, when run on a computer, causes the computer to perform the method described in the first aspect.

[0085] The technical solution provided in this disclosure has the following advantages compared with the prior art:

[0086] By providing an information input interface, merchants can input information about the target livestream room, the streamer, and the resource transfer information to be submitted. Based on the streamer information, a first estimated resource transfer is determined; based on the submitted livestream room information, a second estimated resource transfer is determined; and based on the first and second estimated resource transfer information and the first submitted resource transfer information, the accuracy of the target livestream room's submitted resource transfer information is determined. Compared to resource providers' self-submission, this disclosure achieves effective prediction of resource transfer information. Furthermore, it can obtain the first and second estimated resource transfer information from two dimensions (streamer and livestream room), and then determine the accuracy of the target livestream room's submitted resource transfer information based on these two information and the first submitted resource transfer information. The accuracy of the submitted resource transfer information can further provide reasonable reference information for the calibration of submitted resource transfer information. In addition, it avoids manual accuracy assessment, reducing labor costs and improving operational efficiency. Attached Figure Description

[0087] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0088] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0089] Figure 1 A schematic diagram of a system architecture for an exemplary application environment that can be applied to the information processing method of the embodiments of this disclosure is shown;

[0090] Figure 2 This is a flowchart of an information processing method in an embodiment of this disclosure;

[0091] Figure 3 This is a flowchart illustrating the determination of first estimated resource transfer information in an embodiment of this disclosure;

[0092] Figure 4 This is a schematic diagram of information processing in an embodiment of this disclosure;

[0093] Figure 5 This is a flowchart illustrating the training method of the target accuracy evaluation model in this embodiment of the disclosure;

[0094] Figure 6 This is a schematic diagram of the structure of an information processing device in an embodiment of this disclosure;

[0095] Figure 7 This is a schematic diagram of the structure of an electronic device according to an embodiment of this disclosure. Detailed Implementation

[0096] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0097] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0098] This disclosure provides an information processing method, apparatus, electronic device, medium, and program product that can improve the accuracy of evaluating resource transfer information submitted by a target live streaming room.

[0099] Figure 1 A schematic diagram of a system architecture for an exemplary application environment that can be applied to the information processing methods of embodiments of this disclosure is shown.

[0100] like Figure 1 As shown, system architecture 100 may include one or more of terminal devices 101, 102, and 103, a network 104, and a server 105. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, 103, and server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables. Terminal devices 101, 102, and 103 may be various electronic devices with displays, including but not limited to desktop computers, laptops, smartphones, and tablets. It should be understood that... Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, there can be any number of terminal devices, networks, and servers. For example, server 105 could be a server cluster consisting of multiple servers.

[0101] The information processing method provided in this embodiment is generally executed by server 105, and correspondingly, the information processing device can be installed in server 105. However, those skilled in the art will readily understand that the information processing method provided in this embodiment can also be executed by terminal devices 101, 102, and 103. For example, server 105 can pre-train and generate a target accuracy evaluation model using the information processing method provided in this embodiment. Terminal devices 101, 102, and 103 can input the live room information, anchor information, and resource transfer request information of the target live room in the information input interface. The live room information, anchor information, and resource transfer request information can be uploaded to server 105 via network 104. Server 105 processes the live room information, anchor information, and resource transfer request information based on this information processing method, determines the accuracy of the resource transfer request information, and sends the accuracy of the resource transfer request information to terminal devices 101, 102, and 103.

[0102] See Figure 2 , Figure 2 This is a flowchart of an information processing method according to an embodiment of the present disclosure, which may include the following steps:

[0103] Step S210: Receive the target live room information, the host information, and the resource transfer information submitted through the information input interface.

[0104] Step S220: Determine the first estimated resource transfer information based on the broadcaster information.

[0105] Step S230: Determine the second estimated resource transfer information based on the live broadcast room information.

[0106] Step S240: Based on the first estimated resource transfer information, the second estimated resource transfer information, and the reported resource transfer information, determine the accuracy of the reported resource transfer information for the target live streaming room.

[0107] The information processing method of this disclosure provides an information input interface, allowing merchants to input livestream room information, streamer information, and resource transfer information for a target livestream room. Based on the streamer information, a first estimated resource transfer information is determined; based on the information of the reported livestream room, a second estimated resource transfer information is determined; and based on the first and second estimated resource transfer information and the first reported resource transfer information, the accuracy of the reported resource transfer information for the target livestream room is determined. Compared to the resource provider's self-reporting, this disclosure achieves effective prediction of resource transfer information. Furthermore, the first and second estimated resource transfer information can be obtained from two dimensions (streamer and livestream room), respectively. Based on the first and second estimated resource transfer information and the first reported resource transfer information, the accuracy of the reported resource transfer information for the target livestream room can be determined. The accuracy of the reported resource transfer information can further provide reasonable reference information for the calibration of the reported resource transfer information. In addition, it avoids manual accuracy assessment, reducing labor costs and improving operational efficiency.

