Multi-channel picture content auditing method and device, electronic equipment and storage medium

Abstract

The invention relates to a multi-channel picture content auditing method and device, electronic equipment and a storage medium. The method comprises the following steps: receiving a to-be-audited picture uploaded by any service party and a unique identifier of the service party; identifying a target third party for picture auditing according to the unique identifier of the business party; if the target third party is the third party audited by the first channel, sending the to-be-audited picture to the third party audited by the first channel, and determining a content audit result of the to-be-audited picture according to an audit result fed back by the third party audited by the first channel; and if the target third parties comprise the third party audited by the first channel and the third party audited by the second channel, sending the to-be-audited picture to the third party audited by the first channel and the third party audited by the second channel, and determining a content auditing result of the to-be-audited picture according to an auditing result fed back by the third party of the first channel auditing and an auditing result fed back by the third party of the second channel auditing. By adopting the method, the false alarm rate of picture content auditing can be reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing application, in particular to a multi-channel picture content review method and device, electronic equipment and storage medium. BACKGROUND

[0002] In the current online car-hailing field, there is a common problem of single review channel for picture content review uploaded by business parties. That is, for review of all picture content uploaded by business parties, only a single channel can be used for unified review, and other channels cannot be selected according to business scenarios. This single-channel review mode gradually exposes many drawbacks when facing complex and diverse business scenarios and picture content, especially a high false positive rate, which seriously affects the quality and efficiency of review. SUMMARY

[0003] Therefore, it is necessary to provide a multi-channel picture content review method, device, electronic equipment and storage medium to intelligently select a review channel according to a unique identifier of a business party, and reduce the false positive rate of picture content review.

[0004] According to a first aspect of certain example embodiments of the present application, a multi-channel picture content review method is provided, including: receiving a picture to be reviewed uploaded by any business party and a unique identifier of the business party; identifying a target third party for picture review according to the unique identifier of the business party; if the target third party is a third party for first-channel review, sending the picture to be reviewed to the third party for first-channel review, and determining a content review result of the picture to be reviewed according to a review result fed back by the third party for first-channel review; if the target third party includes a third party for first-channel review and a third party for second-channel review, sending the picture to be reviewed to the third party for first-channel review and the third party for second-channel review respectively, and determining the content review result of the picture to be reviewed according to a review result fed back by the third party for first-channel review and a review result fed back by the third party for second-channel review.

[0005] In one example, determining the content review result of the picture to be reviewed according to the review result fed back by the third party for first-channel review includes: if the review result fed back by the third party for first-channel review is that the picture is in violation, obtaining a violation identifier of the third party from the review result fed back by the third party for first-channel review; obtaining a local violation identifier from a violation identifier system according to a violation detection type of the picture to be reviewed; if the violation identifier of the third party is the same as a violation interception type mapped by the local violation identifier, determining that the content review result of the picture to be reviewed is not passed, and if the violation identifier of the third party is not the same as the violation interception type mapped by the local violation identifier, determining that the content review result of the picture to be reviewed is passed.

[0006] In one example, the content review result of the picture to be reviewed is determined according to the review result of the third-party feedback of the first channel review and the review result of the third-party feedback of the second channel review, including: if any of the review result of the third-party feedback of the first channel review and the review result of the third-party feedback of the second channel review indicates that the review fails, the content review result of the picture to be reviewed is determined as failing.

[0007] In one example, if any of the review result of the third-party feedback of the first channel review and the review result of the third-party feedback of the second channel review indicates that the review fails, the content review result of the picture to be reviewed is determined as failing, including: if any of the review result of the third-party feedback of the first channel review and the review result of the third-party feedback of the second channel review is picture violation, the violation identifier of the third party is obtained from the review result corresponding to the picture violation; the local violation identifier is obtained from the violation identifier system according to the violation detection type of the picture to be reviewed; if the violation identifier of the third party and the local violation identifier are mapped to the same violation interception type, it is determined that the review result corresponding to the picture violation indicates that the review fails.

