Comment sorting method and device, electronic equipment and storage medium

Abstract

The invention provides a comment sorting method and device, electronic equipment and a storage medium, and relates to the technical field of computers, in particular to the technical fields of development and management of multimedia and internet products, big data processing, information security and the like. According to the specific implementation scheme, multiple to-be-reviewed comments are obtained; wherein the multiple to-be-reviewed comments are in one-to-one correspondence with multiple users; obtaining comment auditing records of a plurality of users; obtaining interaction feedback results corresponding to the plurality of users; and based on the comment auditing records of the plurality of users and the interactive feedback results corresponding to the plurality of users, obtaining an auditing sorting result of the plurality of comments to be audited.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and particularly to technologies such as multimedia, development and management of Internet products, big data processing, information security, etc. Specifically, it relates to a comment sorting method, device, electronic device, and storage medium. Background Art

[0002] In the actual operation of content production Internet products, the product background continuously receives comments published by users, and uses a combination of manual review and machine filtering to review these comments, and then displays the comments that pass the review, so as to ensure the quality of the displayed comments. Summary of the Invention

[0003] The present disclosure provides a comment sorting method, device, electronic device, and storage medium.

[0004] According to a first aspect of the present disclosure, there is provided a comment sorting method, including:

[0005] Obtaining multiple comments to be reviewed; wherein, the multiple comments to be reviewed correspond to multiple users one by one;

[0006] Obtaining the comment review records of multiple users;

[0007] Obtaining the interactive feedback results corresponding to multiple users;

[0008] Based on the comment review records of multiple users and the interactive feedback results corresponding to multiple users, obtaining the submission sorting results of the multiple comments to be reviewed.

[0009] According to a second aspect of the present disclosure, there is provided a priority sorting device, including:

[0010] A comment-to-be-reviewed obtaining unit, configured to obtain multiple comments to be reviewed; wherein, the multiple comments to be reviewed correspond to multiple users one by one;

[0011] A comment review record obtaining unit, configured to obtain the comment review records of multiple users;

[0012] An interactive feedback result obtaining unit, configured to obtain the interactive feedback results corresponding to multiple users;

[0013] A submission sorting result obtaining unit, configured to obtain the submission sorting results of the multiple comments to be reviewed based on the comment review records of multiple users and the interactive feedback results corresponding to multiple users.

[0014] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0015] At least one processor;

[0016] A memory communicatively connected to the at least one processor;

[0017] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method provided in the first aspect of the present disclosure.

[0018] According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the method provided in the first aspect of the present disclosure.

[0019] According to a fifth aspect of the present disclosure, there is provided a computer program product including a computer program which, when executed by a processor, implements the method provided in the first aspect of the present disclosure.

[0020] Adopting the present disclosure can improve the effective exposure and dissemination efficiency of high-quality comments.

[0021] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0023] Figure 1 is a schematic flowchart of a comment ranking method provided by an embodiment of the present disclosure;

[0024] Figure 2 is a complete schematic flowchart of a comment ranking method provided by an embodiment of the present disclosure;

[0025] Figure 3 is a schematic diagram of an application scenario of a comment ranking method provided by an embodiment of the present disclosure;

[0026] Figure 4 is a schematic structural block diagram of a comment ranking device provided by an embodiment of the present disclosure;

[0027] Figure 5 is a schematic structural block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be appreciated by those skilled in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0029] As mentioned above, in the actual operation of content-producing internet products, the product backend continuously receives user comments and uses a combination of manual review and machine filtering to review these comments. Only those comments that pass the review are displayed to ensure the quality of the displayed comments. However, due to limitations in machine and human resources, it is often difficult for the product backend to achieve comprehensive and real-time synchronous review. Therefore, the current main method is to use a review mechanism based on the order in which comments are published, pushing user comments to the comment review system.

[0030] However, the inventors have found that the use of a review mechanism based on the order of comment releases can easily lead to a backlog of review tasks when faced with a large number of comments. Moreover, in extreme cases, a large number of low-quality or inappropriate comments may be pushed to the comment review system first. In contrast, high-quality comments are forced to remain at the end of the target review queue, resulting in the inability of high-quality comments to pass the review in a timely manner, which ultimately affects the effective exposure and dissemination efficiency of high-quality comments.

[0031] In view of the above problems, the embodiment of the present disclosure provides a comment sorting method, which can be applied to electronic devices. The electronic device can be a server, a workbench, a mainframe computer, a conventional computer (for example, a desktop computer, a laptop computer, a car computer, etc.) or other similar computing devices. Figure 1 The flowchart shown in FIG2 illustrates a comment sorting method provided by an embodiment of the present disclosure. It should be noted that although a logical order is shown in the flowchart, in some cases, the steps shown or described in the flowchart may be performed in other orders.

[0032] Step S101: Obtain multiple comments to be reviewed.

[0033] Among them, multiple comments to be reviewed are published by multiple users, that is, multiple comments to be reviewed correspond to multiple users one by one. Here, multiple users can be multiple different users, or can include at least some of the same users, which is not limited in the embodiment of the present disclosure.

[0034] In addition, it should be noted that in the embodiments of the present disclosure, multiple comments to be reviewed can be comments published on the same resource or comments published on different resources. Among them, the resource can be content provided by a resource provider (for example, an author) through an Internet product for content production (for example, provided through creation, sharing, legal transfer, etc.), such as articles, short videos, movies, music, etc. Here, the Internet product for content production can be an Internet application or a network platform.

[0035] Step S102: Obtain the comment review records of multiple users.

[0036] In the embodiments of the present disclosure, for each of the multiple users, the comment review record of the user can be used to record multiple comments published by the user in the historical stage and the review status of each comment in the multiple comments, so as to reflect the expected comment quality of the user.

[0037] Step S103: Obtain the interactive feedback results corresponding to the multiple users.

[0038] In the embodiments of the present disclosure, for each of the multiple users, the corresponding interactive feedback result can be used to characterize the comprehensive interactive feedback situation triggered by multiple comments (here, the multiple comments can be published asynchronously) after the user has published multiple comments in the historical stage, so as to reflect the expected comment popularity of the user.

[0039] Step S104: Based on the comment review records of the multiple users and the interactive feedback results corresponding to the multiple users, obtain the submission sorting result of the multiple comments to be reviewed.

[0040] Among them, the submission sorting result is used to characterize the target submission order of the multiple comments to be reviewed.

[0041] After obtaining the submission sorting result of the multiple comments to be reviewed, based on this, the multiple comments to be reviewed can be pushed to the comment review system.

[0042] By using the comment ranking method provided in the embodiments of the present disclosure, after obtaining multiple to-be-reviewed comments corresponding to multiple users one by one, the comment review records of multiple users can be obtained, and the interactive feedback results corresponding to multiple users can be obtained, and based on the comment review records of multiple users and the interactive feedback results corresponding to multiple users, the submission ranking results of multiple to-be-reviewed comments can be obtained. Among them, the comment review records of multiple users can reflect the expected comment quality of each user among multiple users, and the interactive feedback results corresponding to multiple users can reflect the expected comment popularity of each user among multiple users. Therefore, in the submission ranking results of multiple to-be-reviewed comments obtained based on the comment review records of multiple users and the interactive feedback results corresponding to multiple users, high-quality comments that can trigger popularity can be arranged at the front of the target review queue. In this way, high-quality comments can pass the review in a timely manner, thereby improving the effective exposure and dissemination efficiency of high-quality comments.

[0043] In some alternative embodiments, step S101, that is, "obtaining multiple to-be-reviewed comments" may include:

[0044] Step S101-1, determining at least one popular resource from multiple candidate resources at a target time interval.

[0045] In one example, the target time interval may be a preset fixed time interval. Among them, the preset fixed time interval may be 1 hour (H), 2H, etc., and its specific value can be set according to application requirements, and the embodiments of the present disclosure do not limit this.

[0046] In another example, the target time interval may also be dynamically determined. For example, during peak hours, a shorter first time interval may be used as the target time interval. Correspondingly, during non-peak hours, a longer second time interval may be used as the target time interval. Among them, peak hours may include [18:00, 24:00] on weekdays, [06:00, 09:00] on weekdays, and [06:00, 24:00] on non-working days. Correspondingly, non-peak hours may include (24:00, 06:00) on weekdays, (09:00, 18:00) on weekdays, and (24:00, 06:00) on non-working days; the first time interval may be 20 minutes (Min), 30Min, 40Min, etc., and its specific value can be set according to application requirements, and the embodiments of the present disclosure do not limit this; the second time interval may be 2H, 4H, etc., and its specific value can be set according to application requirements, and the embodiments of the present disclosure also do not limit this.

