Video review method and device

By grading and leveling adjustments to the video to be reviewed, and combining preset tags and playback volume allocation audit nodes, the problem of low efficiency of video manual review is solved, and the refined processing and efficiency improvement of video review is achieved.

CN114463674BActive Publication Date: 2024-11-22BEIJING SHAREIT INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210001663.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-01-04
Publication Date
2024-11-22
Estimated Expiration
2042-01-04

AI Technical Summary

Technical Problem

The existing technology cannot effectively improve the quality and efficiency of manual video review, resulting in low audit efficiency.

Method used

By grading the video to be reviewed, the manual audit nodes assigned to the corresponding level are reviewed based on the preset tags and playback volume, and the scoring and level adjustments are made based on the audit results, and the allocation and video level of the manual audit node are optimized.

Benefits of technology

The quality and efficiency of manual video review have been improved, the refined processing of video review has been achieved, and the review efficiency has been improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114463674B_ABST
    Figure CN114463674B_ABST
Patent Text Reader

Abstract

The present disclosure is about a method and device for video review; the method includes: grading the acquired videos to be reviewed to obtain graded videos to be reviewed; reviewing the graded videos to be reviewed through manual review nodes of corresponding levels to obtain review results; and outputting the review results. In this way, the present disclosure can refine the quality and efficiency of manual video review and improve the efficiency of video review.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to but is not limited to the field of Internet communication technology, and in particular to a method and device for video review. Background Art

[0002] With the development of Internet technology, users' demand for watching various types of videos has increased. Therefore, the corresponding video industry has become more and more prosperous, the video content has become more and more abundant, and the major video platforms produce a huge number of videos every day.

[0003] However, as a video platform, ensuring video compliance is an important task. Simple machine review is not enough, and manual review is needed. During manual review, how to ensure the efficiency and quality of manual review is an increasingly critical issue.

[0004] It can be seen that there is no relevant solution to the problem of low efficiency of video review due to the inability of relevant technologies to effectively refine the quality and efficiency of manual video review. Summary of the invention

[0005] The present disclosure provides a method and device for video review to solve the technical problem in the related art that the quality and efficiency of manual video review cannot be effectively refined, resulting in low efficiency of video review.

[0006] According to a first aspect of an embodiment of the present disclosure, a method for video review is provided, including: grading acquired videos to be reviewed to obtain graded videos to be reviewed; reviewing the graded videos to be reviewed through manual review nodes of corresponding levels to obtain review results; and outputting the review results.

[0007] In the above scheme, before grading the acquired videos to be reviewed, the method further includes: acquiring the videos to be reviewed from a video pool.

[0008] In the above scheme, the acquired videos to be reviewed are graded to obtain the graded videos to be reviewed, including: classifying the videos to be reviewed according to preset tags to obtain the classified videos to be reviewed; calculating the priority of the classified videos to be reviewed according to the weights of the preset tags to obtain the graded videos to be reviewed.

[0009] In the above scheme, after obtaining the graded videos to be reviewed, the method further includes: grading the graded videos to be reviewed according to the playback volume, and obtaining videos input into the manual review nodes of the corresponding level.

[0010] In the above scheme, after outputting the audit results, the method further includes: scoring the manual audit nodes of each level according to the audit results; and adjusting the level of the manual audit nodes according to the scores.

[0011] In the above scheme, scoring the manual review nodes at each level based on the review results includes: conducting an audit through the first type of quality inspection and / or the second type of quality inspection based on the review results to obtain a first audit result corresponding to the first type of quality inspection, and / or a second audit result corresponding to the second type of quality inspection; and obtaining scores for the manual review nodes at each level based on the first audit result and / or the second audit result.

[0012] In the above scheme, an audit is performed through the first type of quality inspection based on the audit result, and the first audit result corresponding to the first type of quality inspection includes: when the audit result includes an audit log, and the standard of the first type of quality inspection includes labels and / or manual review nodes, based on the labels of the video to be reviewed in the audit log, the manual review node is verified for the review of the video to be reviewed to obtain the first audit result; and / or, based on the level of the manual review node in the audit log, the manual review node is verified for the review of the video to be reviewed to obtain the first audit result.