[0108] The technical solutions of the embodiments of this disclosure are described in detail below:

[0109] In step S210, the system receives the target live room information, the broadcaster information, and the resource transfer information submitted through the information input interface.

[0110] In this embodiment, the target livestream room is a livestream room on a livestreaming platform where livestream transactions take place. The streamer or merchant can input the target livestream room information, streamer information, and resource transfer information in the information input interface. Streamer information refers to the streamer information corresponding to the target livestream room, and resource transfer information refers to the resource transfer information corresponding to the target livestream room. Streamer information may include the streamer's ID, the category distribution information of the streamer's historically sold items, historical resource transfer information, etc. Livestream room information includes: livestream room ID, historical resource transfer information corresponding to the livestream room, historical advertising return on investment, future livestream time information, etc. Resource transfer information is the proposed target, which can be a specific transaction value, such as the volume of goods sold or the total amount of goods sold. Historical resource transfer information is the resource transfer information that the streamer has already completed within a historical time period. Resources may include, for example, goods, services, rights, etc. Resource transfer information may include, for example, the transaction amount of goods sold, etc. The resource transfer information may be the transaction amount of goods to be completed in the target livestream, preset before or during the target livestream.

[0111] Because the information submitted by the target livestream room regarding resource transfer may contain inaccuracies, the livestream platform can predict the accuracy of this information. The platform's servers can assess the accuracy of the submitted resource transfer information based on the livestream room information, the streamer information, and the submitted resource transfer details.

[0112] Step S220: Determine the first estimated resource transfer information based on the broadcaster information.

[0113] Because different streamers on a live streaming platform have a significant impact on transaction value, this disclosure can estimate resource transfer information between target streamers at the streamer level, obtaining the first estimated resource transfer information. It is understood that the first estimated resource transfer information and the reported resource transfer information are the same type of information. For example, if the reported resource transfer information is the total transaction amount, the first estimated resource transfer information will also be the total transaction amount.

[0114] See Figure 3 , Figure 3 A flowchart illustrating the determination of first estimated resource transfer information in this embodiment of the present disclosure may include the following steps:

[0115] Step S310: Obtain the target historical resource transfer information corresponding to the broadcaster based on the broadcaster information.

[0116] As mentioned above, the streamer information may include the streamer's historical resource transfer information, etc. The historical resource transfer information can be real resource transfer information within one or more historical time ranges. This disclosure can estimate the resource transfer information of a target live streaming room based on the streamer's historical resource transfer information. In an optional implementation, the streamer's first historical resource transfer information can be obtained based on the streamer information. For example, the streamer's historical resource transfer information within the 90 days prior to the current moment can be obtained as the first historical resource transfer information.

[0117] Similarly, based on the streamer information, the second historical resource transfer information of the first similar streamer (streamers with a high similarity to the streamer on the live streaming platform) can be obtained, and the resource transfer information of the target live streaming room can be estimated based on the second historical resource transfer information of the first similar streamer. For example, the historical resource transfer information of the first similar streamer within 60 days prior to the current moment can be obtained as the second historical resource transfer information. Furthermore, the streamers with the highest similarity to the streamer among all streamers who meet the first preset condition (preferably determined according to the model parameters of the target accuracy evaluation model) can be identified as the first similar streamers; the first preset condition includes, for example, all streamers on the live streaming platform corresponding to the target live streaming room, but is not limited to this.

[0118] Then, the target historical resource transfer information can be determined based on the first historical resource transfer information and / or the second historical resource transfer information. That is, the resource transfer information of the target live stream can be estimated based solely on the first historical resource transfer information, or solely on the second historical resource transfer information, or simultaneously based on both the first and second historical resource transfer information.

[0119] Optionally, if the resource transfer information of the target live streaming room is estimated based on both the first historical resource transfer information and the second historical resource transfer information, the target historical resource transfer information may include the average value of the first historical resource transfer information and the average value of the second historical resource transfer information.

[0120] Step S320: Based on the broadcaster information, obtain the target resource transfer information corresponding to the broadcaster.