[0008] In one example, the business party unique identifier contains identification information of any business party and scene information of the picture to be reviewed, and the target third party of the picture review is identified according to the business party unique identifier, including: the target third party of the picture review is queried from the pre-configured review strategy table according to the identification information of any business party and the scene information of the picture to be reviewed; if the query is successful, the target third party is determined as the third party of the first channel review according to the query result, or the target third party includes the third party of the first channel review and the third party of the second channel review; if the query fails, the target third party is determined as the third party of the default channel review.

[0009] In one example, a multi-channel picture content review method further includes: obtaining identification information of a plurality of business parties and a plurality of violation detection scenes; configuring a review strategy table according to the identification information of each business party and each violation detection scene, and the mapping relationship between the identification information of each business party and each violation detection scene and the third party of the channel review is constructed in the review strategy table.

[0010] In one example, the audit result of the third-party feedback of the first channel audit includes an audit suggestion and scene information for each of the multiple rule detection scenes, the audit suggestion including any one of an audit pass, an audit fail, and manual audit; the audit result of the third-party feedback of the first channel audit includes result information of the audit fail and the scene information, or result information of the audit pass; or, the audit result of the third-party feedback of the second channel audit includes an audit suggestion and scene information for each of the multiple rule detection scenes, the audit suggestion including any one of an audit pass, an audit fail, and manual audit; the audit result of the third-party feedback of the first channel audit includes result information of the audit fail and the scene information, or result information of the audit pass.

[0011] According to a second aspect of certain example embodiments of the present application, there is provided a multi-channel picture content audit apparatus, comprising: a receiving module configured to receive a picture to be audited uploaded by any business party and a unique identifier of the business party; an identifying module configured to identify a target third party for the picture audit according to the unique identifier of the business party; a first audit module configured to, if the target third party is a third party for a first channel audit, send the picture to be audited to the third party for the first channel audit, and determine a content audit result of the picture to be audited according to an audit result of the third party for the first channel audit; and a second audit module configured to, if the target third party includes a third party for a first channel audit and a third party for a second channel audit, send the picture to be audited to the third party for the first channel audit and the third party for the second channel audit respectively, and determine the content audit result of the picture to be audited according to an audit result of the third party for the first channel audit and an audit result of the third party for the second channel audit.

[0012] According to a third aspect of certain example embodiments of the present application, there is provided an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the steps of any of the above methods when executing the computer program.

[0013] According to a fourth aspect of certain example embodiments of the present application, there is provided a computer-readable storage medium having a computer program stored thereon, the computer program being executable on a processor to implement the steps of any of the above methods.

[0014] The multi-channel picture content review method, device, electronic device and storage medium described above receive a picture to be reviewed uploaded by any business party and a unique identifier of the business party; identify a target third party for picture review according to the unique identifier of the business party; if the target third party is a third party for first channel review, send the picture to be reviewed to the third party for first channel review, and determine a content review result of the picture to be reviewed according to a review result fed back by the third party for first channel review; if the target third party includes the third party for first channel review and a third party for second channel review, send the picture to be reviewed to the third party for first channel review and the third party for second channel review respectively, and determine the content review result of the picture to be reviewed according to a review result fed back by the third party for first channel review and a review result fed back by the third party for second channel review. Therefore, the corresponding picture review channel can be intelligently selected according to the unique identifier of the business party, and the content review result of the picture to be reviewed can be determined in combination with the review results of the two channels when two channels are required for review, thereby reducing the false positive rate of picture content review. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 A flowchart of a multi-channel picture content review method in some example embodiments of the present application; Figure 2 An implementation diagram of a multi-channel picture content review method in some specific example embodiments of the present application; Figure 3 A structural block diagram of a multi-channel picture content review device in some example embodiments of the present application; Figure 4 An internal structural diagram of an electronic device in some example embodiments of the present application. DETAILED DESCRIPTION

[0016] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0017] The following detailed description is provided to help the reader obtain a comprehensive understanding of the methods, devices, electronic devices, storage media and / or computer program products described herein. However, various changes, modifications and equivalents of the methods, devices, storage media and / or computer program products described herein will be apparent to those skilled in the art after understanding the disclosure of the present application. For example, the order of the operations described herein is only an example and is not limited to those set forth herein, but can be changed as will be apparent to those skilled in the art after understanding the disclosure of the present application, except for the operations that must occur in a specific order. In addition, the description of features known in the art can be omitted in order to be more clear and concise.

