Information processing method, device, electronic device and storage medium

Abstract

The embodiments of the present application disclose an information processing method, an apparatus, an electronic device, and a storage medium. In the process of screening objects to be reviewed based on the values ​​of the target attributes of the objects to be reviewed and the target value of the screening threshold, and reviewing the screened objects to be reviewed, the target value of the screening threshold is automatically updated according to the number of backlog objects to be reviewed and the correspondence between multiple preset backlog intervals and the values ​​of the screening threshold, thereby realizing automatic updating of the screening threshold and eliminating the need to manually update the target value of the screening threshold, thereby overcoming the problem that manually setting the screening threshold is prone to unreasonable screening threshold setting and occupies human resources.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and more specifically, to an information processing method, device, electronic device, and storage medium. Background Art

[0002] With the advent of mobile internet, users are posting more and more information to online platforms. For operational needs, online platform operators need to manually review some of the objects posted to the online platforms. The specific objects that require review are determined based on the object's attributes and screening thresholds.

[0003] At present, the values ​​of the above-mentioned screening thresholds are set manually, which may easily lead to the problem that the backlog of the screened content to be reviewed is too much or too little due to the unreasonable setting of the screening threshold values. The value of the screening threshold needs to be adjusted multiple times, resulting in a waste of resources. For example, if the backlog of content to be reviewed is too large, the content that cannot be reviewed will waste storage and computing resources. If the backlog of content to be reviewed is too small, it may not be enough for the reviewers to review, resulting in idle staff. In addition, manually adjusting the value of the screening threshold will also occupy human resources.

[0004] Therefore, how to overcome resource waste has become a technical problem that needs to be solved urgently. Summary of the Invention

[0005] The purpose of this application is to provide an information processing method, device, electronic device, and storage medium, including the following technical solutions:

[0006] An information processing method, characterized in that the method comprises:

[0007] Based on the target attribute of the object to be screened and the screening threshold, the object to be screened whose value of the target attribute is greater than the target value of the screening threshold is screened out from the set of objects to be screened as the object to be reviewed;

[0008] If a target indication message for any object to be reviewed is obtained, the object to be reviewed is determined as a reviewed object; the target indication message indicates that the review of the object to be reviewed has been completed;

[0009] When a preset condition for updating the screening threshold is met, obtaining a backlog of the objects to be reviewed;

[0010] Searching for a target backlog interval to which the backlog of the object to be reviewed belongs in a plurality of pre-configured backlog intervals; wherein different backlog intervals correspond to different values ​​of the screening threshold; the intersection of different backlog intervals is zero, and the union of all backlog intervals constitutes a continuous backlog interval; if the minimum value of a first backlog interval is greater than the minimum value of a second backlog interval, then the value of the screening threshold corresponding to the first backlog interval is greater than the value of the screening threshold corresponding to the second backlog interval; the first backlog interval and the second backlog interval are any two backlog intervals among the plurality of backlog intervals;

[0011] The value of the screening threshold corresponding to the target backlog interval is used as the target value of the screening threshold.

[0012] Optionally, in the above method, satisfying a preset condition for updating the screening threshold includes:

[0013] a preset adjustment period for reaching said screening threshold;

[0014] or,

[0015] The duration during which the backlog of objects to be reviewed is outside the preset backlog range reaches a first preset duration.

[0016] Optionally, the method further includes filtering out, from the set of objects to be screened, objects whose target attribute values ​​are greater than the target value of the screening threshold based on the target attribute of the objects to be screened and the screening threshold as objects to be reviewed, including:

[0017] Based on a first target attribute of the object to be screened corresponding to a target audit channel and a first screening threshold corresponding to the target audit channel, screen out the objects to be screened whose values ​​of the first target attribute are greater than a target value of the first screening threshold from the set of objects to be screened as the objects to be screened for the target audit channel; the target audit channel is any audit channel among a plurality of preset audit channels; different audit channels have different target attributes corresponding to them, or different audit channels have different screening threshold values ​​corresponding to them;

[0018] Accordingly, obtaining the backlog of objects to be reviewed includes: obtaining the backlog of objects to be reviewed in the target review channel;

[0019] The searching for the target backlog interval to which the backlog of the object to be reviewed belongs in the pre-configured multiple backlog intervals includes: searching for the target backlog interval to which the backlog of the object to be reviewed of the target review channel belongs in the pre-configured multiple backlog intervals corresponding to the target review channel.

[0020] The above method may optionally further include:

[0021] When the update condition of the correspondence between different backlog intervals in the multiple backlog intervals and different values ​​of the screening threshold is met, the correspondence between different backlog intervals in the multiple backlog intervals and different values ​​of the screening threshold is updated based on the target attributes of the objects to be reviewed that are marked as reviewed within the second preset time period.

[0022] Optionally, the method further includes updating the correspondence between different backlog intervals in the plurality of backlog intervals and different values ​​of the screening threshold based on the target attributes of the pending objects marked as reviewed within the second preset time period, including:

[0023] Obtaining the median of the values ​​of the target attributes of the objects to be reviewed that are marked as reviewed within the second preset time period when they are determined to be the objects to be reviewed;

[0024] Using the median as a first value of the screening threshold, establishing a correspondence between the first value and a third backlog interval among the multiple backlog intervals; the third backlog interval is a backlog interval defined according to operational requirements;

[0025] Based on the correspondence between the third backlog interval and the first value, a correspondence between non-third backlog intervals in the multiple backlog intervals and other values ​​of the screening threshold is determined.

[0026] Optionally, in the above method, obtaining the median of the target attributes of the objects to be reviewed that are marked as reviewed within the second preset time period when they are determined to be the objects to be reviewed includes:

[0027] sorting the values ​​of the target attributes of the objects to be reviewed that are marked as reviewed within the second preset time period when they are determined to be the objects to be reviewed;

[0028] The median of the target attributes of the objects to be reviewed that are marked as reviewed within the second preset time period when they are determined to be the objects to be reviewed is determined based on the values ​​ranked in the middle.

[0029] Optionally, in the above method, determining, based on the correspondence between the third backlog interval and the first value, the correspondence between non-third backlog intervals in the multiple backlog intervals and other values ​​of the screening threshold value includes:

[0030] Taking the third backlog interval and the first value as a reference, if the minimum value of any non-third backlog interval among the multiple backlog intervals increases by a first increment relative to the minimum value of the third backlog interval, the first value is increased by a second increment and used as the value of the screening threshold corresponding to any non-third backlog interval; the second increment is positively correlated with the first increment; if the minimum value of any non-third backlog interval among the multiple backlog intervals decreases by the first increment relative to the minimum value of the third backlog interval, the first value is reduced by the second increment and used as the value of the screening threshold corresponding to any non-third backlog interval.