[0047] In addition, it should be noted that in the embodiments of the present disclosure, after determining the target time interval, at least one candidate resource with the largest interaction increment within the target time period can be determined from multiple candidate resources as the popular resource. That is, N candidate resources with the largest interaction increment within the target time period can be determined from multiple candidate resources as the popular resource. Among them, the interaction enhancement can be the overall increment of interaction behaviors such as comments, shares, collections, and likes; N≥1 and is an integer, which can be specifically set according to application requirements, and the embodiments of the present disclosure do not limit this.

[0048] In addition, it should also be noted that in the embodiments of the present disclosure, the target time period can be determined based on the current time point and the target time interval. For example, if the target time interval is a preset fixed time interval, specifically 1H, then at 09:00 on April 14, 2025, N candidate resources with the largest interaction increment within the target time period [08:00 on April 14, 2025, 09:00 on April 14, 2025] can be determined from multiple candidate resources as the popular resource; for another example, if the target time interval is a preset fixed time interval, specifically 2H, then at 09:00 on April 14, 2025, N candidate resources with the largest interaction increment within the target time period [07:00 on April 14, 2025, 09:00 on April 14, 2025] can be determined from multiple candidate resources as the popular resource.

[0049] Step S101-2: Determine multiple target comment messages from the comment information collection of at least one popular resource as the preliminary selected comments to obtain multiple preliminary selected comments.

[0050] Among them, the multiple target comment messages are resource comment messages that have not been selected as preliminary selected comments.

[0051] Exemplarily, the popular resources include Resource A, Resource B, and Resource C. Among them, the comment information collection of Resource A includes resource comment information A1, resource comment information A2, and resource comment information A3 that have been selected as primary comments, as well as resource comment information A4, resource comment information A5, resource comment information A6, and resource comment information A7 that have not been selected as primary comments; the comment information collection of Resource B includes resource comment information B1, resource comment information B2, resource comment information B3, resource comment information B4, and resource comment information B5 that have been selected as primary comments, as well as resource comment information B6, resource comment information B7, and resource comment information B8 that have not been selected as primary comments; the comment information collection of Resource C includes resource comment information C1, resource comment information C2, resource comment information C3, resource comment information C4, and resource comment information C5 that have been selected as primary comments, as well as resource comment information C6 and resource comment information C7 that have not been selected as primary comments. Then, from the comment information collections of Resource A, Resource B, and Resource C, resource comment information A4, resource comment information A5, resource comment information A6, and resource comment information A7 for Resource A, resource comment information B6, resource comment information B7, and resource comment information B8 for Resource B, and resource comment information C6 and resource comment information C7 for Resource C can be respectively determined as primary comments to obtain 9 primary comments.

[0052] Step S101-3, based on multiple primary comments, obtain multiple comments to be reviewed.

[0053] After obtaining multiple primary comments, each primary comment among the multiple primary comments can be used as a comment to be reviewed, or the multiple primary comments can be screened to obtain multiple comments to be reviewed. Among them, screening the multiple primary comments can be to eliminate illegal, non-compliant, and duplicate primary comments among the multiple primary comments.

[0054] In the above manner, in the embodiments of the present disclosure, at least one popular resource can be determined from multiple candidate resources at a target time interval, and multiple target comment information can be determined from the comment information collections of the at least one popular resource as primary comments to obtain multiple primary comments, and then multiple comments to be reviewed can be obtained based on the multiple primary comments. In this way, it can be ensured that the multiple comments to be reviewed all come from popular resources, and popular resources are relatively popular among users. Therefore, the resource comments under them are used as primary comments and then as comments to be reviewed and pushed to the comment review system in a timely manner, which can enable them to be displayed as soon as possible after passing the review, thereby triggering more discussions and interactions, and ultimately increasing the user stickiness of content production Internet products.

[0055] In some alternative embodiments, step S103, that is, "obtain the interactive feedback results of multiple users" may include:

[0056] Step S103-1, determine multiple data collection dimensions.

[0057] Among them, the multiple data collection dimensions may include:

[0058] The first data collection dimension: the interaction dimension with other users;

[0059] The second data collection dimension: the interaction dimension with the resource provider.

[0060] Among them, other users may be any users except the resource author.

[0061] Step S103-2, take each user among the multiple users as the second target user, and respectively obtain the characterization data of the interaction situation of the second target user from the multiple data collection dimensions, so as to obtain multiple characterization data of the interaction situation.

[0062] Among them, the multiple characterization data of the interaction situation correspond one-to-one with the multiple data collection dimensions, and each characterization data of the interaction situation among the multiple characterization data of the interaction situation may include multiple interaction index data, such as the number of comments, the number of shares, the number of favorites, the number of likes, etc. Exemplarily, the multiple data collection dimensions include the first data collection dimension and the second data collection dimension. Then, after taking each user among the multiple users as the second target user, the characterization data of the interaction situation of the second target user can be obtained from the first data collection dimension to be used to characterize the interaction situations such as comments, shares, favorites, likes, etc. of other users on the comments made by the second target user; at the same time, the characterization data of the interaction situation of the second target user can be obtained from the second data collection dimension to be used to characterize the interaction situations such as comments, shares, favorites, likes, etc. of the resource provider on the comments made by the second target user.

[0063] Step S103-3, obtain the interactive feedback result based on the multiple characterization data of the interaction situation.

[0064] Among them, the interactive feedback result can be used to characterize the comprehensive interactive feedback situation triggered by multiple comments (here, multiple comments may be published asynchronously) after the second target user published multiple comments in the historical stage, so as to reflect the expected comment popularity of the second target user.

[0065] For step S103-3, in one example, it can be implemented in the following manner:

[0066] First, each piece of interaction situation representation data among multiple pieces of interaction situation representation data can be used as target interaction situation representation data. Based on the target interaction situation representation data, multiple target interaction index data can be determined. Among them, the multiple target interaction index data can include interaction index data such as the number of comments, the number of shares, the number of collections, and the number of likes.

[0067] After that, based on the multiple target interaction index data, an interaction feedback score corresponding to the target interaction situation representation data can be obtained.

[0068] In a specific example, the to-be-reviewed comments corresponding to the second target user among multiple to-be-reviewed comments can be used as the fourth target to-be-reviewed comments, so as to determine the second target resource type of the current resource targeted by the fourth target to-be-reviewed comments. And based on the second target resource type, weight distribution parameters of the multiple target interaction index data can be obtained. Then, based on the weight distribution parameters of the multiple target interaction index data, the multiple target interaction index data are weighted and summed to obtain an interaction feedback score corresponding to the target interaction situation representation data. Among them, the second target resource type can be current affairs, social livelihood, entertainment gossip, audio-visual resources (such as movies, music), etc.

[0069] Exemplarily, the second target resource type is current affairs. The multiple target interaction index data include the number of comments, the number of shares, the number of collections, and the number of likes. Then, the weight distribution parameter of the number of comments can be set as the fifth weight distribution parameter, and the weight distribution parameters of the number of shares, the number of collections, and the number of likes can be set as the sixth weight distribution parameter. Moreover, the sixth weight distribution parameter is greater than the fifth weight distribution parameter. For example, the fifth weight distribution parameter can be 0.1, and the sixth weight distribution parameter can be 0.3. Specifically, it can also be set according to application requirements, and the embodiments of the present disclosure do not limit this.

[0070] Exemplarily, the second target resource type is any one of social livelihood, entertainment gossip, and audio-visual resources. The multiple target interaction index data include the number of comments, the number of shares, the number of collections, and the number of likes. Then, the weight distribution parameters of the number of comments, the number of shares, the number of collections, and the number of likes can be set as the seventh weight distribution parameter. Among them, the seventh weight distribution parameter can be 0.25. Specifically, it can also be set according to application requirements, and the embodiments of the present disclosure do not limit this.

[0071] Finally, based on the multiple interaction feedback scores corresponding one by one to the multiple interaction situation representation data, an interaction feedback result can be obtained.

[0072] In an example, the mean value of the multiple interaction feedback scores can be used as the interaction feedback result;

[0073] In another example, the sum of the multiple interaction feedback scores can be used as the interaction feedback result;

[0074] In yet another example, multiple interactive feedback scores can be weighted and summed to obtain an interactive feedback result.