[0018] The features described herein can be implemented in different forms and should not be construed as limited to the examples described herein. Rather, these examples have been provided so that this disclosure will be thorough and will fully convey the scope of the methods, electronic devices, and / or storage media described herein to those skilled in the art.

[0019] The terminology used herein is for the purpose of describing various examples only and is not intended to be limiting of the disclosure. As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. The terms "comprises," "comprising," "includes," "including," and "has," "having," and the like are inclusive of the terms "consisting of" and "consisting essentially of" and are intended to be open-ended, allowing for the inclusion of additional features or components.

[0020] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein should not be interpreted as limiting the disclosure to the specific embodiments described herein and / or illustrated in the drawings. It will be understood by those within the art that, in some aspects of the disclosure, relative terms are intended to encompass different orientations of the device. In addition, specific details are not to be understood as limiting, since the embodiments of the disclosure can be practiced with or without such specific details.

[0021] It should be noted that the terms "first", "second", and the like, used in the description and the claims of the present application are intended to distinguish between similar objects, but are not necessarily used to describe a particular sequential or chronological order. It is to be understood that the use of data so designated is not to be construed as limiting of the embodiments of the present application, unless the context clearly indicates otherwise. The implementations described in the following certain example embodiments are not meant to be exhaustive or to be limiting in any way. Rather, they are to be considered as merely examples of apparatus and methods consistent with the present application as detailed in the following claims.

[0022] Also, in the description of the examples, when it is considered that a detailed description of related structures or functions that are well-known can cause obscuring the present application, such a detailed description will be omitted.

[0023] Hereinafter, the embodiments will be described in detail with reference to the accompanying drawings. However, the embodiments can be implemented in various forms and are not limited to the examples described herein.

[0024] In some example embodiments of the present application, as shown in Figure 1 A multi-channel picture content review method is provided. The method is applied to a background electronic device, for example, and includes the following steps: Step S101, receiving a picture to be reviewed uploaded by any business party and a unique identifier of the business party.

[0025] In this embodiment, the background manages multiple business parties. The picture to be reviewed uploaded by any business party and the unique identifier of the business party are used to represent the identity of the business party. The background performs picture content review on the picture to be reviewed according to the unique identifier of the business party. Specifically, the business party can be a driver end of a network car-hailing service, and the picture to be reviewed is a picture carried by the driver end when reporting a service. For example, the driver end of a car accident scene needs to report the service termination reason, which contains a proof picture. The background needs to review whether the picture content is illegal.

[0026] Step S102, identifying a target third party for picture review according to the unique identifier of the business party.

[0027] In this embodiment, the background configures different third parties for picture review for different business parties. After obtaining the unique identifier of the business party, the audit channel of the picture to be reviewed, i.e., the target third party, is determined based on the unique identifier of the business party.

[0028] In one example, the unique identifier of the business party includes identification information of any business party and scene information of the picture to be reviewed. Identifying the target third party for picture review according to the unique identifier of the business party includes: querying the target third party for picture review from a pre-configured audit strategy table according to the identification information of any business party and the scene information of the picture to be reviewed; if the query is successful, determining the target third party to be a first-channel third party for review according to the query result, or the target third party includes a first-channel third party for review and a second-channel third party for review; if the query fails, determining the target third party to be a default-channel third party for review.

[0029] The configuration step of the audit strategy table includes: obtaining identification information of multiple business parties and multiple illegal detection scenes; configuring the audit strategy table according to the identification information of each business party and each illegal detection scene, and constructing a mapping relationship between the identification information of each business party and each illegal detection scene and the third party for channel review in the audit strategy table.

[0030] Specifically, the unique identifier for a business entity includes the identification information of any business entity and the context information of the image to be reviewed. For example, `service_type` represents the identifier of the business entity, and `business_type` represents the context information of the image to be reviewed; the two together constitute the unique identifier for the business entity. The backend identifies the business entity's identifier and the context of the image to be reviewed from the unique identifier. Then, the backend content security service queries the configuration policy in the review policy table based on these two pieces of information to determine the target third party.

