Data processing method and device, equipment and storage medium
By adopting a security level-based differentiated review strategy based on object history, the problem of resource waste caused by indiscriminate review was solved, and the efficiency of content review was improved.
Patent Information
- Application Number
- CN202510967153.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-14
- Publication Date
- 2025-11-14
AI Technical Summary
In existing technologies, content moderation strategies are indiscriminate, resulting in a waste of a large amount of computing resources and human resources on the repeated review of low-risk content, which is inefficient.
Based on an object's historical records, its security level is determined and differentiated audits are implemented. High-security-level objects are subject to a simple strategy, while low-security-level objects are subject to strict audits.
By focusing on reviewing high-risk content and reducing redundant reviews of low-risk content, we can effectively reduce computing and human resource costs and improve review efficiency.
Smart Images
Figure CN120952685A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer technology, and in particular to a data processing method, apparatus, device, and storage medium. Background Technology
[0002] In this era of information overload on the internet, content moderation is a crucial safeguard for a healthy online ecosystem. Without effective moderation, false information, malicious speech, and other harmful content will spread unchecked, severely damaging user experience, harming platform reputation, and even crossing legal boundaries. Therefore, content moderation is not only a fundamental requirement for the legal operation of platforms but also a necessary measure for building a clean and healthy cyberspace.
[0003] Currently, most platforms adopt an indiscriminate content review strategy, applying the same review process and standards to all user-submitted content.
[0004] However, the homogenized process of indiscriminate review strategies is creating serious efficiency bottlenecks. Because clearly normal content still needs to pass full review, a large amount of computing resources and human resources are consumed in meaningless screening, resulting in a significant decrease in overall review efficiency. Summary of the Invention
[0005] This application provides a data processing method, apparatus, device, and storage medium that can determine the corresponding security level of an object based on its historical records and implement differentiated audits. A simple audit strategy is applied to content published by objects with high security levels, while content published by objects with low security levels undergoes strict audits. By focusing audit resources on high-risk content and reducing redundant audits of low-risk content, audit efficiency is effectively reduced, both in terms of computing power and manpower.
[0006] In a first aspect, this application provides a data processing method, the method comprising:
[0007] Obtain all target records of the target object within a preset time period, wherein the target records include target behavior, target behavior type, and duration of target behavior occurrence;
[0008] Based on the target behavior, target behavior type, and duration of the target behavior in the target record, determine the target score corresponding to the target record;
[0009] Based on the target scores corresponding to all target records, the target security level of the target object is determined;
[0010] When the target object uploads target content, the target content is reviewed using the review strategy corresponding to the target security level.
[0011] Optionally, determining the target score corresponding to the target record based on the target behavior, target behavior type, and duration of the target behavior in the target record includes:
[0012] Based on the target behavior, a first score is determined, which indicates the magnitude of the impact of the target behavior;
[0013] Determine the target type weight corresponding to the target behavior type;
[0014] Determine the target decay factor based on the duration of the target behavior.
[0015] The target score is determined based on the first score, the target type weight, and the target decay factor.
[0016] Optionally, determining the target decay factor based on the duration of the target behavior includes:
[0017] Obtain the preset attenuation constant;
[0018] The target attenuation factor is determined based on the duration of the target behavior and the attenuation constant.
[0019] Optionally, determining the target security level of the target object based on the target scores corresponding to all target records includes:
[0020] The total target score is obtained based on the target scores corresponding to all target records.
[0021] Based on the total target score, the target security level of the target object is determined.
[0022] Optionally, determining the target security level of the target object based on the total target score includes:
[0023] Obtain the standard score corresponding to the target object;
[0024] The difference between the standard score and the target total score is taken as the target safety score;
[0025] Based on the target security score and the security score range corresponding to each security level, determine the target security score range in which the target security score falls;
[0026] The security level corresponding to the target security score range is taken as the target security level.
[0027] Optionally, the method further includes:
[0028] When the target record within the preset time period is updated, the step of determining the target security level of the target object is reset.