[0075] In the embodiments of the present disclosure, through the above methods, multiple data collection dimensions can be determined, and each user among multiple users can be used as a second target user. The interactive situation characterization data of the second target user can be obtained respectively from multiple data collection dimensions to obtain multiple interactive situation characterization data. Then, based on multiple interactive feedback scores corresponding one by one to the multiple interactive situation characterization data, an interactive feedback result can be obtained. In this way, for each user among multiple users, the interactive feedback result can characterize the expected comment popularity of the user in different dimensions (for example, the interactive dimension with other users and the interactive dimension with the resource provider), thereby improving the reliability of the interactive feedback result.

[0076] Moreover, when obtaining the interactive feedback result based on multiple interactive situation characterization data, each interactive situation characterization data among the multiple interactive situation characterization data can be used as the target interactive situation characterization data. Based on the target interactive situation characterization data, multiple target interactive index data can be determined, and based on the multiple target interactive index data, an interactive feedback score corresponding to the target interactive situation characterization data can be obtained. Then, based on multiple interactive feedback scores corresponding one by one to the multiple interactive situation characterization data, an interactive feedback result can be obtained. Among them, obtaining the interactive feedback score corresponding to the target interactive situation characterization data based on the multiple target interactive index data can further include: using the review comments corresponding to the second target user among multiple review comments to be reviewed as the fourth target review comments to determine the second target resource type of the current resource targeted by the fourth target review comments, and based on the second target resource type, obtaining the weight distribution parameters of the multiple target interactive index data. Then, based on the weight distribution parameters of the multiple target interactive index data, the multiple target interactive index data are weighted and summed to obtain the interactive feedback score corresponding to the target interactive situation characterization data. On the one hand, in the process of obtaining the interactive feedback result based on multiple interactive situation characterization data, the interactive feedback score corresponding to the target interactive situation characterization data is obtained based on rich interactive index data, that is, multiple target interactive index data. In this way, the accuracy of the interactive feedback score can be ensured, thereby further improving the reliability of the interactive feedback result. On the other hand, in the process of obtaining the interactive feedback score corresponding to the target interactive situation characterization data based on the multiple target interactive index data, the weight distribution parameters of the multiple target interactive index data are not randomly set. Instead, after using the review comments corresponding to the second target user among multiple review comments to be reviewed as the fourth target review comments to determine the second target resource type of the current resource targeted by the fourth target review comments, the weight distribution parameters of the multiple target interactive index data are obtained based on the second target resource type. In this way, it can better meet the personalized interactive needs of content production-based Internet products.

[0077] In some alternative embodiments, step S104, that is, "obtaining the submission sorting results of multiple comments to be reviewed based on the review records of multiple users and the interactive feedback results corresponding to the multiple users" may include:

[0078] Step S104-1: Obtaining the review passing rates of multiple users based on the review records of multiple users.

[0079] As described above, in the embodiments of the present disclosure, for each user among multiple users, the review record of this user can be used to record multiple comments published by this user in the historical stage and the passing situation of each comment among the multiple comments, so as to reflect the expected comment quality of this user.

[0080] For step S104-1, in one example, each user among multiple users can be used as the third target user, and the review passing rate of the third target user can be obtained based on the review record of the third target user. Among them, the review record of the third target user may include M1 review results. Here, M1≥0 and is an integer. Moreover, when M1 = 0, the review passing rate of the third target user can be set to 0; when M1≥1, the number of the first displayable review results can be determined from the M1 review results, denoted as M11, and M11 / M1 can be used as the review passing rate of the third target user. Among them, the first displayable review result is "passed", that is, the historical comment corresponding to the first displayable review result can be displayed.

[0081] For step S104-1, in another example, it can be implemented in the following manner:

[0082] First, each user among multiple users can be used as the first target user, the first target comment to be reviewed corresponding to the first target user can be determined from multiple comments to be reviewed, and the first target resource type of the current resource targeted by the first target comment to be reviewed can be determined. Among them, the first target resource type may be current affairs, social livelihood, entertainment gossip, audio-visual resources (such as movies, music), etc.

[0083] Thereafter, when the comment review record of the first target user is empty, the comment passing rate of the first target user can be set to 0; when the comment review record of the first target user is not empty, that is, including at least one comment review record, attempt to determine at least one target comment review result related to the first target resource type from the comment review record of the first target user. In addition, it should be noted that in this example, when there is no at least one target comment review result related to the first target resource type in the comment review record of the first target user, the comment passing rate of the first target user can also be set to 0; when there is at least one target comment review result related to the first target resource type in the comment review record of the first target user, the number of the at least one target comment review result can be denoted as M2. Among them, M2≥1 and is an integer.

[0084] Finally, based on at least one target comment review result, the comment passing rate of the first target user can be obtained.

[0085] In a specific example, the number of second displayable review results can be determined from the M2 target comment review results, denoted as M21, and M21 / M2 can be used as the comment passing rate of the first target user. Among them, the second displayable review result is "passed", that is, the historical comment corresponding to the second displayable review result can be displayed.

[0086] In the above example, each user among multiple users can be used as the first target user, determine the first target pending review comment corresponding to the first target user from multiple pending review comments, and determine the first target resource type of the current resource targeted by the first target pending review comment, and determine at least one target comment review result related to the first target resource type from the comment review record of the first target user, and then obtain the comment passing rate of the first target user based on at least one target comment review result. In this way, the relevance between the comment passing rate of the first target user and the first target resource type of the current resource targeted by the first target pending review comment (the pending review comment corresponding to the first target user among multiple pending review comments) can be increased, and the reliability of the comment passing rate of the first target user can be improved.

[0087] Step S104-2: Obtain the submission sorting result of multiple pending review comments based on the comment passing rates of multiple users and the interaction feedback results corresponding to multiple users.

[0088] In the above manner, in the embodiments of the present disclosure, based on the comment review records of multiple users, the comment passing rates of multiple users can be obtained, and based on the comment passing rates of multiple users and the corresponding interaction feedback results of multiple users, the submission sorting results of multiple comments to be reviewed can be obtained. In this process, no complex calculation logic is involved. Therefore, the acquisition efficiency of the submission sorting results can be improved.

[0089] Further, for step S104-2, in one example, it can be implemented in the following manner:

[0090] First, based on the comment passing rates of multiple users, the initial sorting results of multiple comments to be reviewed can be obtained.

[0091] For example, for each user among multiple users, the higher the comment passing rate of the user, the earlier the initial submission order can be set, that is, at the front end of the initial review queue.

[0092] Thereafter, in the case where the initial sorting results indicate that there are multiple equally-ordered comments to be reviewed with the same initial submission order among multiple comments to be reviewed, multiple first comment passing rates corresponding one-to-one to the multiple equally-ordered comments to be reviewed can be determined from the comment passing rates of multiple users, and multiple first interaction feedback results corresponding one-to-one to the multiple equally-ordered comments to be reviewed can be determined from the interaction feedback results corresponding to multiple users. Based on the multiple first comment passing rates and the multiple first interaction feedback results, the initial submission orders of the multiple equally-ordered comments to be reviewed in the initial sorting results are adjusted to obtain the submission sorting results.

[0093] In a specific example, when adjusting the initial submission orders of the multiple equally-ordered comments to be reviewed in the initial sorting results based on the multiple first comment passing rates and the multiple first interaction feedback results to obtain the submission sorting results, each equally-ordered comment to be reviewed among the multiple equally-ordered comments to be reviewed can be used as the second target comment to be reviewed, and the first comment passing rate corresponding to the second target comment to be reviewed and the first interaction feedback result corresponding to the second target comment to be reviewed are weighted and summed to obtain the priority index of the second target comment to be reviewed. Based on the priority indices of the multiple equally-ordered comments to be reviewed, the initial submission orders of the multiple equally-ordered comments to be reviewed in the initial sorting results are adjusted to obtain the submission sorting results. For example, the equally-ordered comment to be reviewed with a larger priority index among the multiple equally-ordered comments to be reviewed can be moved towards the front end of the initial review queue. Correspondingly, the equally-ordered comment to be reviewed with a smaller priority index among the multiple equally-ordered comments to be reviewed can be moved towards the rear end of the initial review queue to achieve the purpose of adjusting the initial submission orders of the multiple equally-ordered comments to be reviewed in the initial sorting results.