[0031] For example, the customer service team (service_type) and chat scenarios (business_type) are configured to use a third-party platform for image content review. This third-party platform checks for violations in images under review based on multiple scenarios, and then reports to the backend which scenarios the images violate.

[0032] For example, in a scenario where the asset team (service_type) and drivers upload profile pictures (business_type), a dual-channel review process is configured, involving both a primary review channel and a secondary review channel. The business side can only pass two parameters: service_type and business_type. The content security service uses this information to query the configuration policy in the review policy table to determine the target third party for dual-channel review.

[0033] Specifically, business users need to add a unique identifier to the content security review policy table. Each function has a unique identifier for the business user. When the system reports images to be reviewed, it also reports the unique identifier of the business user to the backend content security review service. The content security review service checks the review policy table based on the unique identifier of the business user to see if there is a configured policy. If so, it returns the configured policy; otherwise, it returns the configured default channel policy.

[0034] The content security audit strategy table has the following structure: CREATE TABLE `content_detection_strategy` ( `id` bigint(20) unsigned NOT NULL AUTO_INCREMENT, `service_type` varchar(64) NOT NULL DEFAULT '' COMMENT 'Service type of the caller', `business_type` varchar(64) NOT NULL DEFAULT '' COMMENT 'Scenario Type', `channel_strategy` varchar(16) NOT NULL DEFAULT 'ALI' COMMENT 'Detection channel strategy: ALI, GAODE, ALI_AND_GAODE', `result_strategy` varchar(16) NOT NULL DEFAULT 'ALI' COMMENT 'Audit result selection strategy: ALI,GAODE,ALI_AND_GAODE', `create_user` bigint(20) DEFAULT '0' COMMENT 'Create user id', `block` varchar(64) NOT NULL DEFAULT '' COMMENT 'Interception type', `update_user` bigint(20) DEFAULT '0' COMMENT 'Modify user id', `create_time` timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP COMMENT 'Creation Time', `update_time` datetime NOT NULL DEFAULT CURRENT_TIMESTAMP ON UPDATECURRENT_TIMESTAMP COMMENT 'Modified time', PRIMARY KEY (`id`), UNIQUE KEY `service_type_business_type` (`service_type`,`business_type`) ) ENGINE=InnoDB AUTO_INCREMENT=19 DEFAULT CHARSET=utf8.

[0035] Among them, service_type + business_type constitute a unique business identifier.

[0036] The business service_type describes the organization of the calling party, such as a financial team. The business_type further describes the scenario information, for example, financial report uploading. The channel_strategy describes which channel is used for detection. The result_strategy describes which channel is used for the review result. The block describes which content of the violation scenario needs to be intercepted. Other fields of information record the policy change operation.

[0037] In step S103, if the target third party is a first-channel review third party, the to-be-reviewed picture is sent to the first-channel review third party, and the content review result of the to-be-reviewed picture is determined according to the review result fed back by the first-channel review third party.

[0038] In this embodiment, the identified target third party can be a single-channel review third party or a plurality of channel review third parties. If it is a single-channel review third party, i.e., a first-channel review third party, the to-be-reviewed picture is sent to the first-channel review third party. The first-channel review third party performs picture content review on the to-be-reviewed picture, identifies whether there is a violation content in the to-be-reviewed picture, and feeds back a review result to the background.

[0039] In one example, the above-mentioned determination of the content review result of the to-be-reviewed picture according to the review result fed back by the first-channel review third party includes: if the review result fed back by the first-channel review third party is that the picture is in violation, obtaining a third-party violation identifier from the review result fed back by the first-channel review third party; obtaining a local violation identifier from a violation identifier system according to a violation detection type of the to-be-reviewed picture; if the third-party violation identifier and the local violation identifier are mapped to the same violation interception type, determining that the content review result of the to-be-reviewed picture is not passed, and if the third-party violation identifier and the local violation identifier are not mapped to the same violation interception type, determining that the content review result of the to-be-reviewed picture is passed.

