Task processing method and device, program product and electronic equipment

Abstract

The invention provides a task processing method and device, a program product and electronic equipment, and relates to the technical field of computers.The method comprises the steps that at least one to-be-submitted object is received; determining whether each to-be-submitted object meets a preset screening condition or not; wherein the preset screening condition comprises at least one of a first filtering sub-condition, a submission truncation sub-condition and a material screening sub-condition; according to the to-be-submitted objects meeting the preset screening condition, constructing a screened object set; and sending the screened object set to an auditing center to obtain an auditing result. According to the method and the device, the received to-be-submitted objects are screened through the preset screening condition, the conditions of repeated submission and invalid submission are avoided, and the submission quantity is reduced, so that the auditing efficiency of an auditing center is improved, and the resource consumption of submitted object conveying is reduced.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and more specifically, to a task processing method, a task processing device, a computer program product, and an electronic device. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the disclosure that are recited in the claims. No description herein is admitted to be prior art by inclusion in this section.

[0003] With the rapid development of Internet technology, the advertising industry has also ushered in new opportunities and challenges. Advertisers can place advertisements through various channels to attract potential customers. However, the legality, authenticity and accuracy of advertising content are crucial. Therefore, advertising review has become an important part of the advertising process. The purpose of the review is to ensure that the content of the advertisement complies with regulations, does not damage the brand image and does not violate laws and regulations. The review process requires a detailed review of the text, pictures, videos and other elements in the advertisement, which requires not only professional reviewers, but also advanced technical tools to assist in the review, and also faces potential legal risks. If the review is not strict, it may lead to illegal and illegal content in the advertisement, which will bring legal disputes and economic losses to advertisers and advertising platforms. Summary of the invention

[0004] However, in the related art, there may be cases of repeated submission for review and invalid submission for review, resulting in low efficiency in reviewing advertisements.

[0005] In view of this, the present disclosure provides a task processing method, a task processing device, a computer program product, and an electronic device to improve the efficiency of advertisement review to a certain extent.

[0006] According to a first aspect of the present disclosure, a task processing method is provided, the method comprising:

[0007] Receive at least one object to be reviewed;

[0008] Determine whether each of the objects to be submitted for review meets a preset screening condition; wherein the preset screening condition includes at least one of a first filtering sub-condition, a submission for review cut-off sub-condition, and a material screening sub-condition;

[0009] Constructing a screened object set based on the objects to be submitted for review that meet the preset screening conditions;

[0010] The screened object set is sent to the review center to obtain the review result.

[0011] In a possible implementation, if the preset screening condition is a first filtering sub-condition, a screened object set is constructed based on the objects to be submitted for review that meet the preset screening condition, including:

[0012] Determine the number of times each object to be submitted for review has been requested;

[0013] When it is determined that the number of times the first object to be submitted for review has been requested is not less than a preset threshold, it is determined that the first filtering sub-condition is satisfied, and the first object to be submitted for review is used as an object in the filtered object set.

[0014] In a possible implementation, if the preset screening condition is a submission for review cutoff sub-condition, a screened object set is constructed based on the objects to be submitted for review that meet the preset screening condition, including:

[0015] Determine push information for each object to be submitted for review; wherein the push information is used to indicate the possibility of the object to be submitted for review being pushed for display;

[0016] When it is determined that the push information of the second review object is within the preset range and the review cutoff sub-condition is met, the second review object is used as an object in the filtered object set.

[0017] In a possible implementation, determining the push information of each object to be submitted for review includes:

[0018] Determine the exposure and click rate of each object to be reviewed;

[0019] According to the exposure rate, click rate and respective weights of each object to be submitted for review, push information for each object to be submitted for review is determined.

[0020] In a possible implementation, if the preset screening condition is a material screening sub-condition, a screened object set is constructed based on the objects to be submitted for review that meet the preset screening condition, including:

[0021] For each object to be submitted for review, perform the following operations:

[0022] Perform a segmentation operation on the object to be submitted for review to obtain a subunit corresponding to the object to be submitted for review, wherein the subunit includes at least one of text, picture, and video;

[0023] According to the sub-unit corresponding to the object to be submitted for review and the material screening sub-condition, obtaining the screening sub-unit corresponding to the object to be submitted for review;

[0024] The screening subunit is used as an object in the screened objects.