[0013] In the above scheme, the second type of quality inspection is used for audit based on the audit results, and the second audit results corresponding to the second type of quality inspection include: when the audit results include the audit number of manual review nodes at each level, the manual review nodes are verified for the audited video based on the audit number to obtain the second audit results.

[0014] In the above scheme, adjusting the level of the manual review node based on the score includes: rating the manual review nodes at each level based on the score, and obtaining the rated manual review nodes, wherein the level of the video to be reviewed obtained by the rated manual review node will be adjusted accordingly.

[0015] In the above scheme, after adjusting the level of the manual review node according to the score, the method further includes: adjusting the level of the video to be reviewed according to the score, so that the video to be reviewed with the adjusted level is reviewed through the manual review node with the corresponding adjusted level.

[0016] According to the second aspect of the embodiments of the present disclosure, there is provided a device for video review, comprising: a grading module, for grading the acquired videos to be reviewed to obtain graded videos to be reviewed; a review module, for reviewing the graded videos to be reviewed through manual review nodes of corresponding levels to obtain review results; and an output module, for outputting the review results.

[0017] The technical solution provided by the present disclosure may have the following beneficial effects:

[0018] In the present disclosure, the acquired videos to be reviewed are graded to obtain graded videos to be reviewed; the graded videos to be reviewed are reviewed by manual review nodes of corresponding levels to obtain review results; the review results are output, and the quality and efficiency of manual review of the videos are refined to improve the efficiency of video review.

[0019] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0021] Figure 1 A schematic flow chart of a video review method provided by an exemplary embodiment is shown;

[0022] Figure 2a A schematic diagram showing a core process in a method for video review provided by an exemplary embodiment is shown;

[0023] Figure 2b A schematic diagram of video grading in a video review method provided by an exemplary embodiment is shown;

[0024] Figure 2c A schematic diagram of a review mechanism in a video review method provided by an exemplary embodiment is shown;

[0025] Figure 3a A schematic diagram of manual scoring in a video review method provided by an exemplary embodiment is shown;

[0026] Figure 3b A schematic diagram of machine scoring in a video review method provided by an exemplary embodiment is shown;

[0027] Figure 4 A schematic diagram showing a level adjustment in a video review method provided by an exemplary embodiment;

[0028] Figure 5 A schematic diagram of a video review apparatus provided by an exemplary embodiment is shown. DETAILED DESCRIPTION

[0029] The following is a description of the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. In the following description, reference is made to the drawings that form a part of the present application and show the specific aspects of the embodiments of the present application or the specific aspects of the embodiments of the present application in an illustrative manner. It should be understood that the embodiments of the present application can be used in other aspects and may include structural or logical changes not depicted in the drawings. Therefore, the following detailed description should not be understood in a restrictive sense, and the scope of the present application is defined by the appended claims. For example, it should be understood that the disclosure of the described method can be equally applicable to the corresponding device or system for performing the method, and vice versa. For example, if one or more specific method steps are described, the corresponding device may include one or more units such as functional units to perform the one or more method steps described (for example, one unit performs one or more steps, or multiple units, each of which performs one or more of the multiple steps), even if such one or more units are not explicitly described or illustrated in the drawings. On the other hand, for example, if a specific device is described based on one or more units such as functional units, the corresponding method may include a step to perform the functionality of the one or more units (e.g., a step to perform the functionality of the one or more units, or multiple steps, each of which performs the functionality of one or more of the multiple units), even if such one or more steps are not explicitly described or illustrated in the drawings. Further, it should be understood that, unless otherwise explicitly stated, the features of the various exemplary embodiments and / or aspects described herein may be combined with each other.