[0121] In addition to estimating the resource transfer information of the target live stream room based on historical resource transfer information (including the historical resource transfer information of the streamer and / or the historical resource transfer information of the first similar streamer), this disclosure can also estimate the resource transfer information of the target live stream room based on the resource transfer information submitted by other submitting streamers. The submitted resource transfer information can be resource transfer information submitted within one or more time ranges.

[0122] In one optional implementation, resource transfer information of a second similar streamer (e.g., a streamer with high similarity to the original streamer among those submitted on the live streaming platform) can be obtained based on the streamer information. Target resource transfer information can then be determined based on this second similar streamer information. The target resource transfer information may be the average value of the resource transfer information of the second similar streamers. Further, multiple streamers (preferably determined based on the model hyperparameters of the target accuracy evaluation model) with the highest similarity to the original streamer among all streamers meeting the second preset condition can be considered as the second similar streamers. The second preset condition may include, for example, all submitted streamers on the live streaming platform corresponding to the target live streaming room, but is not limited to this.

[0123] Step S330: Determine the first estimated resource transfer information based on the target's historical resource transfer information and / or the target's reported resource transfer information.

[0124] In this embodiment, the first estimated resource transfer information can be determined solely based on the target's historical resource transfer information or the target's reported resource transfer information, or it can be determined simultaneously based on both the target's historical resource transfer information and the target's reported resource transfer information. Compared to determining the first estimated resource transfer information solely based on the target's historical resource transfer information or the target's reported resource transfer information, the accuracy of resource transfer information prediction can be improved.

[0125] In one alternative implementation, the accuracy of resource transfer information can be evaluated using a pre-trained target accuracy evaluation model. The target accuracy evaluation model can include multiple different hyperparameters N1, N2, M1, and M2, where N1, N2, M1, and M2 are all positive integers and can be pre-trained. Using the hyperparameters N1, N2, M1, and M2 in the trained target accuracy evaluation model, the first historical resource transfer information of the broadcaster, the second historical resource transfer information of the first similar broadcaster, and the resource transfer information reported by the second similar broadcaster can be determined.

[0126] Specifically, based on the streamer's information, multiple historical resource transfer information for the streamer within a first preset historical time period can be obtained. The N1 historical resource transfer values ​​(e.g., historical transaction amounts) that meet preset filtering criteria are determined as the streamer's first historical resource transfer information. The M1 streamers with the highest similarity among all streamers meeting the first preset criteria are determined as the first similar streamers. Historical resource transfer information for each first similar streamer within a second preset historical time period is obtained. The N2 historical resource transfer values ​​(historical transaction amounts) that meet preset filtering criteria are determined as the second historical resource transfer information for the first similar streamers. The N1 historical resource transfer values ​​that meet the preset filtering criteria can be the largest N1 historical resource transfer value, and the N2 historical resource transfer values ​​that meet the preset filtering criteria can be the largest N2 historical resource transfer value; however, the preset filtering criteria are not limited to these. All streamers meeting the first preset criteria can be a certain type of streamer on the live streaming platform, or they can be all streamers on the live streaming platform, etc.

[0127] Among all broadcasters meeting the second preset condition, the M2 broadcasters with the highest similarity to the original broadcaster are selected as the second similar broadcasters, and their resource transfer information is obtained. All broadcasters meeting the second preset condition can be broadcasters of a certain type on the live streaming platform, or they can be all broadcasters that have submitted applications. Based on the broadcaster information and the information of the broadcasters submitting applications, the similarity between each broadcaster and each broadcaster submitting application can be determined, and thus the M2 broadcasters with the highest similarity are selected as the second similar broadcasters.

[0128] The similarity between livestreamers can be determined based on factors such as the type of livestream and the cumulative transaction volume of goods. For example, the similarity in the type of livestream and the similarity in the cumulative transaction amount.

[0129] This disclosure determines the accuracy of the reported information based on multiple dimensions of broadcaster information (current broadcaster information, similar broadcaster information, and similar broadcaster information in different similarity dimensions), thereby improving the effectiveness of the prediction.

[0130] Step S230: Determine the second estimated resource transfer information based on the live broadcast room information.

[0131] Similarly, a second estimated transaction value corresponding to a live stream room can be determined based on the live stream room dimension. Optionally, multiple historical resource transfer information and / or reported resource transfer information of the live stream room corresponding to the live stream room identifier within a third preset historical time period can be obtained based on the live stream room identifier; the second estimated resource transfer information can be determined based on the multiple historical resource transfer information and / or reported resource transfer information within the third preset historical time period.