[0031] An information processing device, comprising:

[0032] A screening module is used to screen out, based on a target attribute of the object to be screened and a screening threshold, objects to be screened whose values ​​of the target attribute are greater than a target value of the screening threshold from the set of objects to be screened as objects to be reviewed;

[0033] An audit module, configured to determine any object to be audited as an audited object if a target indication message for the object to be audited is obtained; the target indication message indicates that the audit of the object to be audited has been completed;

[0034] A backlog acquisition module, configured to obtain the backlog of the objects to be reviewed when a preset condition for updating the screening threshold is met;

[0035] A search module, configured to search for a target backlog interval to which the backlog of the object to be reviewed belongs in a plurality of pre-configured backlog intervals; wherein different backlog intervals correspond to different values ​​of the screening threshold; the intersection of different backlog intervals is zero, and the union of all backlog intervals constitutes a continuous backlog interval; if the minimum value of a first backlog interval is greater than the minimum value of a second backlog interval, then the value of the screening threshold corresponding to the first backlog interval is greater than the value of the screening threshold corresponding to the second backlog interval; the first backlog interval and the second backlog interval are any two backlog intervals among the plurality of backlog intervals;

[0036] The threshold updating module is configured to use the value of the screening threshold corresponding to the target backlog interval as the target value of the screening threshold.

[0037] An electronic device, comprising:

[0038] Memory, used to store programs;

[0039] The processor is configured to call and execute the program in the memory, and implement the steps of any of the above information processing methods by executing the program.

[0040] A readable storage medium stores a computer program thereon, wherein when the computer program is executed by a processor, the steps of the information processing method described in any one of the above items are implemented.

[0041] Through the above scheme, it can be seen that the information processing method, device, electronic device and storage medium provided by the present application, based on the target attribute of the object to be screened and the screening threshold, screens out the objects to be screened whose target attribute value is greater than the target value of the screening threshold from the set of objects to be screened as the objects to be reviewed; if a target indication message for any object to be reviewed is obtained, the any object to be reviewed is determined as an reviewed object; the target indication message indicates that the review of any object to be reviewed has been completed; when the preset condition for updating the screening threshold is met, the backlog of the object to be reviewed is obtained; and the backlog of the object to be reviewed is searched in multiple pre-configured backlog intervals. The target backlog interval to which the backlog of the audit object belongs; wherein, different backlog intervals correspond to different screening threshold values; the intersection of different backlog intervals is zero, and the union of all backlog intervals constitutes a continuous backlog interval; if the minimum value of the first backlog interval is greater than the minimum value of the second backlog interval, then the value of the screening threshold corresponding to the first backlog interval is greater than the value of the screening threshold corresponding to the second backlog interval; the first backlog interval and the second backlog interval are any two backlog intervals among the multiple backlog intervals; the value of the screening threshold corresponding to the target backlog interval is used as the target value of the screening threshold. In the process of screening objects to be reviewed based on the values ​​of the target attributes of the objects to be screened and the target value of the screening threshold, and reviewing the screened objects to be reviewed, the present application automatically updates the target value of the screening threshold according to the number of backlog objects to be reviewed (i.e., the backlog amount of objects to be reviewed) and the correspondence between multiple preset backlog amount intervals and the values ​​of the screening threshold, thereby realizing automatic updating of the screening threshold, and no longer requiring manual updating of the target value of the screening threshold, thereby overcoming the problem that manually setting the screening threshold is prone to unreasonable screening threshold setting and occupies human resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0043] Figure 1 A flowchart of an implementation of the information processing method provided in an embodiment of the present application;

[0044] Figure 2A flowchart for implementing the updating of the correspondence between different backlog intervals and different values ​​of the screening threshold in a plurality of backlog intervals based on the target attributes of the pending audit objects marked as audited within a second preset time period provided in an embodiment of the present application;

[0045] Figure 3 A flowchart for obtaining the median of the values ​​of the target attributes of the objects to be reviewed that are marked as reviewed within a second preset time period when they are determined to be objects to be reviewed, provided in an embodiment of the present application;

[0046] Figure 4 A system architecture diagram of the information processing method provided in an embodiment of the present application;

[0047] Figure 5 A schematic diagram of the structure of an information processing device provided in an embodiment of the present application;

[0048] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0049] The terms "first," "second," "third," "fourth," and so on (if any) in the specification, claims, and drawings are used to distinguish similar parts and are not necessarily used to describe a particular order or sequential sequence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated herein. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0051] Taking short videos as an example, the current development of short videos is changing with each passing day. Due to operational needs, the operators of short video platforms need to manually review some videos posted to the short video platform. The specific videos that need to be reviewed are currently screened based on the video exposure and exposure threshold. Specifically, videos with exposure greater than the exposure threshold are identified as videos to be reviewed. The operators then review the videos to be reviewed one by one. The reviewed videos will be marked as reviewed videos, and the unreviewed videos to be reviewed will be in the backlog of videos to be reviewed. In this process, if the exposure threshold is relatively small, more videos to be reviewed will be screened out, and there may be a large backlog of videos to be reviewed. The videos to be reviewed that cannot be reviewed will waste storage and computing resources. If the exposure threshold is relatively large, fewer videos to be reviewed will be screened out, and the backlog of videos to be reviewed will be relatively small. There may not be enough videos for reviewers to review, resulting in idle staff. Therefore, the exposure threshold needs to be adjusted. Currently, the exposure threshold is adjusted manually. Manual adjustment of the exposure threshold is based on experience. This can easily lead to problems such as an unreasonable exposure threshold setting, resulting in too many or too few backlogs of videos to be screened for review, and it also takes up human resources.

[0052] In order to overcome the problem of resource waste, this application is proposed.

[0053] like Figure 1 As shown, a flowchart of an implementation of the information processing method provided in an embodiment of the present application may include:

[0054] Step S101: Based on the target attribute of the object to be screened and the screening threshold, the objects to be screened whose target attribute value is greater than the target value of the screening threshold are screened from the set of objects to be screened as objects to be reviewed.

[0055] The objects to be screened in the set of objects to be screened are objects posted on the network platform by network platform users. The objects posted on the network platform may include but are not limited to any of the following: video, text, image, etc.

[0056] Optionally, the target attribute may be an attribute of the object to be filtered that changes over time, that is, the value of the target attribute may change over time.

[0057] As an example, the target attribute may include but is not limited to any of the following: exposure, page views, forwarding, etc.

[0058] Taking video as an example, the target attribute of any video (denoted as video V) may include any one of the exposure, browsing and forwarding volume of video V. Taking exposure as an example, the exposure of video V may include but is not limited to any of the following: the exposure of video V in the current unit time of the target video platform (when video V is released on at least two video platforms, the target video platform may be any one of the at least two video platforms), the sum of the exposure of video V in the current unit time of at least two video platforms, and the cumulative exposure of video V. Among them, the current unit time can be the day, or it can be the 48 hours to which the current moment belongs, or it can be the 12 hours to which the current moment belongs, etc. The cumulative exposure of video V may refer to the total exposure of video V on various video platforms since its release, or it may be the total exposure of video V on various video platforms within a certain time period before the current moment.

[0059] In this application, multiple values ​​of the screening threshold are pre-set, and the target value of the screening threshold is a value determined from the multiple values ​​of the screening threshold. The specific process of determining the target value of the screening threshold can be found in the subsequent embodiments.