[0094] Further, in the above example, when obtaining the priority index of the second target review comment by performing a weighted sum of the first review passing rate corresponding to the second target review comment and the first interaction feedback result corresponding to the second target review comment, the first weight allocation parameter and the second weight allocation parameter can be obtained, and based on the first weight allocation parameter, the first review passing rate corresponding to the second target review comment is weighted to obtain the first weighted passing rate result, and based on the second weight allocation parameter, the first interaction feedback result corresponding to the second target review comment is weighted to obtain the first data weighted result, and then based on the first weighted passing rate result and the first data weighted result, the priority index of the second target review comment is obtained. Among them, weighting the first review passing rate corresponding to the second target review comment based on the first weight allocation parameter can be: calculating the product of the first weight allocation parameter and the first review passing rate corresponding to the second target review comment; weighting the first interaction feedback result corresponding to the second target review comment based on the second weight allocation parameter can be: calculating the product of the second weight allocation parameter and the first interaction feedback result corresponding to the second target review comment; obtaining the priority index of the second target review comment based on the first weighted passing rate result and the first data weighted result can be: taking the mean of the first weighted passing rate result and the first data weighted result as the priority index of the second target review comment; obtaining the priority index of the second target review comment based on the first weighted passing rate result and the first data weighted result can also be: taking the sum of the first weighted passing rate result and the first data weighted result as the priority index of the second target review comment.

[0095] Further, in the above examples, when obtaining the first weight allocation parameter and the second weight allocation parameter, the first weight allocation parameter can be obtained, and when the real-time interaction volume of the current resource targeted by the second target review comment meets the first preset low interaction volume requirement, a first parameter value smaller than the first weight allocation parameter can be obtained as the second weight allocation parameter; or, when the real-time interaction volume of the current resource targeted by the second target review comment meets the first preset high interaction volume requirement, a second parameter value greater than or equal to the first weight allocation parameter can be obtained as the second weight allocation parameter. Among them, the first weight allocation parameter can be a preset fixed weight allocation parameter. In actual implementation, after obtaining the first weight allocation parameter, when the real-time interaction volume of the current resource targeted by the second target review comment meets the first preset low interaction volume requirement, a first weight allocation reference value that is negatively correlated with the real-time interaction volume and smaller than the first weight allocation parameter can be obtained, and the difference between the first weight allocation parameter and the first weight allocation reference value can be used as the second weight allocation parameter. Correspondingly, when the real-time interaction volume of the current resource targeted by the second target review comment meets the first preset high interaction volume requirement, a second weight allocation reference value that is positively correlated with the real-time interaction volume and smaller than the first weight allocation parameter can be obtained, and the sum of the first weight allocation parameter and the second weight allocation reference value can be used as the second weight allocation parameter.

[0096] Moreover, after obtaining the first weight allocation parameter and the second weight allocation parameter, the first weight allocation parameter and the second weight allocation parameter can be scaled proportionally to ensure that the sum of the first weight allocation parameter and the second weight allocation parameter is 1.

[0097] In addition, it should be noted that in the above examples, the first preset low interaction volume requirement can be that the real-time interaction volume is less than the first preset interaction volume threshold; the first preset high interaction volume requirement can be that the real-time interaction volume is greater than or equal to the first preset interaction volume threshold, and the first preset interaction volume threshold can be specifically set according to application requirements, and the embodiments of the present disclosure do not limit this. In addition, the real-time interaction volume can be the interaction situation characterization data of the current resource targeted by the second target review comment, that is, the sum of interaction index data such as the comment volume, share volume, favorite volume, and like volume of the current resource targeted by the second target review comment.

[0098] Exemplarily, the multiple users include:

[0099] User A1, whose comment passing rate is 100%, and the corresponding interaction feedback result is 0.92;

[0100] User A2, whose comment passing rate is 95%, and the corresponding interaction feedback result is 0.98;

[0101] User A3, whose comment passing rate is 95%, and the corresponding interaction feedback result is 0.82;

[0102] User A4, whose comment passing rate is 95%, and the corresponding interaction feedback result is 0.80;

[0103] User A5, whose comment passing rate is 90%, and the corresponding interaction feedback result is 0.85.

[0104] Among multiple comments awaiting review (Comment a1 awaiting review, Comment a2 awaiting review, Comment a3 awaiting review, Comment a4 awaiting review, and Comment a5 awaiting review), User A1 corresponds to Comment a1 awaiting review, User A2 corresponds to Comment a2 awaiting review, User A3 corresponds to Comment a3 awaiting review, User A4 corresponds to Comment a4 awaiting review, and User A5 corresponds to Comment a5 awaiting review.

[0105] Based on the comment passing rates of multiple users, the initial sorting results of multiple comments awaiting review are as follows:

[0106] Comment a1 awaiting review > Comment a2 awaiting review = Comment a3 awaiting review = Comment a4 awaiting review > Comment a5 awaiting review

[0107] Among them, Comment a2 awaiting review, Comment a3 awaiting review, and Comment a4 awaiting review belong to multiple equally-ordered comments awaiting review with the same initial submission order. Therefore, multiple first comment passing rates corresponding one-to-one to multiple equally-ordered comments awaiting review can be determined from the comment passing rates of multiple users (that is, the first comment passing rate of 95% corresponding to Comment a2 awaiting review, the first comment passing rate of 95% corresponding to Comment a3 awaiting review, and the first comment passing rate of 95% corresponding to Comment a4 awaiting review), and multiple first interaction feedback results corresponding one-to-one to multiple equally-ordered comments awaiting review can be determined from the interaction feedback results corresponding to multiple users (that is, the first interaction feedback result of 0.98 corresponding to Comment a2 awaiting review, the first interaction feedback result of 0.82 corresponding to Comment a3 awaiting review, and the first interaction feedback result of 0.80 corresponding to Comment a4 awaiting review), and based on multiple first comment passing rates and multiple first interaction feedback results, the initial submission order of multiple equally-ordered comments awaiting review in the initial sorting results is adjusted to obtain the submission sorting results.

[0108] Suppose that the first review passing rate corresponding to the review to be audited a2 is 95%, and the first interaction feedback result corresponding to the review to be audited a2 is weighted and summed with 0.98, and the priority index of the review to be audited a2 obtained is 0.96; the first review passing rate corresponding to the review to be audited a3 is 95%, and the first interaction feedback result corresponding to the review to be audited a3 is weighted and summed with 0.82, and the priority index of the review to be audited a3 obtained is 0.98; the first review passing rate corresponding to the review to be audited a4 is 95%, and the first interaction feedback result corresponding to the review to be audited a4 is weighted and summed with 0.80, and the priority index of the review to be audited a4 obtained is 0.90. Then, based on the priority index of the review to be audited a2 being 0.96, the priority index of the review to be audited a3 being 0.98, and the priority index of the review to be audited a4 being 0.90, the initial submission order of the reviews to be audited a2, the review to be audited a3, and the review to be audited a4 in the initial sorting result is adjusted, and the obtained submission sorting result is:

[0109] Review to be audited a1 > Review to be audited a3 > Review to be audited a2 > Review to be audited a4 > Review to be audited a5

[0110] In the above example, in the first sorting stage, based on the review passing rates of multiple users, the initial sorting result of multiple reviews to be audited can be obtained. Then, in the case where the initial sorting result indicates that there are multiple equally-ordered reviews to be audited with the same initial submission order among multiple reviews to be audited, enter the second sorting stage, determine multiple first review passing rates corresponding one-to-one to the multiple equally-ordered reviews to be audited from the review passing rates of multiple users, and determine multiple first interaction feedback results corresponding one-to-one to the multiple equally-ordered reviews to be audited from the interaction feedback results corresponding to multiple users, and based on the multiple first review passing rates and the multiple first interaction feedback results, adjust the initial submission order of the multiple equally-ordered reviews to be audited in the initial sorting result to obtain the submission sorting result. Among them, in the first sorting stage, only based on the review passing rates of multiple users, the initial sorting result of multiple reviews to be audited is obtained. Therefore, it will not consume too much computing resources and can reduce the computing resource consumption of the entire sorting method.