[0029] and / or,
[0030] When the preset time period changes, the step of determining the target security level of the target object is reset.
[0031] Optionally, the method further includes:
[0032] When an update command is received, the current security score of all objects is obtained;
[0033] Sort the current security scores of all objects to obtain a security score sequence;
[0034] Based on the number of objects corresponding to each security level, determine the maximum and minimum values for each security level in the security score sequence;
[0035] The range of security scores for each security level is determined based on the maximum and minimum values corresponding to each security level.
[0036] Secondly, this application provides a data processing apparatus, the apparatus comprising:
[0037] The acquisition unit is used to acquire all target records of the target object within a preset time period, wherein the target records include target behavior, target behavior type and target behavior occurrence duration;
[0038] The first determining unit is used to determine the target score corresponding to the target record based on the target behavior, target behavior type and target behavior occurrence duration in the target record;
[0039] The second determining unit is used to determine the target security level of the target object based on the target scores corresponding to all target records;
[0040] The review unit is used to review the target content by adopting the review strategy corresponding to the target security level when the target object uploads the target content.
[0041] Optionally, the first determining unit is configured to:
[0042] Based on the target behavior, a first score is determined, which indicates the magnitude of the impact of the target behavior;
[0043] Determine the target type weight corresponding to the target behavior type;
[0044] Determine the target decay factor based on the duration of the target behavior.
[0045] The target score is determined based on the first score, the target type weight, and the target decay factor.
[0046] Optionally, the first determining unit is configured to:
[0047] Obtain the preset attenuation constant;
[0048] The target attenuation factor is determined based on the duration of the target behavior and the attenuation constant.
[0049] Optionally, the second determining unit is used for:
[0050] The total target score is obtained based on the target scores corresponding to all target records.
[0051] Based on the total target score, the target security level of the target object is determined.
[0052] Optionally, the second determining unit is used for:
[0053] Obtain the standard score corresponding to the target object;
[0054] The difference between the standard score and the target total score is taken as the target safety score;
[0055] Based on the target security score and the security score range corresponding to each security level, determine the target security score range in which the target security score falls;
[0056] The security level corresponding to the target security score range is taken as the target security level.
[0057] Optionally, the device further includes a reset unit, the reset unit being configured to:
[0058] When the target record within the preset time period is updated, the step of determining the target security level of the target object is reset.
[0059] and / or,
[0060] When the preset time period changes, the step of determining the target security level of the target object is reset.
[0061] Optionally, the apparatus further includes a third determining unit, the third determining unit being configured to:
[0062] When an update command is received, the current security score of all objects is obtained;
[0063] Sort the current security scores of all objects to obtain a security score sequence;
[0064] Based on the number of objects corresponding to each security level, determine the maximum and minimum values for each security level in the security score sequence;
[0065] The range of security scores for each security level is determined based on the maximum and minimum values corresponding to each security level.
[0066] Thirdly, this application provides a data processing device, comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus, wherein the processor is configured to:
[0067] Obtain all target records of the target object within a preset time period, wherein the target records include target behavior, target behavior type, and duration of target behavior occurrence;
[0068] Based on the target behavior, target behavior type, and duration of the target behavior in the target record, determine the target score corresponding to the target record;
[0069] Based on the target scores corresponding to all target records, the target security level of the target object is determined;
[0070] When the target object uploads target content, the target content is reviewed using the review strategy corresponding to the target security level.
[0071] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described data processing method.
[0072] Compared with the prior art, the technical solution provided in this application has the following advantages: In this application embodiment, all target records of the target object within a preset time period are obtained, and the target records include target behavior, target behavior type, and target behavior occurrence duration; based on the target behavior, target behavior type, and target behavior occurrence duration in the target records, the target score corresponding to the target record is determined; based on the target scores corresponding to all target records, the target security level of the target object is determined; when the target object uploads target content, the review strategy corresponding to the target security level is used to review the target content. This application embodiment can determine the corresponding security level of an object based on its historical records and implement differentiated review, using a simple review strategy for content published by objects with high security levels and a strict review strategy for content published by objects with low security levels. Through the above method, review resources are focused on high-risk content, reducing repeated reviews of low-risk content, effectively reducing computing power and manpower costs, and improving review efficiency. Attached Figure Description
[0073] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0074] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0075] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.