[0025] In a possible implementation, if the subunit is text, obtaining the screening subunit corresponding to the object to be submitted for review according to the subunit corresponding to the object to be submitted for review and the material screening subcondition includes:

[0026] Regularizing the text corresponding to the object to be submitted for examination to obtain a first text, and performing hash processing on the first text to obtain a first hash value;

[0027] When it is determined that the first Hash value is inconsistent with the Hash value of the text content retrieved in the audit result library, the first text is used as a screening subunit corresponding to the object to be submitted for review.

[0028] In a possible implementation, if the subunit is a picture, obtaining the screening subunit corresponding to the object to be submitted for review according to the subunit corresponding to the object to be submitted for review and the material screening subcondition includes:

[0029] Performing hash processing on the uniform resource locator of the image corresponding to the object to be submitted for review to obtain a second hash value;

[0030] When it is determined that the second Hash value is inconsistent with the Hash value of the uniform resource locator of the picture in the material library, the uniform resource locator of the picture is used as the screening sub-unit corresponding to the object to be submitted for review.

[0031] In a possible implementation, if the subunit is a picture, obtaining the screening subunit corresponding to the object to be submitted for review according to the subunit corresponding to the object to be submitted for review and the material screening subcondition includes:

[0032] Performing hash processing on the content of the image corresponding to the object to be submitted for review to obtain a third hash value;

[0033] When it is determined that the third hash value is inconsistent with the hash value of the content of the picture in the material library, the content of the picture is used as the screening sub-unit corresponding to the object to be submitted for review.

[0034] In a possible implementation, if the subunit is a picture, obtaining the screening subunit corresponding to the object to be submitted for review according to the subunit corresponding to the object to be submitted for review and the material screening subcondition includes:

[0035] Performing key recognition and extraction processing on the image corresponding to the object to be submitted for review, and determining the key words corresponding to the image corresponding to the object to be submitted for review;

[0036] The key words are used as screening sub-units corresponding to the object to be submitted for review.

[0037] In a possible implementation, if the subunit is a picture, obtaining the screening subunit corresponding to the object to be submitted for review according to the subunit corresponding to the object to be submitted for review and the material screening subcondition includes:

[0038] Performing grayscale processing on the image corresponding to the object to be submitted for review to obtain a grayscale image corresponding to the object to be submitted for review;

[0039] Filter the pure color background of the grayscale image to obtain a processed image corresponding to the object to be submitted for review;

[0040] The processed images are aggregated to obtain an aggregated image, and the aggregated image is used as a screening sub-unit corresponding to the object to be submitted for review.

[0041] In a possible implementation manner, if the subunit is a video, obtaining the screening subunit corresponding to the object to be submitted for review according to the subunit corresponding to the object to be submitted for review and the material screening subcondition includes:

[0042] Determine similar frames in the video corresponding to the object to be submitted for review;

[0043] According to the frame cut-off interval and the similar frames, a frame to be submitted for review in the video corresponding to the object to be submitted for review is determined, and the frame to be submitted for review is used as a screening sub-unit corresponding to the object to be submitted for review.

[0044] According to a second aspect of the present disclosure, there is provided a task processing device, the device comprising:

[0045] A receiving unit, configured to receive at least one object to be submitted for review;

[0046] A screening unit, used to determine whether each of the objects to be submitted for review meets a preset screening condition; wherein the preset screening condition includes at least one of a first filtering sub-condition, a submission cut-off sub-condition, and a material screening sub-condition; and, based on the objects to be submitted for review that meet the preset screening condition, construct a screened object set;

[0047] The review unit is used to send the screened object set to the review center to obtain the review result.

[0048] In a possible implementation manner, if the preset screening condition is a first filtering sub-condition, the screening unit is used to:

[0049] Determine the number of times each object to be submitted for review has been requested;

[0050] When it is determined that the number of times the first object to be submitted for review has been requested is not less than a preset threshold, it is determined that the first filtering sub-condition is satisfied, and the first object to be submitted for review is used as an object in the filtered object set.