[0060] Step S102: If a target indication message for any object to be reviewed is obtained, the object to be reviewed is determined as a reviewed object; the target indication message indicates that the review of any object to be reviewed has been completed.

[0061] The objects to be reviewed will be reviewed one by one by reviewers (for example, operators), and the videos to be reviewed after being reviewed will be determined as reviewed objects.

[0062] Optionally, after the reviewer completes the review of any object to be reviewed, he or she may perform a preset operation (for example, click a confirmation button, etc.) to trigger the generation of target indication information for any object to be reviewed. The target indication message indicates that the review of any object to be reviewed has been completed. In response to the target indication information, any object to be reviewed is marked as reviewed. The object to be reviewed marked as reviewed is the reviewed object.

[0063] The objects awaiting review that have not been reviewed are the backlog of objects awaiting review.

[0064] It should be noted that this application does not limit the execution order of step S101 and step S102. Step S101 and step S102 can be executed synchronously, that is, while the objects to be reviewed are being screened, the objects to be reviewed are manually reviewed. Step S101 and step S102 can also be executed asynchronously, that is, only step S101 or only step S102 is executed at the same time.

[0065] Step S103: When the preset conditions for updating the screening threshold are met, the backlog of objects to be reviewed is obtained. The backlog of objects to be reviewed is the number of objects to be reviewed.

[0066] When the pre-set conditions for updating the screening threshold are met, it means that the target value of the screening threshold needs to be updated, and it also means that the backlog of objects to be reviewed needs to be adjusted.

[0067] Step S104: searching for the backlog interval to which the above backlog belongs among a plurality of pre-configured backlog intervals (referred to as the target backlog interval here for ease of description and distinction).

[0068] This application pre-sets multiple backlog intervals. The intersection of different backlog intervals is zero, and the union of all backlog intervals constitutes a continuous backlog interval. Take the multiple backlog intervals shown in Table 1 below as an example. The multiple backlog intervals in Table 1 are sorted by the minimum value in each backlog interval. There is no intersection between any two adjacent backlog intervals. The union of all backlog intervals is a continuous backlog interval [00,000, 95,000). In other words, the maximum value of the previous backlog interval and the minimum value of the next backlog interval in any two adjacent backlog intervals in Table 1 are continuous. If the union of all backlog intervals is not a continuous backlog interval, but two or more continuous backlog intervals, for example, if the backlog interval [55,000, 60,000) in Table 1 is changed to [57,000, 60,000), then the union of all backlog intervals is two continuous backlog intervals, namely [00,000, 55,000) and [57,000, 60,000), respectively. In this case, if the backlog of the object to be reviewed obtained in step S103 is in [55,000, 57,000), the target value of the screening threshold cannot be updated.

[0069] The present application also pre-establishes a correspondence between backlog intervals and screening threshold values, and different backlog intervals correspond to different screening threshold values. For the first backlog interval and the second backlog interval among multiple backlog intervals, if the minimum value of the first backlog interval is greater than the minimum value of the second backlog interval, then the value of the above-mentioned screening threshold corresponding to the first backlog interval is greater than the value of the above-mentioned screening threshold corresponding to the second backlog interval; if the minimum value of the first backlog interval is less than the minimum value of the second backlog interval, then the value of the above-mentioned screening threshold corresponding to the first backlog interval is less than the value of the above-mentioned screening threshold corresponding to the second backlog interval. The first backlog interval and the second backlog interval are any two backlog intervals among the above-mentioned multiple backlog intervals;

[0070] Step S105: The value of the screening threshold corresponding to the target backlog interval is used as the target value of the screening threshold.

[0071] After taking the value of the above-mentioned screening threshold corresponding to the target backlog interval as the target value of the screening threshold, when screening the objects to be reviewed from the set of objects to be screened, the objects to be screened in the set of objects to be screened whose values ​​of the target attributes are greater than the value of the above-mentioned screening threshold corresponding to the target backlog interval are taken as the objects to be reviewed.

[0072] In the present application, the larger the minimum value of the backlog interval, the larger the value of the screening threshold corresponding to the backlog interval, and the smaller the minimum value of the backlog interval, the smaller the value of the screening threshold corresponding to the backlog interval. Therefore, after taking the value of the above-mentioned screening threshold corresponding to the target backlog interval as the target value of the screening threshold, when the backlog of objects to be reviewed is large, the number of objects to be reviewed screened from the objects to be screened can be reduced, thereby reducing the growth rate of objects to be reviewed. When the backlog of objects to be reviewed is small, the number of objects to be reviewed screened from the objects to be screened can be increased, thereby increasing the growth rate of objects to be reviewed, thereby achieving the purpose of automatically and dynamically adjusting the backlog of objects to be reviewed.

[0073] The information processing method of the present application, in the process of screening objects to be reviewed based on the values ​​of the target attributes of the objects to be reviewed and the target value of the screening threshold, and reviewing the screened objects to be reviewed, automatically updates the target value of the screening threshold according to the number of backlog objects to be reviewed and the correspondence between multiple preset backlog amount intervals and the values ​​of the screening threshold, thereby realizing automatic updating of the screening threshold, and no longer requiring manual updating of the target value of the screening threshold, thereby overcoming the problem that manually setting the screening threshold is prone to unreasonable screening threshold setting and occupies human resources.

[0074] In an optional embodiment, the above-mentioned conditions for satisfying the preset conditions for updating the screening threshold may include:

[0075] The preset adjustment period for reaching the screening threshold.

[0076] That is to say, the present application can periodically adjust the target value of the screening threshold, that is, adjust the target value of the screening threshold once every time period, for example, adjust the target value of the screening threshold once every 30 minutes.

[0077] Optionally, the period for adjusting the target value of the screening threshold may be a configurable parameter. Based on this, the information processing method of the present application may further include:

[0078] If a first update instruction for the adjustment period is obtained, the preset adjustment period of the screening threshold is updated to the adjustment period carried in the first update instruction.

[0079] The first update instruction may be triggered to be generated by the user by executing a first preset operation when needed.

[0080] As an example, the adjustment period may also be 15 minutes, or 10 minutes, or 40 minutes, or 60 minutes, etc. Of course, the adjustment period may also be other values, which are not specifically limited here.

[0081] In an optional embodiment, the above-mentioned conditions for satisfying the preset conditions for updating the screening threshold may include:

[0082] The backlog of the subject to be reviewed is outside the preset backlog range for a preset duration (referred to as the first preset duration for ease of description and distinction). The preset backlog range may be a backlog range from the aforementioned multiple backlog ranges, or may be the union of N consecutive backlog ranges (N is an integer greater than 1) from the aforementioned multiple backlog ranges.

[0083] Taking Table 1 below as an example, the preset range may be [50,000, 55,000), or [55,000, 60,000), or [50,000, 60,000), or [45,000, 60,000), and so on.

[0084] In this application, the backlog of objects to be reviewed can be monitored in real time. When the backlog of objects to be reviewed has not entered into a preset range within a first preset time period, it is considered that the value of the screening threshold should be adjusted.