[0030] Example 1

[0031] According to a first aspect of an embodiment of the present disclosure, a method for video review is provided. Figure 1 A schematic diagram of a video review method provided by an exemplary embodiment is shown. Figure 1 As shown, the video review method provided by the embodiment of the present disclosure includes:

[0032] Step S102, grading the acquired videos to be reviewed to obtain graded videos to be reviewed;

[0033] Among them, the video review method provided by the embodiment of the present disclosure can be applied to the application scenario of manual and machine review of videos. The videos to be reviewed will be graded so that videos to be reviewed at different levels are assigned to corresponding manual review nodes.

[0034] The video review method provided by the embodiment of the present disclosure introduces a manual review video grading and priority system to ensure that high-quality and high-importance videos are reviewed first.

[0035] In a preferred implementation, before grading the acquired videos to be reviewed in step S102, the video review method provided by the embodiment of the present disclosure further includes: acquiring the videos to be reviewed from a video pool.

[0036] Among them, Figure 2a As shown, Figure 2a A schematic diagram showing a core process in a video review method provided by an exemplary embodiment is shown. Figure 2a All the videos awaiting review are obtained from the video pool.

[0037] In a preferred implementation, in step S102, the acquired videos to be reviewed are graded to obtain the graded videos to be reviewed, including: classifying the videos to be reviewed according to preset tags to obtain the classified videos to be reviewed; calculating the priority of the classified videos to be reviewed according to the weights of the preset tags to obtain the graded videos to be reviewed.

[0038] Among them, Figure 2b As shown, Figure 2b A schematic diagram of video grading in a method for video review provided by an exemplary embodiment is shown, in which videos to be reviewed are categorized by labeling from a video pool. After the label classification, the priority of the classified videos to be reviewed is calculated based on the weights of the labels (i.e., the preset labels in the embodiment of the present disclosure), and finally the graded videos to be reviewed are obtained.

[0039] Specifically, Figure 2b As shown, in the embodiment of the present disclosure, the preset tags are divided into basic tags and weighted tags. Among them, the basic tags mainly classify the basic information of the video to be reviewed, such as country, language, video length, cover, title, etc.;

[0040] Weight labels mainly refer to labels with special business or project attributes, which will mainly affect the subsequent distribution and reprinting of the video; including: sub-library ownership, whether it is a partner, subscription account level, etc.

[0041] The videos to be reviewed are classified by basic tags, and the priority of each video to be reviewed is further calculated by weight tags, and finally the videos to be reviewed at each level are obtained. That is, the classified videos to be reviewed flow into Figure 2b The video review pool at each level is shown in .

[0042] Among them, the proportion of basic labels is relatively low, and the influence coefficient is small and stable; the influence coefficient of weighted labels is large, and each label has its own influence coefficient specification.

[0043] The auditor level is determined by the auditor's score, which is a weighted sum of (audit volume level coefficient * impact coefficient).

[0044] The audit volume level coefficient is divided according to the daily audit volume of all auditors. For example, 0 to 1000 is level 1, 1000 to 2000 is level 2, and so on. The higher the level, the higher the audit volume level coefficient.

[0045] That is, the label determines the impact coefficient, and the impact coefficient determines the score, which in turn affects the final auditor level.

[0046] Furthermore, after obtaining the graded videos to be reviewed, the video review method provided by the embodiment of the present disclosure further includes: grading the graded videos to be reviewed according to the playback volume, and obtaining videos of manual review nodes of corresponding levels.

[0047] Among them, Figure 2c As shown, Figure 2c A schematic diagram of the review mechanism in the video review method provided by an exemplary embodiment is shown. In order to ensure the safety and quality of videos with high playback volume, it means that after the video is distributed, a secondary manual review is carried out based on playback indicators such as video UV / PV after the initial manual review is passed.

[0048] The videos are classified according to the number of views and other information. Each level will be manually reviewed by auditors of a specific level.

[0049] The video review method provided in the embodiment of the present disclosure adds a quality inspection and review mechanism to ensure that videos with high playback volume can be reviewed multiple times to ensure security;

[0050] Step S104, the graded videos to be reviewed are reviewed by manual review nodes of corresponding levels to obtain review results;

[0051] Among them, the videos to be reviewed after classification are assigned to the manual review nodes of the corresponding level for review, that is, Figure 2a The reviewers at all levels will conduct the review, so that the videos to be reviewed at all levels can be reviewed effectively.