[0076] Figure 1 A flowchart illustrating a data processing method provided in an embodiment of this application;
[0077] Figure 2 A flowchart illustrating a target scoring method provided in an embodiment of this application;
[0078] Figure 3 A flowchart illustrating a method for determining a target security level provided in an embodiment of this application;
[0079] Figure 4 A flowchart illustrating a method for determining a target security level provided in an embodiment of this application;
[0080] Figure 5 A flowchart illustrating a method for determining the security score range corresponding to each security level, provided in an embodiment of this application;
[0081] Figure 6 This is a schematic flowchart of a data processing apparatus provided in an embodiment of this application;
[0082] Figure 7 This is a schematic diagram of a data processing device provided in an embodiment of this application. Detailed Implementation
[0083] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0084] The following disclosure provides numerous different embodiments or examples for implementing various structures of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of the invention. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.
[0085] In the era of information overload on the internet, content moderation is a crucial barrier to ensuring a healthy online ecosystem. Without effective moderation, false information, malicious speech, and other harmful content will spread unchecked, severely damaging user experience, harming platform reputation, and even crossing legal boundaries. Therefore, content moderation is not only a basic requirement for the legal operation of platforms but also a necessary measure for building a clean and healthy cyberspace. Currently, most platforms adopt a non-discriminatory content moderation strategy, applying the same review process and standards to all user-submitted content. However, this homogenized process of non-discriminatory moderation is creating a serious efficiency bottleneck. Because clearly normal content still requires full review, a significant amount of computing resources and manpower are consumed in meaningless screening, leading to a substantial decrease in overall moderation efficiency.
[0086] To address the aforementioned issues, this application provides a data processing method. This method determines the corresponding security level of an object based on its historical records and implements differentiated review. Content published by objects with high security levels is subject to a simple review strategy, while content published by objects with low security levels undergoes strict review. By focusing review resources on high-risk content and reducing redundant reviews of low-risk content, this effectively reduces computing and labor costs and improves review efficiency. Figure 1 As shown, the specific steps include:
[0087] Step 101: Obtain all target records of the target object within a preset time period.
[0088] The target object can be all objects in the system platform or a subset of them; this is not limited. The preset time period is determined based on a preset time window and the current time. The target record includes the target behavior, the target behavior type, and the duration of the target behavior. The target behavior refers to the violation committed by the target object, which may include spam advertising, pornography, hate speech, terrorism-related or politically sensitive content, etc. The target behavior type corresponds to the content format involved in the violation, such as video, images and text, or plain text comments. The duration of the target behavior is the interval between the time the violation occurred and the current time; for example, the duration of the target behavior is 15 days, 30 days, etc.
[0089] In this step, data is collected from the content database, review logs, and user report records of the media playback platform. After cleaning and filtering, the complete historical record of the target object is compiled. Then, using the current time point as the starting point of a preset time window, a corresponding preset time period is defined. Finally, all records of the target object within this time period are selected from the entire historical record and identified as the target records.
[0090] It should be noted that the entity executing this application is the review system of the media playback platform, which is responsible for reviewing the content uploaded by the subject and performing review-related operations.
[0091] Step 102: Determine the target score corresponding to the target record based on the target behavior, target behavior type, and duration of the target behavior in the target record.