[0040] In this example, when the review result fed back by the first-channel review third party is that the picture is in violation, the background immediately performs interception processing on the to-be-reviewed picture. Then, a local violation identifier corresponding to a violation detection type of the to-be-reviewed picture is obtained from an internal violation identifier system, and if the third-party violation identifier and the local violation identifier are mapped to the same violation interception type, it is determined that the picture content of the to-be-reviewed picture is in violation, and the to-be-reviewed picture is intercepted. Otherwise, it is determined that the picture content of the to-be-reviewed picture is not in violation, and the uploaded to-be-reviewed picture is released. Therefore, by configuring a white list, it is allowed to take release measures on some types of violation pictures in a specific scenario.

[0041] For example, if the third-party of the first channel audit determines that the to-be-audited picture exists picture violation, and the third-party violation identifier is porn, the internal local violation identifier is Blm_Sexy through the mapping relationship, and the local configured interception type is not consistent, at this time, the background does not intercept the to-be-audited picture.

[0042] In step S104, if the target third-party includes the third-party of the first channel audit and the third-party of the second channel audit, the to-be-audited picture is sent to the third-party of the first channel audit and the third-party of the second channel audit respectively, and the content audit result of the to-be-audited picture is determined according to the audit result fed back by the third-party of the first channel audit and the audit result fed back by the third-party of the second channel audit.

[0043] In the embodiment, when the identified target third-party is the third-party of the first channel audit and the third-party of the second channel audit, the to-be-audited picture needs to be sent to the third-party of the first channel audit and the third-party of the second channel audit for picture content audit, and the audit results of the two channel audits are collected, and the content audit result of the to-be-audited picture is determined in combination with the audit results of the two channel audits. It can be that when the audit result of any channel audit indicates that the to-be-audited picture exists violation, it is determined that the content audit result of the to-be-audited picture exists violation, the audit is not passed, and the to-be-audited picture uploaded by the business party is intercepted. When the audit results of the two channel audits indicate that the to-be-audited picture does not exist violation, it is determined that the content audit result of the to-be-audited picture is passed, and the picture is not processed.

[0044] In one example, the audit result fed back by the third-party of the first channel audit includes the audit suggestion and scene information of each violation detection scene in multiple violation detection scenes, and the audit suggestion includes any one of audit pass, audit fail and manual audit; the audit result fed back by the third-party of the first channel audit includes result information of audit fail and scene information, or result information of audit pass. Alternatively, the audit result fed back by the third-party of the second channel audit includes the audit suggestion and scene information of each violation detection scene in multiple violation detection scenes, and the audit suggestion includes any one of audit pass, audit fail and manual audit; the audit result fed back by the third-party of the first channel audit includes result information of audit fail and scene information, or result information of audit pass.

[0045] Specifically, in the two channels of the third-party of the first channel audit and the third-party of the second channel audit, any one channel supports sending according to a specific violation scene. The other channel does not support sending according to a specific violation scene, that is, the other channel performs all violation scene detection, and the other channel returns the detected scene information.

[0046] The channel supports sending according to a specific violation scene, and the returned audit result is as follows: { "msg": "OK", "code": 200, "data": [ { "results": [ { "suggestion": "block", "scene": "porn" }, { "suggestion": "pass", "scene": "terrorism" }, { "suggestion": "pass", "scene": "qrcode" }, { "suggestion": "pass", "scene": "ad" }, { "suggestion": "pass", "scene": "live" }, { "suggestion": "pass", "scene": "logo" } ] } ] }。

[0047] Where suggestion indicates the audit suggestion, including three cases. That is: pass (normal), review (manual review), and block (violation). Scene indicates the detected scene information.

[0048] Another channel does not support sending according to a specific violation scene, and for the same picture to be audited, the audit result of sending is as follows: { "data":{ "result":"1", "riskTypeInfoList":[{ "name":"" }] }。

[0049] The background system maps the two audit results into internal violation scenarios according to a mapping table of the audit results.

[0050] In one example, the determination of the content audit result of the to-be-audited picture according to the audit result of the third-party feedback of the first-channel audit and the audit result of the third-party feedback of the second-channel audit includes: if any of the audit result of the first-channel audit and the audit result of the second-channel audit indicates that the audit is not passed, the content audit result of the to-be-audited picture is determined as not passed.