[0051] In a possible implementation manner, if the preset screening condition is a submission for review cutoff sub-condition, the screening unit is used to:

[0052] Determine push information for each object to be submitted for review; wherein the push information is used to indicate the possibility of the object to be submitted for review being pushed for display;

[0053] When it is determined that the push information of the second review object is within the preset range and the review cutoff sub-condition is met, the second review object is used as an object in the filtered object set.

[0054] In a possible implementation manner, if the preset screening condition is a submission for review cutoff sub-condition, the screening unit is used to:

[0055] Determine the exposure and click rate of each object to be reviewed;

[0056] According to the exposure rate, click rate and respective weights of each object to be submitted for review, push information for each object to be submitted for review is determined.

[0057] In a possible implementation manner, if the preset screening condition is a material screening sub-condition, the screening unit is used to:

[0058] For each object to be submitted for review, perform the following operations:

[0059] Perform a segmentation operation on the object to be submitted for review to obtain a subunit corresponding to the object to be submitted for review, wherein the subunit includes at least one of text, picture, and video;

[0060] According to the sub-unit corresponding to the object to be submitted for review and the material screening sub-condition, obtaining the screening sub-unit corresponding to the object to be submitted for review;

[0061] The screening subunit is used as an object in the screened objects.

[0062] In a possible implementation manner, if the preset screening condition is a material screening sub-condition, the screening unit is used to:

[0063] If the subunit is a text, regularizing the text corresponding to the object to be submitted for review to obtain a first text, and performing hash processing on the first text to obtain a first hash value;

[0064] When it is determined that the first Hash value is inconsistent with the Hash value of the text content retrieved in the audit result library, the first text is used as a screening subunit corresponding to the object to be submitted for review.

[0065] In a possible implementation manner, if the preset screening condition is a material screening sub-condition, the screening unit is used to:

[0066] If the subunit is a picture, performing hash processing on the uniform resource locator of the picture corresponding to the object to be submitted for review to obtain a second hash value;

[0067] When it is determined that the second Hash value is inconsistent with the Hash value of the uniform resource locator of the picture in the material library, the uniform resource locator of the picture is used as the screening sub-unit corresponding to the object to be submitted for review.

[0068] In a possible implementation manner, if the preset screening condition is a material screening sub-condition, the screening unit is used to:

[0069] If the subunit is a picture, performing hash processing on the content of the picture corresponding to the object to be submitted for review to obtain a third hash value;

[0070] When it is determined that the third hash value is inconsistent with the hash value of the content of the picture in the material library, the content of the picture is used as the screening sub-unit corresponding to the object to be submitted for review.

[0071] In a possible implementation manner, if the preset screening condition is a material screening sub-condition, the screening unit is used to:

[0072] If the subunit is a picture, performing key recognition and extraction processing on the picture corresponding to the object to be submitted for review, and determining the key words corresponding to the picture corresponding to the object to be submitted for review;

[0073] The key words are used as screening sub-units corresponding to the object to be submitted for review.

[0074] In a possible implementation manner, if the preset screening condition is a material screening sub-condition, the screening unit is used to:

[0075] If the subunit is a picture, grayscale processing is performed on the picture corresponding to the object to be submitted for review to obtain a grayscale picture corresponding to the object to be submitted for review;

[0076] Filter the pure color background of the grayscale image to obtain a processed image corresponding to the object to be submitted for review;

[0077] The processed images are aggregated to obtain an aggregated image, and the aggregated image is used as a screening sub-unit corresponding to the object to be submitted for review.

[0078] In a possible implementation manner, if the preset screening condition is a material screening sub-condition, the screening unit is used to:

[0079] If the subunit is a video, determining similar frames in the video corresponding to the object to be submitted for review;

[0080] According to the frame cut-off interval and the similar frames, a frame to be submitted for review in the video corresponding to the object to be submitted for review is determined, and the frame to be submitted for review is used as a screening sub-unit corresponding to the object to be submitted for review.

[0081] According to a third aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the method of the first aspect and possible implementations thereof are implemented.