[0092] In this step, the target score can be determined in the following ways: First, obtain the pre-defined correspondence between behaviors, behavior types, behavior duration ranges, and scores. Based on the target behavior, target behavior type, and target behavior duration, find the matching score in this correspondence and use it as the target score for the target record. Second, first obtain the pre-defined correspondence between behaviors and scores, find the score corresponding to the target behavior and set it as the first score. Then, based on the target behavior type and target behavior duration, determine the target type weight and target decay factor respectively. Finally, multiply the first score, target type weight, and target decay factor together; the result is the target score. Alternatively, other methods can be used to determine the target score in this step; the specific method is not limited.
[0093] Step 103: Determine the target security level of the target object based on the target scores corresponding to all target records.
[0094] In this step, the target security level can be determined in the following ways: One method is to sum the target scores corresponding to all target records to obtain a total target score, and then, based on the preset correspondence between security levels and total scores, find the security level that matches the total score and set it as the target security level. Another method is to first obtain a preset standard score, calculate the target difference between the standard score and the target total score, and then, based on the preset correspondence between the difference and security levels, find the security level corresponding to the target difference and set it as the target security level. Of course, other methods can also be used to determine the target security level in this step; this is not limited to these methods.
[0095] After determining the target security level of the target object, the target object needs to be associated with and stored with the corresponding target security level to provide data support for subsequent related operations.
[0096] Step 104: When the target object uploads target content, the target content is reviewed using the review strategy corresponding to the target security level.
[0097] The review strategies differ depending on the security level; the higher the level, the more lenient the review, and the lower the level, the more stringent the review. For example, security levels are divided into high, medium, and low. The review strategy for high security level only requires machine review; the review strategy for medium security level adopts a standard process of machine review → ordinary personnel review; and the review strategy for low security level adds senior personnel review to the standard process, i.e., machine review → ordinary personnel review → senior personnel review.
[0098] In this step, it checks whether content uploaded by the target object has been received. If so, the content is identified as the target content. Next, it retrieves the pre-stored mapping between objects and security levels, finds the target security level associated with the target object within this mapping, and applies the corresponding review policy to review the target content.
[0099] In addition, the system stores the correspondence between objects, security levels, and partitions, clearly defining the security level corresponding to each object in each partition (such as video, animation, and live streaming partitions). Based on this, when a target object uploads target content, the system first determines the target partition selected by the user, then, based on the target object and target partition, queries the aforementioned correspondence to determine the target security level corresponding to the target object in the target partition, and finally applies the review strategy corresponding to that target security level to review the target content.
[0100] In this embodiment, all target records of a target object within a preset time period are obtained. Each target record includes target behavior, target behavior type, and duration of the target behavior. Based on the target behavior, target behavior type, and duration of the target behavior in each target record, a target score corresponding to that target record is determined. Based on the target scores corresponding to all target records, the target security level of the target object is determined. When the target object uploads target content, the content is reviewed using the review strategy corresponding to the target security level. This embodiment can determine the corresponding security level of an object based on its historical records and implement differentiated reviews. A simple review strategy is used for content published by objects with high security levels, while content published by objects with low security levels is subject to strict review. Through this method, review resources are focused on high-risk content, reducing redundant reviews of low-risk content, effectively reducing computing and labor costs, and improving review efficiency.
[0101] In this embodiment, a first score corresponding to the target behavior is first determined, reflecting the magnitude of the target behavior's impact. Then, the target type weight corresponding to the target behavior type is clarified, and a target attenuation factor is determined based on the duration of the target behavior. Finally, the target score is calculated by combining the first score, target type weight, and target attenuation factor. The target score calculated above comprehensively considers the impact of the target behavior itself, the differences in the behavior's carrier, and the degree to which the timeliness of the behavior weakens the impact, making the score result more consistent with reality. This avoids the one-sidedness of a single-dimensional evaluation and accurately reflects the true risk of the target behavior, providing a scientific and reliable basis for subsequent operations such as security level classification and audit strategy matching based on the score. Therefore, this embodiment provides a method for determining a target score, which further limits step 102, such as... Figure 2 As shown, the specific steps are as follows:
[0102] Step 201: Determine the first score based on the target behavior.
[0103] The first score indicates the magnitude of the impact of the target behavior.