[0132] The method for predicting resource transfer information based on live stream information can be either a probability-based approach or a data-driven approach, that is, using machine learning, deep learning, etc. from a data perspective.

[0133] Among them, data-driven methods can be econometric statistical models, such as time series and grey models, or machine learning models, such as Random Forest and Support Vector Machine (SVM); they can also be deep learning models, which use multi-layer neural networks to construct nonlinear functions corresponding to complex hypothesis spaces, enabling the neural network functions to have powerful model fitting capabilities. The main one is the seq2seq (encoder-decoder model) prediction method with recurrent neural networks (RNN) and convolutional neural networks (CNN) as the structure.

[0134] Step S240: Based on the first estimated resource transfer information, the second estimated resource transfer information, and the reported resource transfer information, determine the accuracy of the reported resource transfer information for the target live streaming room.

[0135] In this embodiment of the disclosure, the resource transfer information to be reported can be the target value to be achieved in the future, and the first estimated resource transfer information and the second estimated resource transfer information can be the estimated value. Therefore, the accuracy of the resource transfer information to be reported can be evaluated based on the first estimated resource transfer information and the second estimated resource transfer information.

[0136] Optionally, a first relationship data can be determined based on first historical resource transfer information and reported resource transfer information; a second relationship data can be determined based on second historical resource transfer information and reported resource transfer information; a third relationship data can be determined based on target reported resource transfer information and reported resource transfer information; a fourth relationship data can be determined based on second estimated resource transfer information and reported resource transfer information; and the accuracy of the reported resource transfer information can be determined using a target accuracy evaluation model based on at least one of the first, second, and third relationship data and the fourth relationship data. The first / second historical resource transfer information may include first / second historical resource transfer values, such as first / second historical commodity transaction amounts. The first / second estimated resource transfer information may include first / second estimated resource transfer values, such as first / second estimated commodity transaction amounts. The reported resource transfer information may include reported resource transfer values, such as reported commodity transaction amounts.

[0137] For example, by determining the ratios of the reported resource transfer information to the first historical resource transfer value, the second historical resource transfer value, the target reported resource transfer value, and the second estimated resource transfer value, a first ratio, a second ratio, a third ratio, and a fourth ratio are obtained. When the average of the first historical resource transfer value, the average of the second historical resource transfer value, the average of the target reported resource transfer value, and the second estimated resource transfer value include multiple values, the ratio can be the ratio of the reported resource transfer information to the average of the first historical resource transfer value, the average of the second historical resource transfer value, the average of the target reported resource transfer value, and the average of the second estimated resource transfer value. In this case, the first ratio is the first relational data, the second ratio is the second relational data, the third ratio is the third relational data, and the fourth ratio is the fourth relational data.

[0138] Subsequently, a first estimated accuracy can be determined based on the first relational data, at least one first hyperparameter of the target accuracy evaluation model, and a first preset judgment condition; a second estimated accuracy can be determined based on the second relational data, at least one second hyperparameter of the target accuracy evaluation model, and a second preset judgment condition; a third estimated accuracy can be determined based on the third relational data, at least one third hyperparameter of the target accuracy evaluation model, and a third preset judgment condition; a fourth estimated accuracy can be determined based on the fourth relational data, at least one fourth hyperparameter of the target accuracy evaluation model, and a fourth preset judgment condition; and the accuracy of the reported resource transfer information can be determined using a preset comprehensive discrimination matrix of the target accuracy evaluation model based on at least one of the first, second, and third estimated accuracy and the fourth estimated accuracy.

[0139] The first, second, third, and fourth hyperparameters are hyperparameters in the target accuracy evaluation model, which can be represented as K1, K2, K3, and K4, respectively, and can also be pre-trained. The first, second, third, and fourth preset judgment conditions can be pre-set conditions used to determine the estimated accuracy. For example, the first relational data is the ratio of reported resource transfer information to first historical resource transfer information, i.e., the first ratio. The first hyperparameter is K1. The first preset judgment condition can be: if the first ratio is greater than K1, then the first estimated accuracy is determined to be inaccurate; if the first ratio is less than or equal to K1, then the first estimated accuracy is determined to be accurate. The second, third, and fourth preset judgment conditions are similar to the first preset judgment condition and will not be listed individually here.

[0140] The preset comprehensive discrimination matrix is ​​a pre-set matrix in the target accuracy evaluation model used to determine the final accuracy based on at least one of the first predicted accuracy, the second predicted accuracy, the third predicted accuracy, and the fourth predicted accuracy.