[0082] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the method of the above-mentioned first aspect and its possible implementation methods by executing the executable instructions.

[0083] The technical solution disclosed in this disclosure has the following beneficial effects:

[0084] In the disclosed embodiment, at least one object to be submitted for review can be received, and then a judgment is performed on each object to be submitted for review, that is, whether each object to be submitted for review meets the preset screening conditions; wherein the preset screening conditions include at least one of the first filtering sub-condition, the submission for review truncation sub-condition, and the material screening sub-condition; that is, in the disclosed embodiment, the objects to be submitted for review can be screened from multiple aspects, such as whether it is the first triggered object to be submitted for review, whether the sub-content of the object to be submitted for review itself has been submitted for review, etc., so as to fully review and screen the objects to be submitted for review, and avoid the situation where the objects to be submitted for review are submitted for review repeatedly. Further, a screened object set can be constructed according to the objects to be submitted for review that meet the screening conditions, and then the screened object set can be sent to the review center to obtain the submission result. In this way, not only can the processing volume of the review center be reduced, the processing efficiency of the review center be improved, and the submission result can be quickly obtained, but also the review pass rate of the object set can be improved, and the occurrence of invalid submissions of the objects to be reviewed can be reduced.

[0085] Other features and advantages of the present disclosure will be described in the following description, and partly become apparent from the description, or be understood by practicing the present disclosure. The purpose and other advantages of the present disclosure can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments of the present disclosure will be briefly introduced below. Obviously, the drawings introduced below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0087] Figure 1 A schematic diagram of an application scenario in this exemplary embodiment is shown;

[0088] Figure 2 A flowchart showing a task processing method in this exemplary embodiment;

[0089] Figure 3 A schematic diagram showing the structure of a task processing device in this exemplary embodiment is shown;

[0090] Figure 4 A schematic structural diagram of an electronic device in this exemplary embodiment is shown. DETAILED DESCRIPTION

[0091] In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure. In the absence of conflict, the embodiments in the present disclosure and the features in the embodiments can be arbitrarily combined with each other. In addition, although the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in an order different from that here.

[0092] The term "comprising" and any variations thereof in the specification and claims of the present disclosure are intended to cover non-exclusive protection. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0093] In the embodiments of the present disclosure, one or more, "many" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or plural.

[0094] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order, sequence, size, and priority. For example, the first object to be submitted for review and the second object to be submitted for review in the embodiment of the present disclosure are only used to distinguish different objects to be submitted for review. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0095] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, which are schematic diagrams of the present disclosure and are not necessarily drawn to scale. Some of the block diagrams shown in the accompanying drawings may be functional entities, which do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in hardware modules or integrated circuits, or in networks, processors or microcontrollers. The implementation method can be implemented in a variety of forms and should not be understood as being limited to the examples set forth herein. The features, structures or characteristics described in the present disclosure may be combined in one or more implementations in any suitable manner. In the following description, many specific details are provided to provide a full description of the implementation methods of the present disclosure. However, those skilled in the art should be aware that one or more specific details may be omitted when implementing the technical solution of the present disclosure, or one or more specific details may be replaced by other methods, components, devices, steps, etc. It should be noted that in the embodiments of the present disclosure, the dissemination and use of data, etc., are in compliance with relevant national laws and regulations. SUMMARY OF THE INVENTION

[0097] At present, when the advertising exchange market (Ad-Exchange, ADX) processes advertisements, it does not process the same advertisements submitted for review on different demand-side platforms (Demand-Side Platform, DSP), or the same units (such as the same paragraph of copy) in different advertisements, which may result in the same advertising unit being submitted for review multiple times at different time nodes. In addition, there are a large number of advertisements that have been submitted for review, but ultimately not exposed, that is, they are not displayed on the user side, resulting in invalid submissions. In addition, since the review of each advertising unit requires a lot of manpower and time resources, repeated submissions and invalid submissions may lead to inefficient review processes, and cause delays in the review process and increased costs. Furthermore, independent review of each advertisement sent by DSP will lead to a rapid increase in review fees, thereby increasing the cost of advertising delivery, especially when advertisers need to deliver advertisements on a large scale, resulting in a significant increase in review fees and a reduced delivery experience.