[0052] Step S106, output the audit result.

[0053] In a preferred embodiment, after the review result is output in step S106, the video review method provided by the embodiment of the present disclosure further includes: scoring manual review nodes of each level according to the review result; and adjusting the level of the manual review node according to the score.

[0054] Specifically, based on steps S102 to S106, scores are given to the manual review nodes at each level according to the review results, and the levels of the manual review nodes are readjusted according to the scores. In the embodiment of the present disclosure, the scores include manual scoring and / or machine scoring, as follows:

[0055] In a preferred embodiment, scoring the manual review nodes at each level based on the review results includes: conducting an audit through a first type of quality inspection and / or a second type of quality inspection based on the review results to obtain a first audit result corresponding to the first type of quality inspection, and / or a second audit result corresponding to the second type of quality inspection; and obtaining a score for the manual review nodes at each level based on the first audit result and / or the second audit result.

[0056] Specifically, in the presently disclosed embodiment, the first type of quality inspection is manual quality inspection, that is, the first audit result is obtained by quality inspectors auditing the audit results of auditors at all levels, and the second type of quality inspection is machine quality inspection, that is, the audit results of auditors at all levels are audited according to preset standards to obtain the second audit result.

[0057] Among them, in the implementation, the scoring method in the embodiment of the present disclosure includes three implementation methods: method 1, manual review; method 2, machine review; method 3, manual review plus machine review. Based on the above three methods, the scores of manual review nodes at each level are obtained.

[0058] Method 1: Manual review

[0059] A first audit result corresponding to the first audit result of the first quality inspection is obtained by auditing through the first type of quality inspection based on the audit result, including: when the audit result includes an audit log, and the standard of the first type of quality inspection includes labels and / or manual review nodes, based on the labels of the video to be reviewed in the audit log, the manual review nodes are verified for the review of the video to be reviewed to obtain the first audit result; and / or, based on the levels of the manual review nodes in the audit log, the manual review nodes are verified for the review of the video to be reviewed to obtain the first audit result.

[0060] Specifically, Figure 3a As shown, Figure 3a A schematic diagram of manual scoring in a video review method provided by an exemplary embodiment is shown. Based on the review log in the review result (ie, Figure 3a The quality inspector will score the audited log by random inspection and obtain the first audit result.

[0061] Among them, there are two types of random inspections by quality inspectors:

[0062] Based on the label, 5% to 20% (dynamically adjustable) of the daily audit logs of each type of label are extracted to verify the results and mark the correctness. Then, based on the results of these sampling marks, the label impact factor is upgraded or downgraded. If the error rate is high, the impact factor of the label is increased, otherwise it is reduced.

[0063] Based on the auditor (i.e., the manual audit node in the embodiment of the present disclosure), 10% to 30% (dynamically adjustable) is extracted from each auditor's audit log to verify the results and mark the correctness. Then, based on the results of these spot checks and markings, the auditor's score is derived.

[0064] Method 2: Machine audit

[0065] The second audit result corresponding to the second audit result of the second quality inspection is audited based on the audit result, and the second audit result corresponding to the second quality inspection includes: when the audit result includes the audit number of manual review nodes at each level, the manual review node is verified for the audited video based on the audit number to obtain the second audit result.

[0066] Specifically, Figure 3b As shown, Figure 3b A schematic diagram of machine scoring in a video review method provided by an exemplary embodiment is shown. The scoring by the quality inspector is mainly based on the review quality dimension, while the scoring by the machine is mainly based on the review quantity dimension.

[0067] The final score of the auditor is determined by the machine scoring and the quality inspector scoring. The quality inspector scoring is mainly based on the audit quality dimension, while the machine scoring is mainly based on the audit quantity dimension.

[0068] Machine scoring collects data from the label dimension, calculates the normal distribution of the review volume for each label dimension, and then sets scores for different review levels according to a specific algorithm.

[0069] Method 3: Manual scoring + machine scoring, that is, a combination of method 1 and method 2.