[0111] Moreover, when adjusting the initial submission order of multiple equally-ordered comments awaiting review in the initial sorting result based on multiple first review passing rates and multiple first interaction feedback results to obtain the submission sorting result, each equally-ordered comment awaiting review in the multiple equally-ordered comments awaiting review can be used as the second target comment awaiting review. The first review passing rate corresponding to the second target comment awaiting review and the first interaction feedback result corresponding to the second target comment awaiting review are weighted and summed to obtain the priority index of the second target comment awaiting review. Then, based on the priority indexes of the multiple equally-ordered comments awaiting review, the initial submission order of the multiple equally-ordered comments awaiting review in the initial sorting result is adjusted to obtain the submission sorting result. In this process, no complex calculation logic is involved. Therefore, the efficiency of obtaining the submission sorting result can be improved. On the other hand, when weighting and summing the first review passing rate corresponding to the second target comment awaiting review and the first interaction feedback result corresponding to the second target comment awaiting review to obtain the priority index of the second target comment awaiting review, the first weight allocation parameter and the second weight allocation parameter can be obtained. Based on the first weight allocation parameter, the first review passing rate corresponding to the second target comment awaiting review is weighted to obtain the first weighted passing rate result, and based on the second weight allocation parameter, the first interaction feedback result corresponding to the second target comment awaiting review is weighted to obtain the first weighted data result. Then, based on the first weighted passing rate result and the first weighted data result, the priority index of the second target comment awaiting review is obtained. Among them, the first weight allocation parameter and the second weight allocation parameter are dynamically determined based on the real-time interaction volume of the current resource targeted by the second target comment awaiting review. In this way, when the real-time interaction volume of the current resource targeted by the second target comment awaiting review is small, the real-time interaction volume of the current resource targeted by the second target comment awaiting review can be increased as soon as possible; when the real-time interaction volume of the current resource targeted by the second target comment awaiting review is large, efforts are made to improve the real-time interaction quality of the current resource targeted by the second target comment awaiting review, thereby improving the effective exposure and dissemination efficiency of the current resource.

[0112] Further, for step S104-2, in another example, it can be implemented in the following way:

[0113] First, each comment awaiting review in the multiple comments awaiting review can be used as the third target comment awaiting review. The second review passing rate corresponding to the third target comment awaiting review is determined from the review passing rates of multiple users, and the second interaction feedback result corresponding to the third target comment awaiting review is determined from the interaction feedback results corresponding to multiple users.

[0114] After that, the second review passing rate corresponding to the third target comment awaiting review and the second interaction feedback result corresponding to the third target comment awaiting review are weighted and summed to obtain the priority index of the third target comment awaiting review.

[0115] Finally, based on the priority indices of multiple reviews to be audited, the review submission sorting results of multiple reviews to be audited can be obtained. For example, the reviews to be audited with larger priority indices among multiple reviews to be audited can be moved forward in the target review queue, and correspondingly, the reviews to be audited with smaller priority indices among multiple reviews to be audited can be moved backward in the target review queue.

[0116] Further, in the above example, when obtaining the priority index of the third target review to be audited by performing a weighted sum of the second review passing rate corresponding to the third target review to be audited and the second interaction feedback result corresponding to the third target review to be audited, the third weight allocation parameter and the fourth weight allocation parameter can be obtained, and based on the third weight allocation parameter, the second review passing rate corresponding to the third target review to be audited is weighted to obtain the second weighted passing rate result, and based on the fourth weight allocation parameter, the second interaction feedback result corresponding to the third target review to be audited is weighted to obtain the second weighted data result, and then based on the second weighted passing rate result and the second weighted data result, the priority index of the third target review to be audited is obtained. Among them, weighting the second review passing rate corresponding to the third target review to be audited based on the third weight allocation parameter can be: calculating the product of the third weight allocation parameter and the second review passing rate corresponding to the third target review to be audited; weighting the second interaction feedback result corresponding to the third target review to be audited based on the fourth weight allocation parameter can be: calculating the product of the fourth weight allocation parameter and the second interaction feedback result corresponding to the third target review to be audited; obtaining the priority index of the third target review to be audited based on the second weighted passing rate result and the second weighted data result can be: taking the mean of the second weighted passing rate result and the second weighted data result as the priority index of the third target review to be audited; obtaining the priority index of the third target review to be audited based on the second weighted passing rate result and the second weighted data result can also be: taking the sum of the second weighted passing rate result and the second weighted data result as the priority index of the third target review to be audited.

[0117] Further, in the above examples, when obtaining the third weight allocation parameter and the fourth weight allocation parameter, the third weight allocation parameter can be obtained, and when the real-time interaction volume of the current resource targeted by the third target review comment meets the first preset low interaction volume requirement, a third parameter value smaller than the third weight allocation parameter can be obtained as the fourth weight allocation parameter; or, when the real-time interaction volume of the current resource targeted by the third target review comment meets the second preset high interaction volume requirement, a fourth parameter value greater than or equal to the third weight allocation parameter can be obtained as the fourth weight allocation parameter. Among them, the third weight allocation parameter can be a preset fixed weight allocation parameter. In actual implementation, after obtaining the third weight allocation parameter, when the real-time interaction volume of the current resource targeted by the third target review comment meets the second preset low interaction volume requirement, a third weight allocation reference value that is negatively correlated with the real-time interaction volume and smaller than the third weight allocation parameter can be obtained, and the difference between the third weight allocation parameter and the third weight allocation reference value can be used as the fourth weight allocation parameter. Correspondingly, when the real-time interaction volume of the current resource targeted by the third target review comment meets the second preset high interaction volume requirement, a fourth weight allocation reference value that is positively correlated with the real-time interaction volume and smaller than the third weight allocation parameter can be obtained, and the sum of the third weight allocation parameter and the fourth weight allocation reference value can be used as the fourth weight allocation parameter.

[0118] Moreover, after obtaining the third weight allocation parameter and the fourth weight allocation parameter, the third weight allocation parameter and the fourth weight allocation parameter can be scaled proportionally to ensure that the sum of the third weight allocation parameter and the fourth weight allocation parameter is 1.

[0119] In addition, it should be noted that in the above examples, the second preset low interaction volume requirement can be that the real-time interaction volume is less than the second preset interaction volume threshold; the second preset high interaction volume requirement can be that the real-time interaction volume is greater than or equal to the second preset interaction volume threshold, and the second preset interaction volume threshold can be specifically set according to application requirements, and the embodiments of the present disclosure do not limit this. In addition, the real-time interaction volume can be the interaction situation characterization data of the current resource targeted by the third target review comment, that is, the sum of interaction index data such as the comment volume, share volume, favorite volume, and like volume of the current resource targeted by the third target review comment.

[0120] Exemplarily, the multiple users include:

[0121] User A1, whose comment passing rate is 100%, and the corresponding interaction feedback result is 0.92;

[0122] User A2, whose comment passing rate is 95%, and the corresponding interaction feedback result is 0.98;

[0123] User A3, whose comment passing rate is 95%, and the corresponding interactive feedback result is 0.82;

[0124] User A4, whose comment passing rate is 95%, and the corresponding interactive feedback result is 0.80;

[0125] User A5, whose comment passing rate is 90%, and the corresponding interactive feedback result is 0.85.

[0126] Among multiple comments awaiting review (Comment a1 awaiting review, Comment a2 awaiting review, Comment a3 awaiting review, Comment a4 awaiting review, and Comment a5 awaiting review), User A1 corresponds to Comment a1 awaiting review, User A2 corresponds to Comment a2 awaiting review, User A3 corresponds to Comment a3 awaiting review, User A4 corresponds to Comment a4 awaiting review, and User A5 corresponds to Comment a5 awaiting review.

[0127] Suppose, a weighted sum is performed on the second comment passing rate of 100% corresponding to Comment a1 awaiting review and the second interactive feedback result of 0.92 corresponding to Comment a1 awaiting review, and the priority index of Comment a1 awaiting review obtained is 0.98; a weighted sum is performed on the second comment passing rate of 95% corresponding to Comment a2 awaiting review and the second interactive feedback result of 0.98 corresponding to Comment a2 awaiting review, and the priority index of Comment a2 awaiting review obtained is 0.92; a weighted sum is performed on the second comment passing rate of 95% corresponding to Comment a3 awaiting review and the second interactive feedback result of 0.82 corresponding to Comment a3 awaiting review, and the priority index of Comment a3 awaiting review obtained is 0.96; a weighted sum is performed on the second comment passing rate of 95% corresponding to Comment a4 awaiting review and the second interactive feedback result of 0.80 corresponding to Comment a4 awaiting review, and the priority index of Comment a4 awaiting review obtained is 0.90; a weighted sum is performed on the second comment passing rate of 90% corresponding to Comment a5 awaiting review and the second interactive feedback result of 0.85 corresponding to Comment a5 awaiting review, and the priority index of Comment a5 awaiting review obtained is 0.88. Then, based on the priority index of Comment a1 awaiting review, the priority index of Comment a2 awaiting review, the priority index of Comment a3 awaiting review, the priority index of Comment a4 awaiting review, and the priority index of Comment a5 awaiting review, the submission sorting result of Comment a1 awaiting review, Comment a2 awaiting review, Comment a3 awaiting review, Comment a4 awaiting review, and Comment a5 awaiting review is:

[0128] Comment a1 awaiting review > Comment a3 awaiting review > Comment a2 awaiting review > Comment a4 awaiting review > Comment a5 awaiting review

[0129] In the above example, each of the multiple comments awaiting review can be used as the third target comment awaiting review. The second comment approval rate corresponding to the third target comment awaiting review can be determined from the comment approval rates of multiple users, and the second interaction feedback result corresponding to the third target comment awaiting review can be determined from the interaction feedback results corresponding to multiple users. Then, a weighted sum of the second comment approval rate corresponding to the third target comment awaiting review and the second interaction feedback result corresponding to the third target comment awaiting review is calculated to obtain the priority index of the third target comment awaiting review. Based on the priority indices of the multiple comments awaiting review, the submission sorting result of the multiple comments awaiting review is obtained. That is to say, in the above example, the priority index of the third target comment awaiting review is obtained by combining the second comment approval rate corresponding to the third target comment awaiting review and the second interaction feedback result corresponding to the third target comment awaiting review, which can ensure the reliability of its priority index and thus improve the rationality of the submission sorting result.