[0051] If any of the audit result of the first-channel audit and the audit result of the second-channel audit indicates that the audit is not passed, the content audit result of the to-be-audited picture is determined as not passed, including: if any of the audit result of the first-channel audit and the audit result of the second-channel audit is picture violation, the third-party violation identifier is obtained from the audit result corresponding to the picture violation; the local violation identifier is obtained from the violation identifier system according to the violation detection type of the to-be-audited picture; if the third-party violation identifier and the local violation identifier are mapped to the same violation interception type, it is determined that the audit result corresponding to the picture violation indicates that the audit is not passed.

[0052] Specifically, when the audit result of any channel audit is picture violation, the background immediately performs interception processing on the to-be-audited picture. At the same time, the third party whose audit result is picture violation is determined, and the violation identifier is obtained from the audit result of the third party and mapped to the internal violation identifier system to obtain the local violation identifier. If the violation interception types indicated by the two are the same, it is determined that the audit is not passed. Otherwise, it is determined that the audit is passed. Therefore, the violation identifiers of the audit results of multiple channels are uniformly mapped to the internal violation identifier system of the background, and the white list configuration of specific scenarios is realized.

[0053] ​The multi-channel picture content review method described above receives a picture to be reviewed uploaded by any business party and a unique identifier of the business party; identifies a target third party for picture review according to the unique identifier of the business party; if the target third party is a third party for first channel review, sends the picture to be reviewed to the third party for first channel review, and determines the content review result of the picture to be reviewed according to the review result fed back by the third party for first channel review; if the target third party includes the third party for first channel review and the third party for second channel review, sends the picture to be reviewed to the third party for first channel review and the third party for second channel review respectively, and determines the content review result of the picture to be reviewed according to the review result fed back by the third party for first channel review and the review result fed back by the third party for second channel review. Therefore, the corresponding picture review channel can be intelligently selected according to the unique identifier of the business party, and when two channels are required for review, the content review result of the picture to be reviewed is determined in combination with the review results of the two channels, thereby reducing the false positive rate of picture content review.

[0054] In summary, a multi-channel picture content review method of the above embodiment is described below with a specific example: Reference Figure 2 As shown, the business party inputs a pre-agreed unique identifier of the business party, for example, an order identifier when requesting a content security review service. The content security review service matches the review strategy table that has been created according to the unique identifier of the business party, and selects a third party for channel review according to the review strategy table. After receiving the review result of the third party channel, it is converted into an internal identifier and matched with a whitelist strategy. If the current scenario successfully matches the whitelist strategy, the order service picture is released.

[0055] Therefore, the review channel can be dynamically selected according to the business scenario, such as single-channel service detection in the customer service chat scenario, and double-channel submission in the driver avatar upload scenario. Different business scenarios can be set with specific violation detection types, and when the driver uploads the avatar, a variety of violations including logos and two-dimensional codes are comprehensively checked.

[0056] It should be understood that although each step in the flowchart is displayed in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps of the flowchart can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these sub-steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or sub-steps or stages of other steps.

[0057] In some example embodiments of the present application, as shown in Figure 3 A multi-channel picture content review device is provided, including a receiving module 301, an identifying module 302, a first review module 303, and a second review module 304. The receiving module 301 is configured to receive a picture to be reviewed uploaded by any service party and a unique identifier of the service party; the identifying module 302 is configured to identify a target third party for picture review according to the unique identifier of the service party; the first review module 303 is configured to send the picture to be reviewed to the third party for first channel review if the target third party is the third party for first channel review, and determine a content review result of the picture to be reviewed according to a review result fed back by the third party for first channel review; and the second review module 304 is configured to send the picture to be reviewed to the third party for first channel review and the third party for second channel review if the target third party includes the third party for first channel review and the third party for second channel review, and determine the content review result of the picture to be reviewed according to a review result fed back by the third party for first channel review and a review result fed back by the third party for second channel review.

[0058] In one example, determining the content review result of the picture to be reviewed according to the review result fed back by the third party for first channel review includes: if the review result fed back by the third party for first channel review is that the picture is in violation, obtaining a violation identifier of the third party from the review result fed back by the third party for first channel review; obtaining a local violation identifier from a violation identifier system according to a violation detection type of the picture to be reviewed; if the violation identifier of the third party is the same as a violation interception type mapped by the local violation identifier, determining that the content review result of the picture to be reviewed is not passed, and if the violation identifier of the third party is not the same as the violation interception type mapped by the local violation identifier, determining that the content review result of the picture to be reviewed is passed.