[0085] Optionally, the first preset duration may be a configurable parameter. Based on this, the information processing method of the present application may further include:

[0086] If a second update instruction for the first preset duration is obtained, the first preset duration is updated to the duration carried in the second update instruction.

[0087] The second update instruction may be triggered to be generated by the user by executing a second preset operation when needed.

[0088] As an example, the first preset duration can be: 30 minutes, or 15 minutes, or 10 minutes, or 40 minutes, or 60 minutes, etc. Of course, the first preset duration can also be other values, which are not specifically limited here.

[0089] In actual audit scenarios, the objects to be audited in the set of objects to be screened may be audited in different channels (or groups). Therefore, the objects to be audited in the set of objects to be screened need to be screened into different audit channels. Among them, one object to be audited can only be divided into one audit channel, that is, different audit channels have different objects to be audited.

[0090] Optionally, different audit channels represent different audit dimensions, such as professional channels, comprehensive channels, etc.

[0091] Taking videos as an example, professional channels may include but are not limited to at least one of the following: gaming videos, finance videos, and movie videos. Comprehensive channels may include but are not limited to at least one of the following: children's videos and parent-child videos.

[0092] Based on this, in an optional embodiment, based on the target attribute of the object to be screened and the screening threshold, one implementation method of screening out the object to be screened whose target attribute value is greater than the target value of the screening threshold from the set of objects to be screened as the object to be reviewed may be:

[0093] Based on the target attribute of the object to be screened corresponding to the target audit channel (for the convenience of description and distinction, recorded as the first target attribute), and the screening threshold corresponding to the target audit channel (for the convenience of description and distinction, recorded as the first screening threshold), the objects to be screened whose values ​​of the first target attribute are greater than the target value of the first screening threshold are screened out from the set of objects to be screened as the objects to be audited of the target audit channel.

[0094] The target audit channel is any audit channel among the preset multiple audit channels; different audit channels correspond to different target attributes, or different audit channels correspond to different screening threshold values. In other words, this application presets target attributes and screening thresholds for each audit channel.

[0095] Different review channels correspond to different target attributes, and accordingly, different review channels correspond to different screening thresholds; for example, if the target attribute corresponding to the review channel is the daily exposure, the screening threshold is the daily exposure threshold; if the target attribute corresponding to the review channel is the cumulative exposure, the screening threshold is the cumulative exposure threshold.

[0096] When the target attributes corresponding to different audit channels are the same, the screening thresholds corresponding to the different audit channels are also the same, but the values ​​of the screening thresholds are different.

[0097] For example, the daily exposure of videos in professional channels is usually higher, and the corresponding exposure threshold is relatively larger, while the daily exposure of videos in comprehensive channels is usually lower, and the corresponding exposure threshold is relatively smaller.

[0098] For example, if there are two review channels and their corresponding target attributes are both platform exposure, then the corresponding screening thresholds are both platform exposure thresholds. However, the platform exposure thresholds corresponding to one of the review channels include: 5, 15, 20, 25, 30, 35, 40, 45, 50, etc.; the platform exposure thresholds corresponding to the other review channel include: 3, 8, 13, 18, 23, 28, 33, 38, 43, etc.

[0099] In an optional embodiment, a priority is pre-configured for each channel, and different audit channels have different priorities. For any object to be screened, it can be determined one by one in descending order of priority whether the object to be screened is an object to be screened of a certain audit channel, until it is determined that the object to be screened belongs to an object to be screened of an audit channel, and it is no longer necessary to determine whether the object to be screened belongs to an object to be screened of another audit channel. Specifically, corresponding to an audit channel of any priority, if the value of the target attribute of the object to be screened corresponding to the audit channel of any priority is greater than the value of the screening threshold corresponding to the audit channel of any priority, it is determined that the object to be screened is an object to be screened of the audit channel of any priority, and it is no longer necessary to determine whether the object to be screened belongs to an object to be screened of the next priority audit channel; otherwise, it is determined that the object to be screened is not an object to be screened of the audit channel of any priority, and it is necessary to determine whether the object to be screened belongs to an object to be screened of the next priority audit channel.

[0100] In an optional embodiment, each object to be screened has a category label, and the category label is configured for the object to be screened by the network platform according to a preset labeling rule. Based on this, the audit channel corresponding to each object to be screened can be determined according to the preset correspondence between the category label and the audit channel, and according to the category label of each object to be screened, for any object to be screened, assuming that the audit channel corresponding to the object to be screened is the second audit channel, the target attribute corresponding to the second audit channel is the second target attribute, and the screening threshold corresponding to the second audit channel is the second screening threshold, then if the value of the second target attribute of the object to be screened is greater than the target value of the second screening threshold, the object to be screened is determined to be an object to be screened of the second audit channel.

[0101] Accordingly, one implementation method for obtaining the backlog of objects to be reviewed may be:

[0102] Get the backlog of objects to be reviewed in the target review channel.

[0103] After the objects in the set of objects to be screened are filtered into different audit channels, each audit channel will be audited by an auditor. Therefore, the unaudited objects to be audited in each audit channel constitute the backlog of objects to be audited in that audit channel. Therefore, the backlog of objects to be audited in the target audit channel is the number of unaudited objects to be audited in the target audit channel.

[0104] Accordingly, one implementation of searching for the target backlog interval to which the backlog of the object to be reviewed belongs in the pre-configured multiple backlog intervals may be:

[0105] The target backlog amount interval to which the backlog amount of the object to be reviewed of the target review channel belongs is searched among the multiple backlog amount intervals corresponding to the preset target review channel.

[0106] Under different review channels, the backlog amount may belong to the same or different backlog amount intervals. Under different review channels, if the backlog amount belongs to the same backlog amount interval, the corresponding screening threshold value of the backlog amount interval will be different. Under different review channels, if the backlog amount belongs to different backlog amount intervals, the corresponding screening threshold value of the backlog amount interval can be the same or different.

[0107] In an optional embodiment, the correspondence between backlog intervals and screening threshold values ​​can be updated. Based on this, when the aforementioned update condition for the correspondence between different backlog intervals and different screening threshold values ​​is met, the correspondence between different backlog intervals and different screening threshold values ​​can be updated based on the target attributes of the pending review objects marked as reviewed within a preset second predetermined time period.

[0108] Optionally, the update condition satisfying the correspondence between different backlog intervals in the plurality of backlog intervals and different values ​​of the screening threshold may include:

[0109] The preset adjustment period for the correspondence between different backlog intervals in the above-mentioned multiple backlog intervals and different values ​​of the screening threshold is achieved. The preset adjustment period here may be the same as or different from the preset adjustment period of the aforementioned screening threshold; in the case where the preset adjustment period for the correspondence between different backlog intervals in the above-mentioned multiple backlog intervals and different values ​​of the screening threshold is the same as the preset adjustment period of the aforementioned screening threshold, the adjustment time for the correspondence between different backlog intervals in the above-mentioned multiple backlog intervals and different values ​​of the screening threshold is different from the adjustment time of the aforementioned screening threshold, that is, although the adjustment periods of the two are the same, the adjustment times are different, for example, both are adjusted once a day, but one is adjusted at 1 a.m. and the other is adjusted at 2 a.m.