[0130] Moreover, when calculating a weighted sum of the second comment approval rate corresponding to the third target comment awaiting review and the second interaction feedback result corresponding to the third target comment awaiting review to obtain the priority index of the third target comment awaiting review, the third weight allocation parameter and the fourth weight allocation parameter can be obtained. Based on the third weight allocation parameter, the second comment approval rate corresponding to the third target comment awaiting review is weighted to obtain the weighted result of the second approval rate, and based on the fourth weight allocation parameter, the second interaction feedback result corresponding to the third target comment awaiting review is weighted to obtain the weighted result of the second data. Then, based on the weighted result of the second approval rate and the weighted result of the second data, the priority index of the third target comment awaiting review is obtained. Among them, the third weight allocation parameter and the fourth weight allocation parameter are dynamically determined based on the real-time interaction volume of the current resource targeted by the third target comment awaiting review. In this way, when the real-time interaction volume of the current resource targeted by the third target comment awaiting review is small, the real-time interaction volume of the current resource targeted by the third target comment awaiting review can be increased as soon as possible; when the real-time interaction volume of the current resource targeted by the third target comment awaiting review is large, efforts are made to improve the real-time interaction quality of the current resource targeted by the third target comment awaiting review, thereby improving the effective exposure and dissemination efficiency of the current resource.

[0131] Next, combined with Figure 2 , the complete process of a comment sorting method provided by an embodiment of the present disclosure will be described.

[0132] First, multiple comments awaiting review can be obtained, and the multiple comments awaiting review are respectively published by multiple users, that is, the multiple comments awaiting review correspond one-to-one with multiple users.

[0133] In one example, at least one popular resource can be determined from multiple candidate resources at a target time interval, and multiple target comment messages can be determined from the comment information collection of at least one popular resource as the primary selected comments, so as to obtain multiple primary selected comments, and then multiple comments to be reviewed can be obtained based on the multiple primary selected comments.

[0134] The above process can refer to the relevant description of the corresponding step (that is, step S101) in the foregoing embodiment of the comment sorting method, and will not be elaborated here.

[0135] After that, the comment review records of multiple users can be obtained.

[0136] The above process can refer to the relevant description of the corresponding step (that is, step S102) in the foregoing embodiment of the comment sorting method, and will not be elaborated here.

[0137] Next, using the interactive feedback result acquisition system, the interactive feedback results corresponding to multiple users are obtained.

[0138] In one example, multiple data collection dimensions can be determined, and each user among the multiple users is used as a second target user, and the interaction situation characterization data of the second target user is obtained from multiple data collection dimensions respectively, so as to obtain multiple interaction situation characterization data, and then the interactive feedback result is obtained based on the multiple interaction situation characterization data.

[0139] The above process can refer to the relevant description of the corresponding step (that is, step S103) in the foregoing embodiment of the comment sorting method, and will not be elaborated here.

[0140] Finally, using the sorting system, based on the comment review records of multiple users and the interactive feedback results corresponding to multiple users, the submission sorting results of multiple comments to be reviewed are obtained.

[0141] In one example, the comment passing rate of multiple users can be obtained based on the comment review records of multiple users, and the submission sorting results of multiple comments to be reviewed are obtained based on the comment passing rate of multiple users and the interactive feedback results corresponding to multiple users.

[0142] The above process can refer to the relevant description of the corresponding step (that is, step S104) in the foregoing embodiment of the comment sorting method, and will not be elaborated here.

[0143] After obtaining the submission sorting results of multiple comments to be reviewed, accordingly, multiple comments to be reviewed can be pushed to the comment review system, so that in the comment review system, the multiple comments to be reviewed are reviewed in a combination of manual review and machine filtering, and then the comments that pass the review are displayed, so as to ensure the quality of the displayed comments.

[0144] Please refer to Figure 3, which is a schematic diagram of an application scenario of a comment sorting method provided by an embodiment of the present disclosure.

[0145] The comment sorting method provided by an embodiment of the present disclosure is applied to an electronic device. Among them, the electronic device can be a server, or a workbench, a mainframe computer, a conventional computer (such as a desktop computer, a laptop computer, an in-vehicle computer, etc.) or other similar computing devices.

[0146] Here, the electronic device is used to:

[0147] Obtain multiple comments to be reviewed; among them, the multiple comments to be reviewed correspond to multiple users one by one;

[0148] Obtain the comment review records of multiple users;

[0149] Obtain the interactive feedback results corresponding to multiple users;

[0150] Based on the comment review records of multiple users and the interactive feedback results corresponding to multiple users, obtain the submission sorting results of multiple comments to be reviewed.

[0151] It should be noted that in the embodiments of the present disclosure, Figure 3 The shown application scenario schematic diagram is only illustrative and not restrictive. Those skilled in the art can make various obvious changes and / or replacements based on Figure 3 Examples, and the obtained technical solutions still fall within the scope of the disclosure of the embodiments of the present disclosure.

[0152] To better implement the comment sorting method, an embodiment of the present disclosure also provides a comment sorting device, which can be integrated into an electronic device. Among them, the electronic device can be a server, or a workbench, a mainframe computer, a conventional computer (such as a desktop computer, a laptop computer, an in-vehicle computer, etc.) or other similar computing devices. Hereinafter, with reference to Figure 4 The shown schematic structural block diagram, a comment sorting device 400 provided by an embodiment of the disclosure will be described.

[0153] The comment sorting device 400 includes:

[0154] A to-be-reviewed comment acquisition unit 401, configured to obtain multiple comments to be reviewed; among them, the multiple comments to be reviewed correspond to multiple users one by one;

[0155] A comment review record acquisition unit 402, configured to obtain the comment review records of multiple users;

[0156] An interactive feedback result acquisition unit 403, configured to obtain the interactive feedback results corresponding to multiple users;

[0157] The submission sorting result acquisition unit 404 is configured to obtain the submission sorting results of multiple comments to be reviewed based on the comment review records of multiple users and the interactive feedback results corresponding to the multiple users.

[0158] In some alternative embodiments, the submission sorting result acquisition unit 404 is configured to:

[0159] Based on the comment review records of multiple users, obtain the comment passing rates of the multiple users;

[0160] Based on the comment passing rates of the multiple users and the interactive feedback results corresponding to the multiple users, obtain the submission sorting results of multiple comments to be reviewed.

[0161] In some alternative embodiments, the submission sorting result acquisition unit 404 is configured to:

[0162] Take each user among the multiple users as the first target user, determine the first target comment to be reviewed corresponding to the first target user from the multiple comments to be reviewed, and determine the first target resource type of the current resource targeted by the first target comment to be reviewed;

[0163] From the comment review records of the first target user, determine at least one target comment review result related to the first target resource type;

[0164] Based on at least one target comment review result, obtain the comment passing rate of the first target user.

[0165] In some alternative embodiments, the submission sorting result acquisition unit 404 is configured to:

[0166] Based on the comment passing rates of multiple users, obtain the initial sorting results of multiple comments to be reviewed;

[0167] In the case where the initial sorting results indicate that there are multiple equally-ordered comments to be reviewed with the same initial submission order among the multiple comments to be reviewed, determine multiple first comment passing rates corresponding one-to-one to the multiple equally-ordered comments to be reviewed from the comment passing rates of multiple users, and determine multiple first interactive feedback results corresponding one-to-one to the multiple equally-ordered comments to be reviewed from the interactive feedback results corresponding to the multiple users;

[0168] Based on the multiple first comment passing rates and the multiple first interactive feedback results, adjust the initial submission order of the multiple equally-ordered comments to be reviewed in the initial sorting results to obtain the submission sorting results.