[0070] In a preferred embodiment, adjusting the level of the manual review node based on the score includes: rating the manual review nodes at each level based on the score to obtain the rated manual review nodes, wherein the level of the video to be reviewed obtained by the rated manual review node will be adjusted accordingly.

[0071] Specifically, Figure 4 As shown, Figure 4 A schematic diagram of grade adjustment in a method of video review provided by an exemplary embodiment is shown. In the process of re-adjusting the grade based on the scores of reviewers at each level (i.e., the scores in the disclosed embodiment), the final grade of the reviewer at that level can be obtained based on the number of videos to be reviewed, the accuracy score and the weight ratio reviewed by the reviewers at each level.

[0072] Among them, based on Figure 3a and 3b , the scores of auditors at all levels will affect Figure 4The final level and power of the auditors in the system, that is, the higher the level of the auditor, the more privileges they can have and the higher impact audit tasks they can be assigned first. And the performance and bonus of each auditor are linked to the score, which in turn improves the enthusiasm of the auditors in their work.

[0073] That is, the machine scoring will determine the auditor’s final score from the dimension of audit quantity, while the quality inspector’s scoring will have an impact from the dimension of quality.

[0074] The scoring system will assign weights to quantity and quality based on the progress of the current application project. For example, in the early stages of a project, if you want to increase the number of videos, the ratio of quantity to quality may be 7:3; when the project reaches the deep cultivation stage, the ratio will be adjusted to 5:5. In some areas with strict laws and regulations, the ratio will be adjusted to 2:8.

[0075] In a preferred embodiment, after adjusting the level of the manual review node according to the score, the video review method provided by the embodiment of the present disclosure also includes: adjusting the level of the video to be reviewed according to the score, so that the video to be reviewed with the adjusted level is reviewed through the manual review node with the corresponding adjusted level.

[0076] Specific, combined Figure 2a After the quality inspectors and machines have conducted random inspections, the levels of the manual review nodes at each level can be adjusted based on the scores. At the same time, the levels of the videos to be reviewed in the video pool can also be adjusted, and then the videos to be reviewed with the adjusted levels can be assigned to the manual review nodes with the adjusted levels for review.

[0077] The video audit method provided by the embodiment of the present disclosure introduces a scoring PK mechanism to improve the enthusiasm of auditors: the auditors' work is scored by two methods: quality inspectors and machines. Auditors with high scores can obtain high-quality audit tasks and have the right to batch audit. They can also receive high rewards.

[0078] The technical solution provided by the present disclosure may have the following beneficial effects:

[0079] In the present disclosure, the acquired videos to be reviewed are graded to obtain graded videos to be reviewed; the graded videos to be reviewed are reviewed by manual review nodes of corresponding levels to obtain review results; the review results are output, and the quality and efficiency of manual review of the videos are refined to improve the efficiency of video review.

[0080] Example 2

[0081] According to a second aspect of an embodiment of the present disclosure, a video review device is provided. Figure 5 A schematic diagram of a video review device provided by an exemplary embodiment is shown. Figure 5As shown, the video review device provided by the embodiment of the present disclosure includes:

[0082] The grading module 52 is used to grade the acquired videos to be reviewed to obtain graded videos to be reviewed; the review module 54 is used to review the graded videos to be reviewed through manual review nodes of corresponding levels to obtain review results; the output module 56 is used to output the review results.

[0083] In the above scheme, the video review device provided by the embodiment of the present disclosure also includes: before grading the acquired videos to be reviewed, an acquisition module is used to acquire the videos to be reviewed from the video pool.

[0084] In the above scheme, the grading module 52 includes: a classification unit, which is used to classify the videos to be reviewed according to preset tags to obtain the classified videos to be reviewed; a first grading unit, which is used to calculate the priority of the classified videos to be reviewed according to the weights of the preset tags to obtain the graded videos to be reviewed.

[0085] In the above scheme, the video review device provided by the embodiment of the present disclosure also includes: a second grading unit, which is used to grade the graded videos to be reviewed according to the playback volume after obtaining the graded videos to be reviewed, and obtain videos of the manual review nodes of the corresponding level.