[0059] In one example, determining the content review result of the picture to be reviewed according to the review result fed back by the third party for first channel review and the review result fed back by the third party for second channel review includes: if any of the review result fed back by the third party for first channel review and the review result fed back by the third party for second channel review indicates that the review is not passed, determining that the content review result of the picture to be reviewed is not passed.

[0060] In one example, if any of the audit results of the third-party feedback of the first channel audit and the third-party feedback of the second channel audit indicates that the audit is not passed, the content audit result of the to-be-audited picture is determined to be not passed, including: if any of the audit results of the third-party feedback of the first channel audit and the third-party feedback of the second channel audit is picture violation, the third-party violation identifier is obtained from the audit result corresponding to the picture violation; the local violation identifier is obtained from the violation identifier system according to the violation detection type of the to-be-audited picture; if the third-party violation identifier and the local violation identifier are mapped to the same violation interception type, it is determined that the audit result corresponding to the picture violation indicates that the audit is not passed.

[0061] In one example, the business party unique identifier contains the identification information of any business party and the scene information of the to-be-audited picture, and the target third party of the picture audit is identified according to the business party unique identifier, including: the target third party of the picture audit is queried from the pre-configured audit strategy table according to the identification information of any business party and the scene information of the to-be-audited picture; if the query is successful, the target third party is determined to be the third party of the first channel audit according to the query result, or the target third party includes the third party of the first channel audit and the third party of the second channel audit; if the query fails, the target third party is determined to be the third party of the default channel audit.

[0062] In one example, the multi-channel picture content audit device further includes a construction module configured to obtain identification information of a plurality of business parties and a plurality of violation detection scenes; and configure an audit strategy table according to the identification information of each business party and each violation detection scene, and the mapping relationship between the identification information of each business party and each violation detection scene and the third party of the channel audit is constructed in the audit strategy table.

[0063] In one example, the audit result of the third party of the first channel audit includes the audit suggestion of each violation detection scene in the plurality of violation detection scenes and the scene information, and the audit suggestion includes any of the audit passed, the audit not passed, and the manual audit; the audit result of the third party of the first channel audit includes the result information of the audit not passed and the scene information, or the result information of the audit passed; or, the audit result of the third party of the second channel audit includes the audit suggestion of each violation detection scene in the plurality of violation detection scenes and the scene information, and the audit suggestion includes any of the audit passed, the audit not passed, and the manual audit; the audit result of the third party of the first channel audit includes the result information of the audit not passed and the scene information, or the result information of the audit passed.

[0064] The specific limitation of the multi-channel picture content review device can refer to the limitation of the multi-channel picture content review method, which will not be repeated here. Each module in the multi-channel picture content review device can be realized by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the electronic device in hardware form, or can be stored in the memory in the electronic device in software form, so that the processor calls and executes the operation corresponding to each module.

[0065] In some example embodiments of the present application, an electronic device, which can be a server, has an internal structure diagram as shown in Figure 4 The electronic device includes a processor, a memory, a network interface and a database connected by a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store data information uploaded by a business party. The network interface of the electronic device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement a multi-channel picture content review method.

[0066] Those skilled in the art can understand that Figure 4 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0067] In some example embodiments of the present application, an electronic device is provided, which includes a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the multi-channel picture content review method in any of the example embodiments described above.

[0068] In some example embodiments of the present application, a computer readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the multi-channel picture content review method in any of the example embodiments described above.

[0069] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, storage, databases, or other media in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0070] The technical features of the above embodiments can be combined in any way. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, but as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0071] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, some modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for reviewing image content across multiple channels, characterized in that, The method includes: It can receive images for review uploaded by any business party, along with the business party's unique identifier. The target third party for image review is identified based on the unique identifier of the business entity. If the target third party is a third party reviewed by the first channel, then the image to be reviewed is sent to the third party reviewed by the first channel, and the content review result of the image to be reviewed is determined according to the review result fed back by the third party reviewed by the first channel. If the target third party includes a third party that reviews through a first channel and a third party that reviews through a second channel, the image to be reviewed will be sent to both the third party that reviews through the first channel and the third party that reviews through the second channel, and the content review result of the image to be reviewed will be determined based on the review results provided by the third party that reviews through the first channel and the third party that reviews through the second channel.