[0141] Specifically, based on the comprehensive discrimination matrix, if the fourth estimated accuracy is inaccurate, or if the first, second, and third estimated accuracy are all inaccurate, then the accuracy of the resource transfer information corresponding to the target live broadcast room is determined to be at the first accuracy level (i.e., low accuracy). If the first, second, third, and fourth estimated accuracy are all accurate, then the accuracy of the resource transfer information can be considered to be at the second accuracy level (i.e., high accuracy). In other cases, the accuracy of the resource transfer information can be considered to be at the third accuracy level (i.e., medium accuracy).

[0142] See Figure 4 , Figure 4 This is a schematic diagram of information processing in an embodiment of this disclosure. It can be seen that the input to the information processing is: the live stream information of the target live stream, the streamer information, and the resource transfer information to be submitted. First estimated resource transfer information and second estimated resource transfer information are obtained at the streamer and live stream dimensions, respectively. Based on the first estimated resource transfer information, the second estimated resource transfer information, and the resource transfer information to be submitted, a preset comprehensive discrimination matrix is ​​used for comprehensive judgment, and finally, the accuracy of the resource transfer information to be submitted is output. This disclosure generates a target accuracy evaluation model through training, and obtains accurate evaluation data (i.e., first historical resource transfer information, second historical resource transfer information of the first similar streamer, and resource transfer information to be submitted by the second similar streamer) through multiple hyperparameters in the target accuracy evaluation model. The accuracy of the resource transfer information to be submitted in the target live stream is evaluated using a preset comprehensive discrimination matrix, which can improve the accuracy of the resource transfer information evaluation.

[0143] The training method for the target accuracy evaluation model is introduced below.

[0144] See Figure 5 , Figure 5 The flowchart of the training method for the target accuracy evaluation model in this embodiment of the disclosure may include the following steps:

[0145] Step S510: Improve the genetic algorithm based on the alarm rate penalty function to obtain the improved genetic algorithm.

[0146] Step S520: The hyperparameters of the initial accuracy evaluation model are tuned based on the improved genetic algorithm to obtain the optimized target accuracy evaluation model.

[0147] Specifically, multiple sample data and the target achievement result corresponding to each sample data (i.e., target achieved or target not achieved) can be obtained. Each sample data includes: the anchor information of the sample live broadcast room, the live broadcast room information, and the resource transfer information.

[0148] The hyperparameters are initialized to obtain the initial accuracy evaluation model.

[0149] Based on the initial accuracy assessment model, the anchor information, the live stream room information, and the resource transfer information reported by the sample live stream rooms, the accuracy of the resource transfer information reported by the sample live stream rooms is determined. Based on the accuracy of the resource transfer information reported by the sample live stream rooms and the target achievement results, the optimization function value is determined.

[0150] Specifically, the accuracy rate of the resource transfer information reported by multiple sample live streaming rooms can be determined based on the accuracy and target achievement results. Then, the probability of achieving the target accuracy (first-level accuracy) can be determined based on the accuracy of the resource transfer information reported by multiple sample live streaming rooms.

[0151] The probability of target accuracy and the actual probability of historical target failure are substituted into a pre-constructed alarm rate penalty function to obtain the alarm rate penalty function value. Optionally, the target probability x can be determined based on the probability of target accuracy and the actual probability of historical target failure. For example, the ratio of the probability of target accuracy to the actual probability of historical target failure can be used to determine the target probability x.

[0152] Among them, if the alarm rate penalty function Substitute the target probability x into Y(x) to determine the alarm rate penalty function value.

[0153] The accuracy of resource transfer information reports from multiple sample live streaming rooms is multiplied with the alarm rate penalty function value to determine the optimal function value. An improved genetic algorithm, specifically the optimized function value obtained after incorporating the alarm rate penalty function, is used to optimize the hyperparameters and generate a target accuracy evaluation model. This disclosure, by introducing the alarm rate penalty function, can improve the accuracy of the generated target accuracy evaluation model, thereby enabling a more accurate determination of the accuracy of resource transfer information reports.

[0154] It should be noted that, since the historical sample data corresponding to different historical time periods are different, in this embodiment of the disclosure, a new target accuracy assessment model can be trained every preset time period (e.g., one week) or before each accuracy assessment, so as to improve the accuracy of the accuracy assessment.

[0155] Corresponding to the above method embodiments, this disclosure also provides an information processing apparatus, see below. Figure 6 The information processing device 600 includes:

[0156] The live room information receiving module 610 is used to receive the live room information, the host information and the resource transfer information of the target live room input through the information input interface;

[0157] The first estimated resource transfer information determination module 620 is used to determine the first estimated resource transfer information based on the broadcaster information.