[0110] However, typically, the preset adjustment period for the correspondence between different backlog intervals and different screening threshold values ​​is greater than the preset adjustment period for the screening threshold. For example, the correspondence between different backlog intervals and different screening threshold values ​​may be adjusted monthly, and the target screening threshold value may be adjusted every 30 minutes.

[0111] In the case of auditing in different channels, corresponding to any audit channel, when the update condition of the correspondence between different backlog intervals in the above-mentioned multiple backlog intervals and different values ​​of the screening threshold is met, the correspondence between different backlog intervals in the multiple backlog intervals corresponding to any audit channel and different values ​​of the screening threshold can be updated based on the target attributes of the audited objects marked as audited in any audit channel within the preset second preset time period.

[0112] like Figure 2 The flowchart for implementing the updating of the correspondence between different backlog intervals and different values ​​of the screening threshold in the above-mentioned multiple backlog intervals based on the target attributes of the pending review objects marked as reviewed within the second preset time period provided in the embodiment of the present application may include:

[0113] Step S201: obtaining the median of the values ​​of the target attributes of the objects to be reviewed that are marked as reviewed within a second preset time period when they are determined to be the objects to be reviewed.

[0114] Since each audited object is determined as an object to be audited by an object to be screened, and finally determined as an audited object by an object to be audited, the value of the target attribute of the audited object when it is determined as an object to be audited within the second preset time period refers to the value of the target attribute when the audited object was determined as an object to be audited before it was determined as an audited object.

[0115] Step S202: using the median as a first value of the screening threshold, and establishing a correspondence between the first value and a third backlog interval among the multiple backlog intervals.

[0116] The third backlog interval may be a backlog interval defined by the operation personnel according to operation requirements.

[0117] Step S203: Based on the correspondence between the third backlog interval and the first value, determining the correspondence between non-third backlog intervals in the plurality of backlog intervals and other values ​​of the screening threshold.

[0118] Optionally, the third backlog interval and the first value may be used as a reference. If the minimum value of any non-third backlog interval among the multiple backlog intervals is increased by a first increment relative to the minimum value of the third backlog interval, the first value may be increased by a second increment as the value of the screening threshold corresponding to any non-third backlog interval; the second increment is positively correlated with the first increment.

[0119] If the minimum value of any non-third backlog interval among multiple backlog intervals is reduced by the above-mentioned first increment relative to the minimum value of the third backlog interval, the first value is reduced by the above-mentioned second increment as the value of the above-mentioned screening threshold corresponding to any non-third backlog interval.

[0120] In the case where there are multiple audit channels, for any audit channel, obtain the median of the values ​​of the target attributes of the objects to be audited that are marked as audited in any audit channel within the second preset time period when they are determined to be objects to be audited; use the median as the first value of the above-mentioned screening threshold corresponding to any audit channel, and establish a correspondence between the first value under any audit channel and the third backlog interval under any audit channel; based on the correspondence between the third backlog interval under any audit channel and the first value, determine the correspondence between other backlog intervals under any audit channel and other values ​​of the screening threshold.

[0121] In an optional embodiment, a flowchart for implementing the above-mentioned acquisition of the median of the values ​​of the target attributes of the objects to be reviewed that are marked as reviewed within the second preset time period when they are determined to be objects to be reviewed is as follows: Figure 3 Said may include:

[0122] Step S301: sorting the values ​​of the target attributes of the objects to be reviewed that are marked as reviewed within a second preset time period when they are determined to be the objects to be reviewed.

[0123] Step S302: determining the median of the target attributes of the objects to be reviewed that are marked as reviewed within the second preset time period when they are determined to be the objects to be reviewed based on the values ​​ranked in the middle.

[0124] Optionally, if the number of reviewed objects within the second preset time period is an odd number, the value of the target attribute of the reviewed object in the middle position can be determined as the median of the values ​​of the target attributes of the objects to be reviewed marked as reviewed within the second preset time period when they were determined as objects to be reviewed.

[0125] Optionally, if the number of reviewed objects within the second preset time period is even, and there are two reviewed objects in the middle position, then:

[0126] The value of the target attribute of any of the two audited objects ranked in the middle when it is determined as an object to be audited can be determined as the median of the values ​​of the target attribute of the objects to be audited marked as audited within the second preset time period when they are determined as objects to be audited. For example, if the number of audited objects within the second preset time period is 700,000, then after sorting the 700,000 audited objects according to the values ​​of the target attribute when they are determined as objects to be audited, the value of the target attribute of the audited object ranked 350,000 when it is determined as an object to be audited can be determined as the median of the values ​​of the target attribute of the objects to be audited marked as audited within the second preset time period when they are determined as objects to be audited.

[0127] or,

[0128] The average value of the target attributes of the two reviewed objects in the middle position when they were determined as objects to be reviewed can be determined as the median value of the target attributes of the objects to be reviewed marked as reviewed within the second preset time period when they were determined as objects to be reviewed.

[0129] In the case where there are multiple audit channels, for any audit channel, the audited objects under any audit channel within the second preset time period can be sorted according to the values ​​of the target attributes when they are determined as objects to be audited; based on the values ​​ranked in the middle position, the median of the values ​​of the target attributes of the audited objects under any audit channel within the second preset time period when they are determined as objects to be audited is determined.

[0130] The following uses the short video platform as an example to illustrate the solution of this application.

[0131] Short video platforms typically require the review of short videos posted on the platform. This review may include, but is not limited to, any of the following: quality review, originality review (i.e., reviewing whether the short video is original), and length-short association review (i.e., reviewing whether the short video is associated with a longer video). Regardless of the type of review, the information processing method provided in the aforementioned embodiments of this application can be used to automatically adjust the daily exposure threshold value.

[0132] In this example, we take the daily exposure of a short video on a short video platform P as the target attribute extraction channel T (which can be any review channel) for the short video to be reviewed. Assume that the corresponding relationship between the video backlog interval and the daily exposure threshold value under channel T is shown in Table 1:

[0133] Table 1

[0134] Backlog range Daily exposure threshold [00,000, 20,000) 1 [20,000, 25,000] 5 [25,000, 30,000] 10 [30,000, 35,000] 15 [35,000, 40,000] 20 [40,000, 45,000] 25 [45,000, 50,000] 30 [50,000, 55,000] 35 [55,000, 60,000] 40 [60,000, 65,000] 45 [65,000, 70,000] 50 [70,000, 75,000] 55 [75,000, 80,000] 60 [80,000, 85,000] 65 [85,000, 90,000] 70 [90,000, 95,000] 75

[0135] Assume that the current target value of the daily exposure threshold is 10, that is, if the daily exposure value of any video V in the short video platform P is greater than 10, the video V will be extracted as a video to be reviewed. Otherwise, it is prohibited to extract the video V as a video to be reviewed.