[0169] In some alternative embodiments, the submission sorting result acquisition unit 404 is configured to:

[0170] Taking each of the multiple equally-ordered comments awaiting review as the second target comment awaiting review, perform a weighted sum on the first comment approval rate corresponding to the second target comment awaiting review and the first interaction feedback result corresponding to the second target comment awaiting review to obtain the priority index of the second target comment awaiting review;

[0171] Based on the priority indexes of the multiple equally-ordered comments awaiting review, adjust the initial submission order of the multiple equally-ordered comments in the initial sorting result to obtain the submission sorting result.

[0172] In some alternative embodiments, the submission sorting result obtaining unit 404 is configured to:

[0173] Obtain a first weight distribution parameter and a second weight distribution parameter;

[0174] Based on the first weight distribution parameter, perform a weighted process on the first comment approval rate corresponding to the second target comment awaiting review to obtain a first weighted approval rate result;

[0175] Based on the second weight distribution parameter, perform a weighted process on the first interaction feedback result corresponding to the second target comment awaiting review to obtain a first weighted data result;

[0176] Based on the first weighted approval rate result and the first weighted data result, obtain the priority index of the second target comment awaiting review.

[0177] In some alternative embodiments, the submission sorting result obtaining unit 404 is configured to:

[0178] Obtain a first weight distribution parameter;

[0179] When the real-time interaction volume of the current resource targeted by the second target comment awaiting review meets the first preset low interaction volume requirement, obtain a first parameter value smaller than the first weight distribution parameter as the second weight distribution parameter;

[0180] Alternatively, when the real-time interaction volume of the current resource targeted by the second target comment awaiting review meets the first preset high interaction volume requirement, obtain a second parameter value greater than or equal to the first weight distribution parameter as the second weight distribution parameter.

[0181] In some alternative embodiments, the submission sorting result obtaining unit 404 is configured to:

[0182] Taking each of the multiple comments awaiting review as the third target comment awaiting review, determine the second comment approval rate corresponding to the third target comment awaiting review from the comment approval rates of multiple users, and determine the second interaction feedback result corresponding to the third target comment awaiting review from the interaction feedback results corresponding to multiple users;

[0183] Perform a weighted sum of the second review passing rate corresponding to the third target review to be audited and the second interaction feedback result corresponding to the third target review to be audited to obtain the priority index of the third target review to be audited;

[0184] Based on the priority indices of multiple reviews to be audited, obtain the submission sorting result of the multiple reviews to be audited.

[0185] In some alternative embodiments, the submission sorting result acquisition unit 404 is configured to:

[0186] Obtain a third weight allocation parameter and a fourth weight allocation parameter;

[0187] Based on the third weight allocation parameter, perform a weighted process on the second review passing rate corresponding to the third target review to be audited to obtain a second passing rate weighted result;

[0188] Based on the fourth weight allocation parameter, perform a weighted process on the second interaction feedback result corresponding to the third target review to be audited to obtain a second data weighted result;

[0189] Based on the second passing rate weighted result and the second data weighted result, obtain the priority index of the third target review to be audited.

[0190] In some alternative embodiments, the submission sorting result acquisition unit 404 is configured to:

[0191] Obtain a third weight allocation parameter;

[0192] When the real-time interaction volume of the current resource targeted by the third target review to be audited meets the first preset low interaction volume requirement, obtain a third parameter value smaller than the third weight allocation parameter as the fourth weight allocation parameter;

[0193] Alternatively, when the real-time interaction volume of the current resource targeted by the third target review to be audited meets the second preset high interaction volume requirement, obtain a fourth parameter value greater than or equal to the third weight allocation parameter as the fourth weight allocation parameter.

[0194] In some alternative embodiments, the review to be audited acquisition unit 401 is configured to:

[0195] Determine at least one popular resource from multiple candidate resources at a target time interval;

[0196] Determine multiple target comment information from the comment information collections of at least one popular resource as primary selection reviews to obtain multiple primary selection reviews;

[0197] Based on the multiple primary selection reviews, obtain multiple reviews to be audited.

[0198] In some alternative embodiments, the interactive feedback result acquisition unit 403 is configured to:

[0199] Determine multiple data collection dimensions;

[0200] Take each user among the multiple users as a second target user, and respectively obtain the characterization data of the interaction situation of the second target user from multiple data collection dimensions, so as to obtain multiple characterization data of the interaction situation;

[0201] Based on the multiple characterization data of the interaction situation, obtain an interactive feedback result.

[0202] In some alternative embodiments, the interactive feedback result acquisition unit 403 is configured to:

[0203] Take each characterization data of the interaction situation among the multiple characterization data of the interaction situation as the target characterization data of the interaction situation, and based on the target characterization data of the interaction situation, determine multiple target interaction index data;

[0204] Based on the multiple target interaction index data, obtain an interactive feedback score corresponding to the target characterization data of the interaction situation;

[0205] Based on the multiple interactive feedback scores corresponding one-to-one to the multiple characterization data of the interaction situation, obtain an interactive feedback result.

[0206] In some alternative embodiments, the interactive feedback result acquisition unit 403 is configured to:

[0207] Determine the second target resource type of the current resource targeted by the fourth target review comment; wherein, the fourth target review comment is the review comment corresponding to the second target user among the multiple review comments;

[0208] Based on the second target resource type, obtain the weight distribution parameters of the multiple target interaction index data;

[0209] Based on the weight distribution parameters of the multiple target interaction index data, perform weighted summation on the multiple target interaction index data to obtain an interactive feedback score corresponding to the target characterization data of the interaction situation.

[0210] In the embodiments of the present disclosure, for the specific functions and examples of each unit in the comment sorting device 400, reference may be made to the relevant descriptions of the corresponding steps in the foregoing comment sorting method embodiments, which will not be elaborated herein.

[0211] In the technical solution of the present disclosure, the acquisition, storage, and application of the user's personal information involved all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0212] According to the embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0213] Figure 5 FIG. 2 shows a schematic structural block diagram of an exemplary electronic device 500 that can be used to implement embodiments of the present disclosure. The electronic device 500 is intended to represent various forms of digital computers, such as in-vehicle computing devices, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device 500 can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0214] As Figure 5 shown, the electronic device 500 includes a computing unit 501 that can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0215] A plurality of components in the electronic device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of renderers, speakers, etc.; a storage unit 508, such as a magnetic disk, an optical disc, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the electronic device 500 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0216] The computing unit 501 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 executes the various methods and processes described above, such as the comment ranking method. For example, in some embodiments, the comment ranking method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the comment ranking method described above can be executed. Alternatively, in other embodiments, the computing unit 501 can be configured as the comment ranking method by any other suitable means (e.g., by means of firmware).

[0217] Various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuit systems, integrated circuit systems, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), System On Chip (SOC) systems, Complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0218] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data optimization devices, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowchart and / or block diagram are implemented. The program codes can be executed entirely on the machine, partially on the machine, executed partially on the machine and partially on a remote machine as an independent software package, or executed entirely on a remote machine or server.

[0219] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a RAM, a ROM, an erasable programmable read-only memory (EPROM) or flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0220] In order to provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a rendering device for rendering information to the user (e.g., a cathode ray tube (CRT) renderer or a liquid crystal display (LCD) renderer); and a keyboard and a pointing device (e.g., a mouse or a trackball), through which the user can provide input to the computer. Other kinds of devices are also used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0221] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN), and the Internet.

[0222] A computer system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, or a server of a distributed system, or a server incorporating blockchain.

[0223] Embodiments of the present disclosure also provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute a comment ranking method.

[0224] Embodiments of the present disclosure also provide a computer program product, including a computer program which, when executed by a processor, implements a comment ranking method.

[0225] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and this is not limited herein. In addition, in the present disclosure, relational terms such as "first", "second", "third", etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Further, in the present disclosure, "a plurality" can be understood to mean at least two.

[0226] The foregoing specific embodiments do not limit the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the principles of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

1. A comment sorting method, comprising: Obtaining multiple comments to be reviewed; wherein, the multiple comments to be reviewed correspond to multiple users one by one; Obtaining the comment review records of the multiple users; Obtaining the interactive feedback results corresponding to the multiple users; Based on the comment review records of the multiple users and the interactive feedback results corresponding to the multiple users, obtaining the submission sorting results of the multiple comments to be reviewed.