[0158] The second estimated resource transfer information determination module 630 is used to determine the second estimated resource transfer information based on the live broadcast room information.

[0159] The accuracy determination module 640 is used to determine the accuracy of the reported resource transfer information of the target live broadcast room based on the first estimated resource transfer information, the second estimated resource transfer information, and the reported resource transfer information.

[0160] Optionally, the first estimated resource transfer information determination module 620 includes:

[0161] The target historical resource transfer information acquisition unit is used to acquire the target historical resource transfer information corresponding to the broadcaster based on the broadcaster information;

[0162] The target resource transfer information acquisition unit is used to acquire the target resource transfer information corresponding to the broadcaster based on the broadcaster information.

[0163] The first estimated resource transfer information determination unit is used to determine the first estimated resource transfer information based on the target's historical resource transfer information and / or the target's reported resource transfer information.

[0164] Optionally, the target historical resource transfer information acquisition unit is specifically used to acquire the first historical resource transfer information of the broadcaster based on the broadcaster information; acquire the second historical resource transfer information of the first similar broadcaster based on the broadcaster information; and determine the target historical resource transfer information based on the first historical resource transfer information and / or the second historical resource transfer information.

[0165] The target resource transfer information acquisition unit is specifically used to acquire the resource transfer information of the second similar anchor based on the anchor information; and to determine the target resource transfer information based on the resource transfer information of the second similar anchor.

[0166] Optionally, the target historical resource transfer information acquisition unit acquires the first historical resource transfer information of the broadcaster based on the broadcaster information through the following steps:

[0167] Based on the broadcaster information, obtain multiple historical resource transfer information of the broadcaster within the first preset historical time period;

[0168] The N1 historical resource transfer records that meet the preset filtering criteria are identified as the first historical resource transfer record for the broadcaster; and

[0169] The following steps are used to obtain the second historical resource transfer information of the first similar broadcaster based on the broadcaster's information:

[0170] The M1 streamers with the highest similarity to the streamer among all streamers who meet the first preset condition are identified as the first similar streamers;

[0171] Obtain historical resource transfer information for each first-similar streamer within a second preset historical time period;

[0172] The N2 historical resource transfer information that meet the preset screening conditions are identified as the second historical resource transfer information of the first similar anchor;

[0173] The target resource transfer information acquisition unit obtains resource transfer information of the second similar broadcaster based on the broadcaster information through the following steps:

[0174] The M2 streamers with the highest similarity to the streamer among all streamers who meet the second preset condition are selected as the second similar streamers;

[0175] Obtain the resource transfer information submitted by the second most similar streamer;

[0176] Where N1, N2, M1, and M2 are all positive integers.

[0177] Optionally, the accuracy determination module 640 is specifically used to determine first relationship data based on first historical resource transfer information and resource transfer information submitted by the target live streaming room; determine second relationship data based on second historical resource transfer information and resource transfer information submitted by the target live streaming room; determine third relationship data based on target submitted resource transfer information and resource transfer information submitted by the target live streaming room; determine fourth relationship data based on second estimated resource transfer information and resource transfer information submitted by the target live streaming room; and determine the accuracy of the resource transfer information submitted by the target live streaming room using a target accuracy evaluation model based on at least one of the first relationship data, second relationship data, and third relationship data, and the fourth relationship data.

[0178] Optionally, the accuracy determination module 640 determines the accuracy of the reported resource transfer information using a target accuracy evaluation model based on at least one of the first relation data, the second relation data, and the third relation data, and the fourth relation data, through the following steps:

[0179] The first estimated accuracy is determined based on the first relational data, at least one first hyperparameter of the target accuracy evaluation model, and the first preset judgment condition.

[0180] The second estimated accuracy is determined based on the second relational data, at least one second hyperparameter of the target accuracy evaluation model, and the second preset judgment condition.

[0181] The third estimated accuracy is determined based on the third relation data, at least one third hyperparameter of the target accuracy evaluation model, and the third preset judgment condition.

[0182] The fourth prediction accuracy is determined based on the fourth relation data, at least one fourth hyperparameter of the target accuracy evaluation model, and the fourth preset judgment condition.

[0183] The accuracy of the resource transfer information reported by the target live streaming room is determined by using a preset comprehensive discrimination matrix of the target accuracy evaluation model based on at least one of the first, second, and third estimated accuracy and a fourth estimated accuracy.