[0136] In this example, the target value of the daily exposure threshold is adjusted every 30 minutes. Based on this, when the time from the last adjustment of the daily exposure threshold under the T channel reaches 30 minutes, the backlog of videos to be reviewed under the T channel is obtained. Assuming that the backlog of videos to be reviewed under the T channel is 42,000, based on the corresponding relationship shown in Table 1, the backlog interval of 42,000 is [40,000, 45,000), and the daily exposure value corresponding to the backlog interval [40,000, 45,000) is 25, then the target value of the daily exposure threshold is updated to 25. Afterwards, only when the daily exposure value of any video V in the short video platform P is greater than 25, the video V will be extracted as a video to be reviewed. Otherwise, the video V will be prohibited from being extracted as a video to be reviewed.

[0137] In this example, the correspondence between the backlog interval under channel T and the value of the daily exposure threshold is updated once every month. Based on this, when the time since the last adjustment of the correspondence between the backlog interval under channel T and the value of the daily exposure threshold reaches one month, a statistical analysis is performed on all short videos reviewed under channel T within that month to determine the median of the daily exposure values ​​of each video reviewed within that month when it was determined to be a video to be reviewed. Assuming the median is 35, and the backlog of videos to be reviewed that meet the operational requirements is [55,000, 60,000), 35 is used as the value of the daily exposure threshold corresponding to the backlog interval [55,000, 60,000), that is, the correspondence between [55,000, 60,000) and 35 is established. Thereafter, the correspondence between other backlog intervals and the value of the daily exposure threshold under channel T is updated based on this correspondence. Assume that the update rule is: for every increase of 5000 in the minimum value within the backlog interval, the corresponding daily exposure threshold value increases by 5, and for every decrease of 5000 in the minimum value within the backlog interval, the corresponding daily exposure threshold value decreases by 5. In addition, the daily exposure threshold value cannot be zero, so the daily exposure threshold values ​​corresponding to two adjacent backlog intervals can be different by 5. It is only necessary to meet the requirement that the larger the backlog value within the backlog interval, the larger the corresponding daily exposure threshold value. Based on this, the correspondence between the video backlog interval and the daily exposure threshold value under channel T obtained by the update is shown in Table 2:

[0138] Table 2

[0139]

[0140]

[0141] Afterwards, the exposure threshold is updated based on Table 2. Specifically, when the time from the last adjustment of the daily exposure threshold under the T channel reaches 30 minutes, the backlog of videos to be reviewed under the T channel is obtained. Assuming that the extracted backlog of videos to be reviewed under the T channel is 41,000, based on the corresponding relationship shown in Table 2, the backlog interval to which 41,000 belongs is [40,000, 45,000), then the target value of the exposure threshold is adjusted to 20. Afterwards, if the daily exposure value of any video V in the short video platform P is greater than 20, the video V will be extracted as a video to be reviewed. Otherwise, the video V will be prohibited from being extracted as a video to be reviewed.

[0142] The reviewed videos used to update the correspondence between the video backlog interval and the threshold value may be offline data.

[0143] like Figure 4 FIG. 1 is a system architecture diagram of the information processing method provided by an embodiment of the present application, wherein:

[0144] The up master refers to the video publisher, who uploads the video to the video platform.

[0145] After uploading to the video platform, the video publisher can edit, cut, and process the video with special effects to create new video content (this process is also called video production) and publish the new video content to the video platform. Of course, the video publisher can choose not to edit, cut, or process the video with special effects, but directly publish the uploaded video to the video platform.

[0146] The video platform can perform preliminary filtering on the published videos, for example, filtering out short videos (for example, videos whose duration is less than the judgment threshold) and storing the unfiltered videos in the tag review system content pool. The videos in the tag review system content pool are the videos to be screened.

[0147] Extract the videos to be reviewed under each review channel from the content pool of the label review system (i.e. Figure 4 In the review pool, the videos to be reviewed corresponding to different review channels are stored in different queues.

[0148] Corresponding to any review channel, the reviewer of any channel extracts the videos to be reviewed under any review channel from the review pool for review. Figure 4 In the example shown, two review channels are shown, namely review channel A and review channel B. After any video to be reviewed is reviewed, it is marked as a reviewed object.

[0149] Among them, the process of extracting the videos to be reviewed under each review channel from the content pool of the label review system is based on the core indicators of each channel (for example, the exposure threshold). Specifically, corresponding to any review channel and any video in the content pool of the label review system, if the exposure value of any video (which can be the exposure value of any dimension) is greater than the target value of the exposure threshold corresponding to any review channel, the video will be extracted as the video to be reviewed under any review channel; if the exposure value of any video is less than or equal to the target value of the exposure threshold corresponding to any review channel, it is prohibited to extract any video as the video to be reviewed under any review channel.

[0150] The core indicators of each review channel are obtained by adjusting the automatic threshold adjustment algorithm under each review channel. For the automatic threshold adjustment algorithm under any review channel, please refer to the aforementioned embodiment of the present application, which will not be repeated here. As an example, the video backlog of each review channel can be regularly monitored by the distributed task scheduling platform xxl-job, and then the target value of the exposure threshold used by the automatic threshold adjustment algorithm under each review channel can be adjusted according to the video backlog under each review channel. In addition, every month, the offline data in the most recent month (that is, the video exposure when the reviewed video is determined to be the object to be reviewed) can be used to update the correspondence between the video backlog and the exposure threshold used in the automatic threshold adjustment algorithm, that is, the automatic threshold adjustment algorithm can be updated once a month. Figure 4 In the example shown, offline Hive is used to update the algorithm.

[0151] Figure 4 In the figure, the dashed box shows the method for determining the exposure threshold in the prior art, i.e., manually determining the target value of the exposure threshold. The dashed box shows the method for determining the exposure threshold provided by the present application, i.e., automatically adjusting the target value of the exposure threshold based on the backlog.

[0152] Corresponding to the method embodiment, the present application also provides an information processing device. A structural diagram of the information processing device provided in the embodiment of the present application is as follows: Figure 5 As shown, this may include:

[0153] Screening module 501, review module 502, backlog acquisition module 503, search module 504 and threshold update module 505; wherein,

[0154] The screening module 501 is used to screen out the objects to be screened whose target attribute value is greater than the target value of the screening threshold from the set of objects to be screened based on the target attribute of the objects to be screened and the screening threshold as the objects to be reviewed;

[0155] The audit module 502 is configured to determine any object to be audited as an audited object if a target indication message for the object to be audited is obtained; the target indication message indicates that the audit of the object to be audited has been completed;

[0156] The backlog obtaining module 503 is used to obtain the backlog of the objects to be reviewed when the preset conditions for updating the screening threshold are met;

[0157] The search module 504 is used to search for a target backlog interval to which the backlog of the object to be reviewed belongs in a plurality of pre-configured backlog intervals; wherein different backlog intervals correspond to different values ​​of the screening threshold; the intersection of different backlog intervals is zero, and the union of all backlog intervals constitutes a continuous backlog interval; if the minimum value of a first backlog interval is greater than the minimum value of a second backlog interval, then the value of the screening threshold corresponding to the first backlog interval is greater than the value of the screening threshold corresponding to the second backlog interval; the first backlog interval and the second backlog interval are any two backlog intervals among the plurality of backlog intervals;

[0158] The threshold updating module 505 is configured to use the value of the screening threshold corresponding to the target backlog interval as the target value of the screening threshold.