2. The method according to claim 1, wherein The obtaining the submission sorting results of the multiple comments to be reviewed based on the comment review records of the multiple users and the interactive feedback results corresponding to the multiple users includes: Based on the comment review records of the multiple users, obtaining the comment passing rates of the multiple users; Based on the comment passing rates of the multiple users and the interactive feedback results corresponding to the multiple users, obtaining the submission sorting results of the multiple comments to be reviewed.

3. The method according to claim 2, wherein The obtaining the comment passing rates of the multiple users based on the comment review records of the multiple users includes: Regarding each user among the multiple users as a first target user, determining a first target comment to be reviewed corresponding to the first target user from the multiple comments to be reviewed, and determining a first target resource type of the current resource targeted by the first target comment to be reviewed; Determining at least one target comment review result related to the first target resource type from the comment review records of the first target user; Based on the at least one target comment review result, obtaining the comment passing rate of the first target user.

4. The method according to claim 2 or 3, wherein The obtaining the submission sorting results of the multiple comments to be reviewed based on the comment passing rates of the multiple users and the interactive feedback results corresponding to the multiple users includes: Based on the comment passing rates of the multiple users, obtaining an initial sorting result of the multiple comments to be reviewed; In the case where the initial sorting result indicates that there are multiple equally-ordered comments to be reviewed with the same initial submission order among the multiple comments to be reviewed, determining multiple first comment passing rates corresponding one by one to the multiple equally-ordered comments to be reviewed from the comment passing rates of the multiple users, and determining multiple first interactive feedback results corresponding one by one to the multiple equally-ordered comments to be reviewed from the interactive feedback results corresponding to the multiple users; Based on the multiple first comment passing rates and the multiple first interactive feedback results, adjusting the initial submission order of the multiple equally-ordered comments to be reviewed in the initial sorting result to obtain the submission sorting result.

5. The method according to claim 4, wherein The adjusting the initial submission order of the multiple equally-ordered comments to be reviewed in the initial sorting result based on the multiple first comment passing rates and the multiple first interactive feedback results to obtain the submission sorting result includes: Regarding each equally-ordered comment to be reviewed among the multiple equally-ordered comments to be reviewed as a second target comment to be reviewed, performing a weighted sum of the first comment passing rate corresponding to the second target comment to be reviewed and the first interactive feedback result corresponding to the second target comment to be reviewed to obtain a priority index of the second target comment to be reviewed; Based on the priority indices of the multiple equally-ordered reviews awaiting review, adjust the initial submission order of the multiple equally-ordered reviews awaiting review in the initial sorting result to obtain the submission sorting result.

6. The method according to claim 5, wherein, The weighted summation of the first review passing rate corresponding to the second target review awaiting review and the first interaction feedback result corresponding to the second target review awaiting review to obtain the priority index of the second target review awaiting review includes: Obtain a first weight assignment parameter and a second weight assignment parameter; Based on the first weight assignment parameter, perform weighted processing on the first review passing rate corresponding to the second target review awaiting review to obtain a first weighted passing rate result; Based on the second weight assignment parameter, perform weighted processing on the first interaction feedback result corresponding to the second target review awaiting review to obtain a first weighted data result; Based on the first weighted passing rate result and the first weighted data result, obtain the priority index of the second target review awaiting review.

7. The method according to claim 6, wherein The obtaining of the first weight assignment parameter and the second weight assignment parameter includes: Obtain a first weight assignment parameter; When the real-time interaction volume of the current resource targeted by the second target review awaiting review meets the first preset low interaction volume requirement, obtain a first parameter value smaller than the first weight assignment parameter as the second weight assignment parameter; Or, when the real-time interaction volume of the current resource targeted by the second target review awaiting review meets the first preset high interaction volume requirement, obtain a second parameter value greater than or equal to the first weight assignment parameter as the second weight assignment parameter.

8. The method according to claim 2 or 3, wherein The obtaining of the submission sorting result of the multiple reviews awaiting review based on the review passing rates of the multiple users and the interaction feedback results corresponding to the multiple users includes: Take each review awaiting review in the multiple reviews awaiting review as a third target review awaiting review, determine the second review passing rate corresponding to the third target review awaiting review from the review passing rates of the multiple users, and determine the second interaction feedback result corresponding to the third target review awaiting review from the interaction feedback results corresponding to the multiple users; Perform weighted summation on the second review passing rate corresponding to the third target review awaiting review and the second interaction feedback result corresponding to the third target review awaiting review to obtain the priority index of the third target review awaiting review; Based on the priority indices of the multiple reviews awaiting review, obtain the submission sorting result of the multiple reviews awaiting review.

9. The method according to claim 8, wherein The weighted summation of the second review passing rate corresponding to the third target review awaiting review and the second interaction feedback result corresponding to the third target review awaiting review to obtain the priority index of the third target review awaiting review includes: Obtain a third weight assignment parameter and a fourth weight assignment parameter; Based on the third weight assignment parameter, perform weighted processing on the second review passing rate corresponding to the third target review awaiting review to obtain a second weighted passing rate result; Based on the fourth weight assignment parameter, perform weighted processing on the second interaction feedback result corresponding to the third target review awaiting review to obtain a second weighted data result; Based on the weighted result of the second passing rate and the weighted result of the second data, obtain the priority index of the third target review comment to be reviewed.

10. The method according to claim 9, wherein, The obtaining of the third weight allocation parameter and the fourth weight allocation parameter includes: Obtain the third weight allocation parameter; When the real-time interaction volume of the current resource targeted by the third target review comment to be reviewed meets the first preset low interaction volume requirement, obtain a third parameter value smaller than the third weight allocation parameter as the fourth weight allocation parameter; Alternatively, when the real-time interaction volume of the current resource targeted by the third target review comment to be reviewed meets the second preset high interaction volume requirement, obtain a fourth parameter value greater than or equal to the third weight allocation parameter as the fourth weight allocation parameter.

11. The method according to claim 1, wherein, The obtaining of multiple review comments to be reviewed includes: Determine at least one popular resource from multiple candidate resources at a target time interval; Determine multiple target comment information from the comment information collection of the at least one popular resource as the primary selected comments to obtain multiple primary selected comments; Based on the multiple primary selected comments, obtain the multiple review comments to be reviewed.

12. The method according to claim 1, wherein The obtaining of the interaction feedback results of the multiple users includes: Determine multiple data collection dimensions; Take each user in the multiple users as the second target user, and respectively obtain the interaction situation characterization data of the second target user from the multiple data collection dimensions to obtain multiple interaction situation characterization data; Based on the multiple interaction situation characterization data, obtain the interaction feedback result.

13. The method according to claim 12, wherein, The obtaining of the interaction feedback result based on the multiple interaction situation characterization data includes: Take each interaction situation characterization data in the multiple interaction situation characterization data as the target interaction situation characterization data, and based on the target interaction situation characterization data, determine multiple target interaction index data; Based on the multiple target interaction index data, obtain the interaction feedback score corresponding to the target interaction situation characterization data; Based on the multiple interaction feedback scores corresponding one-to-one to the multiple interaction situation characterization data, obtain the interaction feedback result.

14. The method according to claim 13, wherein, The obtaining of the interaction feedback score corresponding to the target interaction situation characterization data based on the multiple target interaction index data includes: Determine the second target resource type of the current resource targeted by the fourth target review comment to be reviewed; wherein, the fourth target review comment to be reviewed is the review comment to be reviewed corresponding to the second target user among the multiple review comments to be reviewed; Based on the second target resource type, obtain the weight allocation parameter of the multiple target interaction index data; Based on the weight allocation parameter of the multiple target interaction index data, perform weighted summation on the multiple target interaction index data to obtain the interaction feedback score corresponding to the target interaction situation characterization data.

15. A priority ranking device, comprising: A review comment to be reviewed acquisition unit, configured to acquire multiple review comments to be reviewed; wherein, the multiple review comments to be reviewed correspond one-to-one to multiple users; A review audit record acquisition unit, configured to acquire the review audit records of the multiple users; An interaction feedback result acquisition unit, configured to acquire the interaction feedback results corresponding to the multiple users; A submission sorting result acquisition unit for obtaining a submission sorting result of the multiple comments to be reviewed based on the review records of the multiple users' comments and the interactive feedback results corresponding to the multiple users.

16. An electronic device, comprising: At least one processor; A memory communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method according to any one of claims 1 to 14.

17. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 14.

18. A computer program product, comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 14.

Images