[0104] In this step, technicians assign a corresponding score to each violation based on its impact, thus establishing a correspondence between violations and scores, which is then stored in the system. Subsequently, the target violation is identified by finding its corresponding score within this correspondence and designated as the first score.
[0105] Step 202: Determine the target type weight corresponding to the target behavior type.
[0106] Different types of behavior have different type weights. For example, video content, which contains multi-dimensional information such as images and audio, usually has a stronger dissemination and influence than pure text comments, and its corresponding type weight can be set to a higher value (such as 1.2); text and image content has both visual and textual information, and its weight can be set to a medium value (such as 1.0); while the dissemination scope of pure text comments is relatively limited, and its weight can be set to a lower value (such as 0.8).
[0107] In this step, the pre-defined correspondence between behavior types and type weights is obtained. Within this correspondence, the type weight corresponding to the target behavior type is found, and this type weight is determined as the target type weight.
[0108] Step 203: Determine the target decay factor based on the duration of the target behavior.
[0109] In this step, the longer the behavior occurred, the weaker its impact on the current assessment, and the smaller the attenuation factor; the more recent the occurrence, the more significant the impact, and the larger the attenuation factor. In this step, a preset duration range and its corresponding attenuation factor can be obtained. Based on the duration of the target behavior, its corresponding attenuation factor can be found within this relationship, and this attenuation factor can be determined as the target attenuation factor. Alternatively, a preset attenuation constant can be obtained; based on the duration of the target behavior and the attenuation constant, the target attenuation factor can be determined.
[0110] Step 204: Determine the target score based on the first score, target type weight, and target decay factor.
[0111] In this step, the first score, the target type weight, and the target decay factor are multiplied to obtain the target score. For example, according to the preset formula Target Scorei = Si * Wtypei * d, where Target Scorei is the target score corresponding to the i-th target record, Si is the first score corresponding to the i-th target record, Wtypei is the target type weight corresponding to the i-th target record, and di is the target decay factor corresponding to the i-th target record.
[0112] In this embodiment, a preset attenuation constant is first obtained, and then the target attenuation factor is calculated by combining the duration of the target behavior with the attenuation constant. By introducing a preset attenuation constant, a unified benchmark is established for determining the target attenuation factor, ensuring that the calculation rules for the attenuation degree corresponding to different durations are consistent. At the same time, associating the duration of the behavior with the attenuation constant can accurately reflect the attenuation law of the behavior's impact over time, making the attenuation factor more closely match the objective impact of the behavior's timeliness. Therefore, this embodiment provides a method for determining a target attenuation factor, which is a further limitation of step 203. The specific steps are: obtaining a preset attenuation constant; and determining the target attenuation factor based on the duration of the target behavior and the attenuation constant.
[0113] In this step, the system pre-stores attenuation constants. Based on the duration of the target behavior, the attenuation constant, and a preset formula, the target attenuation factor is determined. The preset formula is as follows: di is the target decay factor corresponding to the i-th target record, ti is the duration of the target behavior corresponding to the i-th target record, and λ is the decay constant (e.g., 0.01).
[0114] In this embodiment, the target scores of all target records are aggregated to obtain a total target score, which is then used to determine the target security level of the target object. This embodiment can quantify the comprehensive impact of an object's historical behavior through the total score, thereby accurately determining the security level of the object. Therefore, this embodiment provides a method for determining a target security level, which further defines step 103, such as... Figure 3 As shown, the specific steps are as follows:
[0115] Step 301: Obtain the total target score based on the target scores corresponding to all target records.
[0116] In this step, the target scores corresponding to all target records are added together to obtain the sum of all target scores, and this sum is determined as the total target score.
[0117] Step 302: Determine the target security level based on the overall target score.
[0118] In this step, the system pre-stores the correspondence between total scores and security levels. Based on the target's total score, its corresponding security level is determined from the correspondence and set as the target security level. Alternatively, the target security level of the target object is determined based on its standard score and the target total score.