[0159] The information processing device provided by the embodiment of the present application, in the process of screening objects to be reviewed based on the values ​​of the target attributes of the objects to be reviewed and the target value of the screening threshold, and reviewing the screened objects to be reviewed, automatically updates the target value of the screening threshold according to the number of backlog objects to be reviewed and the correspondence between multiple preset backlog amount intervals and the values ​​of the screening threshold, thereby realizing automatic updating of the screening threshold, and no longer requiring manual updating of the target value of the screening threshold, thereby overcoming the problem that manually setting the screening threshold is prone to unreasonable screening threshold setting and occupies human resources.

[0160] In an optional embodiment, the satisfying of a preset condition for updating the screening threshold includes:

[0161] a preset adjustment period for reaching said screening threshold;

[0162] or,

[0163] The duration during which the backlog of objects to be reviewed is outside the preset backlog range reaches a first preset duration.

[0164] In an optional embodiment, the screening module 501 is used to:

[0165] Based on a first target attribute of the object to be screened corresponding to a target audit channel and a first screening threshold corresponding to the target audit channel, screen out the objects to be screened whose values ​​of the first target attribute are greater than a target value of the first screening threshold from the set of objects to be screened as the objects to be screened for the target audit channel; the target audit channel is any audit channel among a plurality of preset audit channels; different audit channels have different target attributes corresponding to them, or different audit channels have different screening threshold values ​​corresponding to them;

[0166] The backlog acquisition module 503 is used to:

[0167] Obtaining the backlog of objects to be audited in the target audit channel;

[0168] The search module 504 is configured to search for a target backlog interval to which the backlog of the objects to be reviewed of the target review channel belongs among a plurality of backlog intervals corresponding to the pre-configured target review channel.

[0169] In an optional embodiment, the device further comprises:

[0170] A correspondence updating module is used to update the correspondence between different backlog intervals in the multiple backlog intervals and different values ​​of the screening threshold based on the target attributes of the objects to be reviewed that are marked as reviewed within a second preset time period when the update conditions of the correspondence between different backlog intervals in the multiple backlog intervals and different values ​​of the screening threshold are met.

[0171] In an optional embodiment, when the correspondence updating module updates the correspondence between different backlog intervals in the multiple backlog intervals and different values ​​of the screening threshold based on the target attribute of the pending review objects marked as reviewed within the second preset time period, it is specifically configured to:

[0172] Obtaining the median of the values ​​of the target attributes of the objects to be reviewed that are marked as reviewed within the second preset time period when they are determined to be the objects to be reviewed;

[0173] Using the median as a first value of the screening threshold, establishing a correspondence between the first value and a third backlog interval among the multiple backlog intervals; the third backlog interval is a backlog interval defined according to operational requirements;

[0174] Based on the correspondence between the third backlog interval and the first value, a correspondence between non-third backlog intervals in the multiple backlog intervals and other values ​​of the screening threshold is determined.

[0175] In an optional embodiment, when the correspondence updating module obtains the median of the values ​​of the target attributes of the objects to be reviewed marked as reviewed within the second preset time period when they were determined to be the objects to be reviewed, it is used to:

[0176] sorting the values ​​of the target attributes of the objects to be reviewed that are marked as reviewed within the second preset time period when they are determined to be the objects to be reviewed;

[0177] The median of the target attributes of the objects to be reviewed that are marked as reviewed within the second preset time period when they are determined to be the objects to be reviewed is determined based on the values ​​ranked in the middle.

[0178] In an optional embodiment, when determining, based on the correspondence between the third backlog interval and the first value, the correspondence updating module determines the correspondence between a non-third backlog interval among the multiple backlog intervals and other values ​​of the screening threshold, the correspondence updating module is configured to:

[0179] Taking the third backlog interval and the first value as a reference, if the minimum value of any non-third backlog interval among the multiple backlog intervals increases by a first increment relative to the minimum value of the third backlog interval, the first value is increased by a second increment and used as the value of the screening threshold corresponding to any non-third backlog interval; the second increment is positively correlated with the first increment; if the minimum value of any non-third backlog interval among the multiple backlog intervals decreases by the first increment relative to the minimum value of the third backlog interval, the first value is reduced by the second increment and used as the value of the screening threshold corresponding to any non-third backlog interval.

[0180] Corresponding to the method embodiment, the present application also provides an electronic device, a structural diagram of the electronic device is shown as follows: Figure 6 As shown, it may include: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4.

[0181] In an embodiment of the present application, the number of processor 1 , communication interface 2 , memory 3 , and communication bus 4 is at least one, and the processor 1 , communication interface 2 , and memory 3 communicate with each other through the communication bus 4 .

[0182] The processor 1 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0183] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), etc., such as at least one disk memory.

[0184] The memory 3 stores a program, and the processor 1 can call the program stored in the memory 3, and the program is used to:

[0185] Based on the target attribute of the object to be screened and the screening threshold, the object to be screened whose value of the target attribute is greater than the target value of the screening threshold is screened out from the set of objects to be screened as the object to be reviewed;

[0186] If a target indication message for any object to be reviewed is obtained, the object to be reviewed is determined as a reviewed object; the target indication message indicates that the review of the object to be reviewed has been completed;

[0187] When a preset condition for updating the screening threshold is met, obtaining a backlog of the objects to be reviewed;

[0188] Searching for a target backlog interval to which the backlog of the object to be reviewed belongs in a plurality of pre-configured backlog intervals; wherein different backlog intervals correspond to different values ​​of the screening threshold; the intersection of different backlog intervals is zero, and the union of all backlog intervals constitutes a continuous backlog interval; if the minimum value of a first backlog interval is greater than the minimum value of a second backlog interval, then the value of the screening threshold corresponding to the first backlog interval is greater than the value of the screening threshold corresponding to the second backlog interval; the first backlog interval and the second backlog interval are any two backlog intervals among the plurality of backlog intervals;

[0189] The value of the screening threshold corresponding to the target backlog interval is used as the target value of the screening threshold.

[0190] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0191] An embodiment of the present application further provides a storage medium, which may store a program suitable for execution by a processor, wherein the program is used to:

[0192] Based on the target attribute of the object to be screened and the screening threshold, the object to be screened whose value of the target attribute is greater than the target value of the screening threshold is screened out from the set of objects to be screened as the object to be reviewed;

[0193] If a target indication message for any object to be reviewed is obtained, the object to be reviewed is determined as a reviewed object; the target indication message indicates that the review of the object to be reviewed has been completed;

[0194] When a preset condition for updating the screening threshold is met, obtaining a backlog of the objects to be reviewed;

[0195] Searching for a target backlog interval to which the backlog of the object to be reviewed belongs in a plurality of pre-configured backlog intervals; wherein different backlog intervals correspond to different values ​​of the screening threshold; the intersection of different backlog intervals is zero, and the union of all backlog intervals constitutes a continuous backlog interval; if the minimum value of a first backlog interval is greater than the minimum value of a second backlog interval, then the value of the screening threshold corresponding to the first backlog interval is greater than the value of the screening threshold corresponding to the second backlog interval; the first backlog interval and the second backlog interval are any two backlog intervals among the plurality of backlog intervals;

[0196] The value of the screening threshold corresponding to the target backlog interval is used as the target value of the screening threshold.