[0086] In the above scheme, the video review device provided by the embodiment of the present disclosure also includes: a scoring module, which is used to score the manual review nodes of each level according to the review results after outputting the review results; and an adjustment module, which is used to adjust the level of the manual review nodes according to the scores.

[0087] In the above scheme, the scoring module includes: an audit unit, which is used to conduct an audit through the first type of quality inspection and / or the second type of quality inspection according to the audit results, to obtain a first audit result corresponding to the first type of quality inspection, and / or a second audit result corresponding to the second type of quality inspection; a scoring unit, which is used to obtain scores for manual review nodes at each level based on the first audit result and / or the second audit result.

[0088] In the above scheme, the audit unit includes: a first verification sub-unit, which is used to verify the audit of the video to be audited by the manual review node according to the label of the video to be audited in the audit log, when the audit result includes an audit log and the first type of quality inspection standards include labels and / or manual review nodes, so as to obtain a first audit result; and / or a second verification sub-unit, which is used to verify the audit of the video to be audited by the manual review node according to the level of the manual review node in the audit log, so as to obtain a first audit result.

[0089] In the above scheme, the review unit includes: a third verification subunit, which is used to verify the review of the video to be reviewed by the manual review node according to the review number when the review result includes the review number of manual review nodes at each level, so as to obtain a second review result.

[0090] In the above scheme, the adjustment module includes: an adjustment unit, which is used to rate the manual review nodes at each level according to the scores to obtain the rated manual review nodes, wherein the level of the video to be reviewed obtained by the rated manual review nodes will be adjusted accordingly.

[0091] In the above scheme, the video review device provided by the embodiment of the present disclosure also includes: a level adjustment module, which is used to adjust the level of the video to be reviewed according to the score after adjusting the level of the manual review node according to the score, so that the video to be reviewed after the adjusted level is reviewed through the manual review node with the corresponding adjusted level.

[0092] Those skilled in the art will appreciate that the functions described in conjunction with the various illustrative logic blocks, modules, and algorithm steps disclosed herein can be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions described in the various illustrative logic blocks, modules, and steps can be stored or transmitted as one or more instructions or codes on a computer-readable medium and executed by a hardware-based processing unit. Computer-readable media may include computer-readable storage media, which corresponds to tangible media, such as data storage media, or includes any communication media that facilitates the transfer of computer programs from one place to another (e.g., according to a communication protocol). In this manner, computer-readable media may generally correspond to (1) non-temporary tangible computer-readable storage media, or (2) communication media, such as signals or carrier waves. Data storage media may be any available media that can be accessed by one or more computers or one or more processors to retrieve instructions, codes, and / or data structures for implementing the techniques described in this application. A computer program product may include computer-readable media.

[0093] As an example and not limitation, such computer-readable storage media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage, flash memory, or any other medium that can be used to store the desired program code in the form of instructions or data structures and can be accessed by a computer. Also, any connection is properly referred to as a computer-readable medium. For example, if instructions are transmitted from a website, server or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio and microwave are included in the definition of media. However, it should be understood that the computer-readable storage media and data storage media do not include connections, carrier waves, signals or other temporary media, but are actually directed to non-temporary tangible storage media. As used herein, disks and optical disks include compact disks (CDs), laser optical disks, optical optical disks, digital versatile disks (DVDs), and Blu-ray disks, where disks typically reproduce data magnetically, while optical disks reproduce data optically using lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0094] Instructions may be executed by one or more processors, such as one or more digital signal processors (DSPs), general purpose microprocessors, application specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuits. Thus, the term "processor" as used herein may refer to any of the aforementioned structures or any other structures suitable for implementing the techniques described herein. Additionally, in some aspects, the functions described by the various illustrative logic blocks, modules, and steps described herein may be provided within dedicated hardware and / or software modules configured for encoding and decoding, or incorporated in a combined codec. Moreover, the techniques may be fully implemented in one or more circuits or logic elements.