[0184] Optionally, the information processing device 600 described above further includes:

[0185] The genetic algorithm improvement module is used to improve the genetic algorithm based on the alarm rate penalty function to obtain the improved genetic algorithm;

[0186] The target accuracy evaluation model generation module is used to fine-tune the hyperparameters of the initial accuracy evaluation model based on the improved genetic algorithm, so as to obtain the optimized target accuracy evaluation model.

[0187] Optionally, the second estimated resource transfer information determination module is used to obtain multiple historical resource transfer information of the live room corresponding to the live room identifier within a third preset historical time period based on the live room identifier; and to determine the second estimated resource transfer information based on the multiple historical resource transfer information within the third preset historical time period.

[0188] The specific details of each module or unit in the above-mentioned device have been described in detail in the corresponding methods, so they will not be repeated here.

[0189] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0190] In an exemplary embodiment of this disclosure, an electronic device is also provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to perform the information processing method described in this exemplary embodiment.

[0191] Figure 7 This is a schematic diagram of the structure of an electronic device according to an embodiment of this disclosure. It should be noted that... Figure 7The illustrated electronic device 700 is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0192] like Figure 7 As shown, the electronic device 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes based on a program stored in a read-only memory (ROM) 702 or a program loaded from a storage section 708 into a random access memory (RAM) 703. The RAM 703 also stores various programs and data required for system operation. The CPU 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0193] The following components are connected to I / O interface 705: an input section 706 including a keyboard, mouse, etc.; an output section 707 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a local area network (LAN) card, modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to I / O interface 705 as needed. A removable medium 711, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 710 as needed so that computer programs read from it can be installed into storage section 708 as needed.

[0194] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 709, and / or installed from removable medium 711. When the computer program is executed by central processing unit 701, it performs various functions defined in the apparatus of this disclosure.

[0195] In this embodiment of the disclosure, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the above-described information processing method.

[0196] It should be noted that the computer-readable storage medium disclosed herein can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. Program code contained on a computer-readable storage medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, radio frequency, etc., or any suitable combination thereof.

[0197] In this embodiment of the disclosure, a computer program product is also provided, which, when run on a computer, causes the computer to execute the above-described information processing method.

[0198] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0199] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An information processing method, characterized in that, The method includes: Receive the target live stream room information, the streamer information, and the resource transfer request information input through the information input interface; Based on the broadcaster information, determine the first estimated resource transfer information; The second estimated resource transfer information is determined based on the live stream information; Based on the first estimated resource transfer information, the second estimated resource transfer information, and the reported resource transfer information, the accuracy of the reported resource transfer information for the target live streaming room is determined; The step of determining the accuracy of the reported resource transfer information of the target live streaming room based on the first estimated resource transfer information, the second estimated resource transfer information, and the reported resource transfer information includes: The first relationship data is determined based on the first historical resource transfer information of the broadcaster and the resource transfer information submitted by the target live broadcast room; The second relationship data is determined based on the second historical resource transfer information of the first similar streamer and the reported resource transfer information of the target live streaming room; The third relationship data is determined based on the target resource transfer information corresponding to the streamer and the target live streaming room. The fourth relationship data is determined based on the second estimated resource transfer information and the resource transfer information submitted by the target live streaming room; Based on at least one of the first relationship data, the second relationship data, and the third relationship data, and the fourth relationship data, the accuracy of the resource transfer information of the target live broadcast room is determined using a target accuracy evaluation model. The first historical resource transfer information, the second historical resource transfer information, and the target reported resource transfer information are obtained based on the broadcaster information.

2. The method according to claim 1, characterized in that, The step of determining the first estimated resource transfer information based on the broadcaster information includes: Based on the streamer information, obtain the target historical resource transfer information corresponding to the streamer; Based on the broadcaster information, obtain the target resource transfer information corresponding to the broadcaster; The first estimated resource transfer information is determined based on the target's historical resource transfer information and / or the target's reported resource transfer information.

3. The method according to claim 2, characterized in that, The step of obtaining the target historical resource transfer information corresponding to the streamer based on the streamer information includes: Based on the broadcaster information, obtain the broadcaster's first historical resource transfer information; Based on the anchor information, obtain the second historical resource transfer information of the first similar anchor of the anchor; The target historical resource transfer information is determined based on the first historical resource transfer information and / or the second historical resource transfer information; The step of obtaining the target resource transfer information corresponding to the broadcaster based on the broadcaster information includes: Based on the anchor information, obtain the resource transfer information of the second similar anchor of the anchor; Based on the resource transfer information submitted by the second similar broadcaster, the target resource transfer information is determined.