[0119] In this embodiment, the standard score corresponding to the target object is first obtained, and the difference between the standard score and the target total score is calculated as the target security score. Then, based on the score range corresponding to each security level, the range to which the target security score belongs is determined, and the corresponding security level is then set as the target security level. Therefore, this embodiment provides a method for determining a target security level, as follows: Figure 4 As shown, the specific steps include:
[0120] Step 401: Obtain the standard score corresponding to the target object.
[0121] The standard score is the initial score of the target object, for example, a standard score of 1000.
[0122] In this step, the technician has preset standard scores in the system, so when this step needs to be performed, the pre-stored standard scores can be obtained.
[0123] Step 402: The difference between the standard score and the target total score is taken as the target safety score.
[0124] The higher the overall score, the lower the corresponding target security score, meaning the higher the risk of the target and the more critical the content it publishes needs to be reviewed. Conversely, the lower the overall score, the higher the corresponding target security score, indicating that the target is more secure and its content does not require extensive review.
[0125] In this step, the difference between the standard score and the target total score is calculated, and this difference is called the target safety score.
[0126] In addition, the target behaviors in this application also include positive behaviors, which refer to behaviors such as the corresponding content being rated as high-quality content, the corresponding content receiving a large number of likes, and effectively reporting others' violations. These behaviors correspond to bonus points. Therefore, when there is a target behavior that is a positive behavior, a second score is determined based on the target behavior, and the target safety score is added to the second score to obtain the final second score. The steps for determining the second score based on the target behavior are similar to the steps for determining the target total score, specifically: determining a third score based on the target behavior, which indicates the magnitude of the target behavior's impact; determining the type weight corresponding to the type of target behavior; determining a decay factor based on the duration of the target behavior; and determining the second score based on the third score, type weight, and decay factor.
[0127] Step 403: Determine the target security score range based on the target security score and the security score range corresponding to each security level.
[0128] In this step, since each security level corresponds to a range of security scores, the target security score range can be determined.
[0129] For example, a mapping table between security score ranges and security levels can be pre-established, such as: {"900-1000 points": Level 10, "800-899 points": Level 9, ..., "0-99 points": Level 1}.
[0130] Step 404: The security level corresponding to the target security score range is taken as the target security level.
[0131] In this embodiment of the application, when the target record within the preset time period is updated, the step of determining the target security level of the target object is reset; and / or, when the preset time period changes, the step of determining the target security level of the target object is reset.
[0132] In this step, when a new target record is added within the preset time period, it is considered that a new target record has been obtained. This usually occurs after step 105 completes the review of the target content. If the review result determines that the content is in violation, the system will generate a target record based on this content, thus creating a new target record. At this time, the target security level of the target object needs to be redefined. In addition, when the preset time period changes (for example, from December 9th to December 10th to December 10th to December 11th), it is generally a scheduled task that instructs the redefined security level of the object, and the target security level of the target object also needs to be redefined.
[0133] In this embodiment, when an instruction to update the security score range is received, the current security scores of all objects are first obtained and sorted. Then, the maximum and minimum values of the corresponding intervals are determined in the score sequence according to the preset number of objects for each security level, thereby defining the security score range for each level. Therefore, this application provides a method for determining the security score range corresponding to each security level, as follows: Figure 5 As shown, the specific steps include:
[0134] Step 501: When an update instruction is received, obtain the current security score of all objects.
[0135] The update command is used to indicate the range of security scores corresponding to each security level.
[0136] In this step, technicians can send update commands to the system according to actual needs to dynamically divide the security score ranges for each level. Specifically, when the system receives a command to update the security score range, it will obtain the current security scores of all objects. It can either directly retrieve existing scores or recalculate the current security score of each object based on the aforementioned method, thereby obtaining the corresponding total current security scores.
[0137] Step 502: Sort the current security scores of all objects to obtain a security score sequence.