2. The method according to claim 1, characterized in that, The step of determining the content review result of the image to be reviewed based on the review result feedback from the third party reviewed through the first channel includes: If the review result from the third party's feedback on the first channel is that the image is in violation, then the violation identifier of the third party is obtained from the review result from the third party's feedback on the first channel. Based on the violation detection type of the image to be reviewed, obtain the local violation identifier from the violation identifier system; If the violation identifier of the third party is the same as the violation interception type mapped to the local violation identifier, the content review result of the image to be reviewed is determined to be unsuccessful. If the violation identifier of the third party is not the same as the violation interception type mapped to the local violation identifier, the content review result of the image to be reviewed is determined to be successful.

3. The method according to claim 1, characterized in that, The step of determining the content review result of the image to be reviewed based on the review results from the third-party feedback received through the first channel and the review results from the third-party feedback received through the second channel includes: If either the review result from the first channel or the review result from the second channel indicates that the review is unsuccessful, then the content review result of the image to be reviewed is determined to be unsuccessful.

4. The method according to claim 3, characterized in that, If either the review result from the first channel's third-party feedback or the review result from the second channel's third-party feedback indicates that the review is unsuccessful, then the content review result of the image to be reviewed is determined to be unsuccessful, including: If either the review result from the first channel or the review result from the second channel indicates an image violation, then the violation identifier of the third party is obtained from the review result corresponding to the image violation. Based on the violation detection type of the image to be reviewed, obtain the local violation identifier from the violation identifier system; If the violation identifier of the third party is the same as the violation interception type mapped by the local violation identifier, then the review result corresponding to the image violation is determined to be unsuccessful.

5. The method according to claim 1, characterized in that, The unique identifier of the business party includes the identification information of any business party and the scene information of the image to be reviewed. Identifying the target third party for image review based on the unique identifier of the business party includes: Based on the identification information of any business party and the scene information of the image to be reviewed, the target third party for image review is queried from the pre-configured review strategy table; If the query is successful, the target third party is determined to be a third party approved by the first channel, or the target third party includes both a third party approved by the first channel and a third party approved by the second channel, based on the query results. If the query fails, it is determined that the target third party is a third party approved by the default channel.

6. The method according to claim 5, characterized in that, The method further includes: Obtain identification information from multiple business parties and multiple violation detection scenarios; The review strategy table is configured based on the identification information of each business party and the violation detection scenarios. The review strategy table constructs the mapping relationship between the identification information of each business party, each violation detection scenario and the third party of the channel review.

7. The method according to claim 1, characterized in that, The review results from the third-party feedback of the first channel include review suggestions and scenario information for each violation detection scenario in multiple violation detection scenarios. The review suggestions include any one of the following: review passed, review failed, or manual review. The review results from the third-party feedback received through the first channel include information on whether the review was unsuccessful, along with the scenario details, or information on whether the review was successful. or, The review results from the third-party feedback in the second channel include review suggestions and scenario information for each violation detection scenario in multiple violation detection scenarios. The review suggestions include any one of the following: review passed, review failed, or manual review. The review results from the third-party feedback received through the first channel include information on whether the review was unsuccessful and the relevant scenario, or information on whether the review was successful.

8. A multi-channel image content review device, characterized in that, The device includes: The receiving module is used to receive images to be reviewed uploaded by any business party, as well as the unique identifier of the business party. The identification module is used to identify the target third party for image review based on the unique identifier of the business party; The first review module is used to send the image to be reviewed to the first channel review third party if the target third party is a third party reviewed by the first channel, and determine the content review result of the image to be reviewed based on the review result fed back by the first channel review third party; The second review module is used to send the image to be reviewed to the first channel reviewer and the second channel reviewer respectively if the target third party includes the first channel reviewer and the second channel reviewer, and to determine the content review result of the image to be reviewed based on the review results fed back by the first channel reviewer and the second channel reviewer.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

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

Images