4. The method according to claim 3, characterized in that, The step of obtaining the first historical resource transfer information of the broadcaster based on the broadcaster information includes: Based on the broadcaster information, obtain multiple historical resource transfer information of the broadcaster within a first preset historical time period; The N1 historical resource transfer information that meet the preset filtering conditions are determined as the first historical resource transfer information of the broadcaster; The step of obtaining the second historical resource transfer information of the first similar streamer based on the streamer information includes: The M1 streamers with the highest similarity to the streamer among all streamers who meet the first preset condition are identified as the first similar streamers; Obtain historical resource transfer information for each of the first similar broadcasters within a second preset historical time period; The N2 historical resource transfer information that meet the preset screening conditions are determined as the second historical resource transfer information of the first similar anchor; The step of obtaining resource transfer information for a second similar streamer based on the streamer information includes: The M2 streamers who are most similar to the streamer among all streamers who meet the second preset condition are selected as the second similar streamers; Obtain the resource transfer information submitted by the second similar streamer; Where N1, N2, M1, and M2 are all positive integers.

5. The method according to claim 4, characterized in that, Based on at least one of the first relationship data, the second relationship data, and the third relationship data, and the fourth relationship data, the accuracy of the reported resource transfer information of the target live streaming room is determined using a target accuracy evaluation model, including: The first estimated accuracy is determined based on the first relationship data, at least one first hyperparameter of the target accuracy evaluation model, and the first preset judgment condition. The second estimated accuracy is determined based on the second relationship data, at least one second hyperparameter of the target accuracy evaluation model, and the second preset judgment condition. The third estimated accuracy is determined based on the third relationship data, at least one third hyperparameter of the target accuracy evaluation model, and the third preset judgment condition. The fourth estimated accuracy is determined based on the fourth relationship data, at least one fourth hyperparameter of the target accuracy evaluation model, and the fourth preset judgment condition. Based on at least one of the first estimated accuracy, the second estimated accuracy, and the third estimated accuracy, and the fourth estimated accuracy, the accuracy of the resource transfer information reported by the target live streaming room is determined using a preset comprehensive discrimination matrix of the target accuracy evaluation model.

6. The method according to claim 1, characterized in that, Also includes: An improved genetic algorithm is obtained by modifying the genetic algorithm based on the alarm rate penalty function; The hyperparameters of the initial accuracy evaluation model were tuned using the improved genetic algorithm to obtain the optimized target accuracy evaluation model.

7. The method according to claim 1, characterized in that, The second estimated resource transfer information is determined based on the live stream information, including: Based on the live room identifier, obtain multiple historical resource transfer information of the live room corresponding to the live room identifier within a third preset historical time period; The second estimated resource transfer information is determined based on multiple historical resource transfer information within a third preset historical time period.

8. An information processing device, characterized in that, The device includes: The live stream information receiving module is used to receive the target live stream information, the host information, and the resource transfer information submitted by the target live stream input interface. The first estimated resource transfer information determination module is used to determine the first estimated resource transfer information based on the broadcaster information. The second estimated resource transfer information determination module is used to determine the second estimated resource transfer information based on the live broadcast room information; An accuracy determination module is used to determine the accuracy of the reported resource transfer information of the target live streaming room based on the first estimated resource transfer information, the second estimated resource transfer information, and the reported resource transfer information. The step of determining the accuracy of the reported resource transfer information of the target live streaming room based on the first estimated resource transfer information, the second estimated resource transfer information, and the reported resource transfer information includes: The first relationship data is determined based on the first historical resource transfer information of the broadcaster and the resource transfer information submitted by the target live broadcast room; The second relationship data is determined based on the second historical resource transfer information of the first similar streamer and the reported resource transfer information of the target live streaming room; The third relationship data is determined based on the target resource transfer information corresponding to the streamer and the target live streaming room. The fourth relationship data is determined based on the second estimated resource transfer information and the resource transfer information submitted by the target live streaming room; Based on at least one of the first relationship data, the second relationship data, and the third relationship data, and the fourth relationship data, the accuracy of the resource transfer information of the target live broadcast room is determined using a target accuracy evaluation model. The first historical resource transfer information, the second historical resource transfer information, and the target reported resource transfer information are obtained based on the broadcaster information.

9. An electronic device, characterized in that, include: A processor for executing a computer program stored in a memory, wherein the computer program, when executed by the processor, implements the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method described in any one of claims 1-7.

11. A computer program product, characterized in that, When the computer program product is run on a computer, it causes the computer to perform the steps of the method according to any one of claims 1-7.

Images