[0095] The techniques of the present application may be implemented in a variety of described devices or apparatuses, including a wireless handset, an integrated circuit (IC), or a set of ICs (e.g., a chipset). Various components, modules, or units are described in this application to emphasize functional aspects of the devices described for performing the disclosed techniques, but do not necessarily need to be implemented by different hardware units. In fact, as described above, the various units may be combined in a codec hardware unit in conjunction with appropriate software and / or firmware, or provided by interoperating hardware units (including one or more processors as described above).

[0096] In the above embodiments, the description of each embodiment has different emphases. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0097] The above is only an exemplary embodiment of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A video review method, characterized in that: include: The acquired videos to be reviewed are graded to obtain the graded videos to be reviewed; The graded videos to be reviewed are reviewed through manual review nodes of corresponding levels to obtain review results; wherein the levels of the manual review nodes are dynamically adjusted based on the progress of the video review task; Outputting the audit result; Among them, the grading of the acquired videos to be reviewed to obtain the graded videos to be reviewed includes: classifying the videos to be reviewed according to preset tags to obtain the classified videos to be reviewed; calculating the priority of the classified videos to be reviewed according to the weights of the preset tags to obtain the graded videos to be reviewed.

2. The method according to claim 1, characterized in that Before grading the acquired videos to be reviewed, the method further includes: The video to be reviewed is obtained from a video pool.

3. The method according to claim 1, characterized in that: After obtaining the graded video to be reviewed, the method further includes: The videos to be reviewed are graded according to the playback volume, and videos of the manual review nodes corresponding to the input levels are obtained.

4. The method according to claim 1 or 3, characterized in that: After outputting the audit result, the method further includes: Scoring the manual review nodes at each level according to the review results; The level of the manual review node is adjusted according to the score.

5. The method according to claim 4, characterized in that Scoring the manual review nodes at each level according to the review results includes: Conducting an audit through the first type of quality inspection and / or the second type of quality inspection according to the audit results to obtain a first audit result corresponding to the first type of quality inspection and / or a second audit result corresponding to the second type of quality inspection; The scores of the manual review nodes at each level are obtained according to the first review result and / or the second review result.

6. The method according to claim 5, characterized in that According to the audit result, the first type of quality inspection is audited, and the first audit result corresponding to the first type of quality inspection includes: In the case where the audit result includes an audit log, and the first type of quality inspection standard includes a label and / or a manual audit node, based on the label of the video to be audited in the audit log, the manual audit node is verified to verify the audit of the video to be audited to obtain the first audit result; and / or, According to the level of the manual review node in the review log, the review of the video to be reviewed by the manual review node is verified to obtain the first review result.

7. The method according to claim 5, characterized in that The second audit result corresponding to the second type of quality inspection is obtained by auditing the audit result according to the audit result, and includes: In the case where the review result includes the review quantity of the manual review nodes at each level, the review of the video to be reviewed by the manual review nodes is verified according to the review quantity to obtain the second review result.

8. The method according to claim 4, characterized in that The step of adjusting the level of the manual review node according to the score includes: The manual review nodes at each level are rated according to the scores to obtain the rated manual review nodes, wherein the level of the video to be reviewed obtained by the rated manual review nodes will be adjusted accordingly.

9. The method according to claim 4, characterized in that After adjusting the level of the manual review node according to the score, the method further includes: The level of the video to be reviewed is adjusted according to the score, so that the video to be reviewed after the adjusted level is reviewed through the manual review node corresponding to the adjusted level.

10. A video review device, characterized in that: include: A grading module, used to grade the acquired videos to be reviewed, and obtain the graded videos to be reviewed; An audit module is used to audit the graded videos to be audited through manual audit nodes of corresponding levels to obtain audit results; wherein the level of the manual audit node is dynamically adjusted based on the progress of the video audit task; An output module, used for outputting the audit result; Among them, the grading module includes: a classification unit, used to classify the videos to be reviewed according to preset tags to obtain the classified videos to be reviewed; a first grading unit, used to calculate the priority of the classified videos to be reviewed according to the weights of the preset tags to obtain the graded videos to be reviewed.