[0138] In this step, the current safety scores of all objects are sorted in descending order to obtain a safety score sequence. Alternatively, the current safety scores of all objects are sorted in ascending order to obtain a safety score sequence.
[0139] Step 503: Based on the number of objects corresponding to each security level, determine the maximum and minimum values corresponding to each security level in the security score sequence.
[0140] In this step, if the security score sequence is arranged from largest to smallest, first select the corresponding number of security scores from the sequence based on the number of objects corresponding to the highest security level. Set the maximum value as the maximum value for that level and the minimum value as the minimum value for that level. Then, process in this manner until the maximum and minimum values for all security levels are determined. If the security score sequence is arranged from smallest to largest, the determination steps are similar and will not be detailed here.
[0141] Step 504: Determine the range of security scores for each security level based on the maximum and minimum values corresponding to each security level.
[0142] In this step, for each security level, a security score range is constructed with the minimum value corresponding to that security level as the lower limit and the maximum value as the upper limit.
[0143] like Figure 6 As shown, this application provides a data processing apparatus, which corresponds to the method embodiment, and specifically includes:
[0144] The acquisition unit 601 is used to acquire all target records of the target object within a preset time period, wherein the target records include target behavior, target behavior type and target behavior occurrence duration;
[0145] The first determining unit 602 is used to determine the target score corresponding to the target record based on the target behavior, target behavior type and target behavior occurrence duration in the target record;
[0146] The second determining unit 603 is used to determine the target security level of the target object based on the target scores corresponding to all target records;
[0147] The review unit 604 is used to review the target content by adopting the review strategy corresponding to the target security level when the target object uploads the target content.
[0148] Optionally, the first determining unit 602 is configured to:
[0149] Based on the target behavior, a first score is determined, which indicates the magnitude of the impact of the target behavior;
[0150] Determine the target type weight corresponding to the target behavior type;
[0151] Determine the target decay factor based on the duration of the target behavior.
[0152] The target score is determined based on the first score, the target type weight, and the target decay factor.
[0153] Optionally, the first determining unit 602 is configured to:
[0154] Obtain the preset attenuation constant;
[0155] The target attenuation factor is determined based on the duration of the target behavior and the attenuation constant.
[0156] Optionally, the second determining unit 603 is used for:
[0157] The total target score is obtained based on the target scores corresponding to all target records.
[0158] Based on the total target score, the target security level of the target object is determined.
[0159] Optionally, the second determining unit 603 is used for:
[0160] Obtain the standard score corresponding to the target object;
[0161] The difference between the standard score and the target total score is taken as the target safety score;
[0162] Based on the target security score and the security score range corresponding to each security level, determine the target security score range in which the target security score falls;
[0163] The security level corresponding to the target security score range is taken as the target security level.
[0164] Optionally, the device further includes a reset unit 605, the reset unit 605 being configured to:
[0165] When the target record within the preset time period is updated, the step of determining the target security level of the target object is reset.
[0166] and / or,
[0167] When the preset time period changes, the step of determining the target security level of the target object is reset.
[0168] Optionally, the device further includes a third determining unit 606, the third determining unit 606 being configured to:
[0169] When an update command is received, the current security score of all objects is obtained;
[0170] Sort the current security scores of all objects to obtain a security score sequence;
[0171] Based on the number of objects corresponding to each security level, determine the maximum and minimum values for each security level in the security score sequence;
[0172] The range of security scores for each security level is determined based on the maximum and minimum values corresponding to each security level.
[0173] like Figure 7 As shown in the figure, this application provides a data processing device, including a processor 701, a communication interface 702, a memory 703, and a communication bus 704, wherein the processor 701, the communication interface 702, and the memory 703 communicate with each other through the communication bus 704.