[0197] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0198] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0199] In the several embodiments provided herein, it should be understood that the disclosed systems, devices, and methods may be implemented in other ways. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0200] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0201] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0202] It should be understood that in the embodiments of the present application, the various embodiments and features can be combined with each other to solve the aforementioned technical problems.

[0203] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0204] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An information processing method, characterized in that: The method comprises: Based on the target attribute of the object to be screened and the screening threshold, the object to be screened whose value of the target attribute is greater than the target value of the screening threshold is screened out from the set of objects to be screened as the object to be reviewed; If a target indication message for any object to be reviewed is obtained, the object to be reviewed is determined as a reviewed object; the target indication message indicates that the review of the object to be reviewed has been completed; When a preset condition for updating the screening threshold is met, obtaining a backlog of the objects to be reviewed; Searching for a target backlog interval to which the backlog of the object to be reviewed belongs in a plurality of pre-configured backlog intervals; wherein different backlog intervals correspond to different values ​​of the screening threshold; the intersection of different backlog intervals is zero, and the union of all backlog intervals constitutes a continuous backlog interval; if the minimum value of a first backlog interval is greater than the minimum value of a second backlog interval, then the value of the screening threshold corresponding to the first backlog interval is greater than the value of the screening threshold corresponding to the second backlog interval; the first backlog interval and the second backlog interval are any two backlog intervals among the plurality of backlog intervals; The value of the screening threshold corresponding to the target backlog interval is used as the target value of the screening threshold.

2. The method according to claim 1, characterized in that The predetermined condition for updating the screening threshold is satisfied, including: a preset adjustment period for reaching said screening threshold; or, The duration during which the backlog of objects to be reviewed is outside the preset backlog range reaches a first preset duration.

3. The method according to claim 1, characterized in that The method of screening out, based on the target attribute of the object to be screened and the screening threshold, the object to be screened whose value of the target attribute is greater than the target value of the screening threshold from the set of objects to be screened as the object to be reviewed includes: Based on a first target attribute of the object to be screened corresponding to a target audit channel and a first screening threshold corresponding to the target audit channel, screen out the objects to be screened whose values ​​of the first target attribute are greater than a target value of the first screening threshold from the set of objects to be screened as the objects to be screened for the target audit channel; the target audit channel is any audit channel among a plurality of preset audit channels; different audit channels have different target attributes corresponding to them, or different audit channels have different screening threshold values ​​corresponding to them; Accordingly, obtaining the backlog of objects to be reviewed includes: obtaining the backlog of objects to be reviewed in the target review channel; The searching for the target backlog interval to which the backlog of the object to be reviewed belongs in the pre-configured multiple backlog intervals includes: searching for the target backlog interval to which the backlog of the object to be reviewed of the target review channel belongs in the pre-configured multiple backlog intervals corresponding to the target review channel.

4. The method according to claim 1, wherein Also includes: When the update condition of the correspondence between different backlog intervals in the multiple backlog intervals and different values ​​of the screening threshold is met, the correspondence between different backlog intervals in the multiple backlog intervals and different values ​​of the screening threshold is updated based on the target attributes of the objects to be reviewed that are marked as reviewed within the second preset time period.

5. The method according to claim 4, characterized in that The process of updating the correspondence between different backlog intervals in the plurality of backlog intervals and different values ​​of the screening threshold based on the target attributes of the objects to be reviewed that are marked as reviewed within the second preset time period includes: Obtaining the median of the values ​​of the target attributes of the objects to be reviewed that are marked as reviewed within the second preset time period when they are determined to be the objects to be reviewed; Using the median as a first value of the screening threshold, establishing a correspondence between the first value and a third backlog interval among the multiple backlog intervals; the third backlog interval is a backlog interval defined according to operational requirements; Based on the correspondence between the third backlog interval and the first value, a correspondence between non-third backlog intervals in the multiple backlog intervals and other values ​​of the screening threshold is determined.

6. The method according to claim 5, characterized in that The obtaining of the median of the target attributes of the objects to be reviewed marked as reviewed within the second preset time period when the objects are determined to be objects to be reviewed includes: sorting the values ​​of the target attributes of the objects to be reviewed that are marked as reviewed within the second preset time period when they are determined to be the objects to be reviewed; The median of the target attributes of the objects to be reviewed that are marked as reviewed within the second preset time period when they are determined to be the objects to be reviewed is determined based on the values ​​ranked in the middle.

7. The method according to claim 5, characterized in that The determining, based on the correspondence between the third backlog interval and the first value, a correspondence between a non-third backlog interval in the multiple backlog intervals and other values ​​of the screening threshold, includes: Taking the third backlog interval and the first value as a reference, if the minimum value of any non-third backlog interval among the multiple backlog intervals increases by a first increment relative to the minimum value of the third backlog interval, the first value is increased by a second increment and used as the value of the screening threshold corresponding to any non-third backlog interval; the second increment is positively correlated with the first increment; if the minimum value of any non-third backlog interval among the multiple backlog intervals decreases by the first increment relative to the minimum value of the third backlog interval, the first value is reduced by the second increment and used as the value of the screening threshold corresponding to any non-third backlog interval.

8. An information processing device, characterized in that include: A screening module is used to screen out, based on a target attribute of the object to be screened and a screening threshold, objects to be screened whose values ​​of the target attribute are greater than a target value of the screening threshold from the set of objects to be screened as objects to be reviewed; An audit module, configured to determine any object to be audited as an audited object if a target indication message for the object to be audited is obtained; The target indication message indicates that the review of any of the objects to be reviewed has been completed; A backlog acquisition module, configured to obtain the backlog of the objects to be reviewed when a preset condition for updating the screening threshold is met; A search module, configured to search for a target backlog interval to which the backlog of the object to be reviewed belongs in a plurality of pre-configured backlog intervals; wherein different backlog intervals correspond to different values ​​of the screening threshold; the intersection of different backlog intervals is zero, and the union of all backlog intervals constitutes a continuous backlog interval; if the minimum value of a first backlog interval is greater than the minimum value of a second backlog interval, then the value of the screening threshold corresponding to the first backlog interval is greater than the value of the screening threshold corresponding to the second backlog interval; the first backlog interval and the second backlog interval are any two backlog intervals among the plurality of backlog intervals; The threshold updating module is configured to use the value of the screening threshold corresponding to the target backlog interval as the target value of the screening threshold.

9. An electronic device comprising: Memory, used to store programs; A processor is configured to call and execute the program in the memory, and implement the steps of the information processing method according to any one of claims 1 to 7 by executing the program.

10. A readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the computer program implements the steps of the information processing method according to any one of claims 1 to 7.

Images