[0174] Memory 703 is used to store computer programs;
[0175] In one embodiment of this application, when the processor 701 executes a program stored in the memory 703, it implements the data processing method provided in any of the foregoing method embodiments, including:
[0176] Obtain all target records of the target object within a preset time period, wherein the target records include target behavior, target behavior type, and duration of target behavior occurrence;
[0177] Based on the target behavior, target behavior type, and duration of the target behavior in the target record, determine the target score corresponding to the target record;
[0178] Based on the target scores corresponding to all target records, the target security level of the target object is determined;
[0179] When the target object uploads target content, the target content is reviewed using the review strategy corresponding to the target security level.
[0180] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps performed by the data processing method provided in any of the foregoing method embodiments.
[0181] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. 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 the modules can be selected to achieve the purpose of this embodiment according to actual needs.
[0182] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0183] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.
[0184] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.
Claims
1. A data processing method, characterized in that, The method includes: Obtain all target records of the target object within a preset time period, wherein the target records include target behavior, target behavior type, and duration of target behavior occurrence; Based on the target behavior, target behavior type, and duration of the target behavior in the target record, determine the target score corresponding to the target record; Based on the target scores corresponding to all target records, the target security level of the target object is determined; When the target object uploads target content, the target content is reviewed using the review strategy corresponding to the target security level.
2. The method according to claim 1, characterized in that, The step of determining the target score corresponding to the target record based on the target behavior, target behavior type, and duration of the target behavior in the target record includes: Based on the target behavior, a first score is determined, which indicates the magnitude of the impact of the target behavior; Determine the target type weight corresponding to the target behavior type; Determine the target decay factor based on the duration of the target behavior. The target score is determined based on the first score, the target type weight, and the target decay factor.
3. The method according to claim 2, characterized in that, The step of determining the target attenuation factor based on the duration of the target behavior includes: Obtain the preset attenuation constant; The target attenuation factor is determined based on the duration of the target behavior and the attenuation constant.
4. The method according to claim 1, characterized in that, The step of determining the target security level of the target object based on the target scores corresponding to all target records includes: The total target score is obtained based on the target scores corresponding to all target records. Based on the total target score, the target security level of the target object is determined.
5. The method according to claim 4, characterized in that, The step of determining the target security level of the target object based on the total target score includes: Obtain the standard score corresponding to the target object; The difference between the standard score and the target total score is taken as the target safety score; Based on the target security score and the security score range corresponding to each security level, determine the target security score range in which the target security score falls; The security level corresponding to the target security score range is taken as the target security level.
6. The method according to claim 1, characterized in that, The method further includes: When the target record within the preset time period is updated, the step of determining the target security level of the target object is reset. and / or, When the preset time period changes, the step of determining the target security level of the target object is reset.
7. The method according to claim 5, characterized in that, The method further includes: When an update command is received, the current security score of all objects is obtained; Sort the current security scores of all objects to obtain a security score sequence; Based on the number of objects corresponding to each security level, determine the maximum and minimum values for each security level in the security score sequence; The range of security scores for each security level is determined based on the maximum and minimum values corresponding to each security level.
8. A data processing apparatus, characterized in that, The device includes: The acquisition unit is used to acquire all target records of the target object within a preset time period, wherein the target records include target behavior, target behavior type and target behavior occurrence duration; The first determining unit is used to determine the target score corresponding to the target record based on the target behavior, target behavior type and target behavior occurrence duration in the target record; The second determining unit is used to determine the target security level of the target object based on the target scores corresponding to all target records; The review unit is used to review the target content by adopting the review strategy corresponding to the target security level when the target object uploads the target content.
9. A data processing device, characterized in that, include: At least one communication interface; At least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; At least one memory connected to the at least one bus, wherein the processor is configured to: Obtain all target records of the target object within a preset time period, wherein the target records include target behavior, target behavior type, and duration of target behavior occurrence; Based on the target behavior, target behavior type, and duration of the target behavior in the target record, determine the target score corresponding to the target record; Based on the target scores corresponding to all target records, the target security level of the target object is determined; When the target object uploads target content, the target content is reviewed using the review strategy corresponding to the target security level.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the data processing method according to any one of claims 1 to 7.