[0098] In view of this, the embodiment of the present disclosure provides a task processing method, through which at least one object to be submitted for review can be received, and then a judgment is performed on each object to be submitted for review, that is, whether each object to be submitted for review meets the preset screening conditions; wherein the preset screening conditions include at least one of the first filtering sub-condition, the submission for review truncation sub-condition and the material screening sub-condition; that is, in the embodiment of the present disclosure, the objects to be submitted for review can be screened from multiple aspects, such as whether it is the first triggered object to be submitted for review, whether the sub-content of the object to be submitted for review itself has been submitted for review, etc., so as to fully review and screen the objects to be submitted for review, and avoid the situation where the objects to be submitted for review are submitted for review repeatedly. Further, according to the objects to be submitted for review that meet the screening conditions, a screened object set can be constructed, and then the screened object set can be sent to the review center to obtain the submission result. In this way, not only can the processing volume of the review center be reduced, the processing efficiency of the review center be improved, and the submission result can be quickly obtained, but also the review pass rate of the object set can be improved, the appearance of invalid submission objects to be reviewed can be reduced, the review cost can be reduced, and the delivery experience can be improved.

[0099] After introducing the basic principles of the present disclosure, various non-limiting embodiments of the present disclosure are described in detail below.

[0100] Application Scenario Overview

[0101] In order to better understand the technical solutions provided by the embodiments of the present disclosure, the following briefly introduces the application scenarios to which the technical solutions provided by the embodiments of the present disclosure are applicable. It should be noted that the application scenarios introduced below are only used to illustrate the embodiments of the present disclosure and are not intended to limit the present disclosure. In specific implementation, the technical solutions provided by the embodiments of the present disclosure can be flexibly applied according to actual needs.

[0102] In order to more clearly introduce the contents of the embodiments of the present disclosure, some key terms are introduced below:

[0103] Demand-Side Platform (DSP): is a system and an online advertising platform. The platform serves advertisers or agencies and helps them place advertisements on the Internet or mobile Internet. In other words, the platform can provide real-time bidding for advertisers or agencies.

[0104] Sell-Side Platform (SSP): A platform where media provide traffic. In other words, media can manage their own advertising space on SSP and control the display of advertisements.

[0105] Ad-Exchange (ADX): It matches DSP and SSP to conduct transactions, that is, it serves DSP and SSP. After receiving the request from SSP, it passes the advertising traffic information to DSP and asks them for their bids. After the DSP responds, it returns the corresponding advertising creative and bid. Specifically, ADX is based on real-time bidding (RTB). The media's ads are placed on it, and the highest bidder wins, which is more fair and just. For example, Google's DoubleClick, Microsoft's AdECN, Alibaba's Tanx, etc.

[0106] Real-time bidding (RTB) is a bidding technology that evaluates and bids for tens of thousands of ads for an ad request in real time.

[0107] Message-Digest Algorithm 5 (MD5): is a widely used hash function used to convert messages of any length into a fixed-length hash value. The hash value generated by the MD5 hash algorithm is usually a 128-bit (16-byte) hexadecimal number, usually represented by a 32-character hexadecimal number.

[0108] In the embodiments of the present disclosure, the task processing technology can be applied to various business scenarios corresponding to ADX. For example, the supply-side platform is a music platform, and the business scenario corresponding to ADX is to process whether the advertisements triggered by other demand-side platforms are delivered to the music platform. This is not limited in the embodiments of the present disclosure.

[0109] See also Figure 1 As shown, Figure 1This is an application scenario to which the technical solution of the embodiment of the present disclosure can be applied. In the scenario diagram, there are devices 101 deployed with SSP, devices 102 deployed with ADX, and devices 103 deployed with DSP. The device 103 deployed with DSP can be connected to multiple other devices 104, which are devices corresponding to various advertisers or agents. Figure 1 Only one is shown.

[0110] Among them, the device 101 deployed with SSP, the device 102 deployed with ADX, the device 103 deployed with DSP and other devices 104, as well as each device 104 can be directly or indirectly connected to each other through one or more networks.

[0111] In the embodiment of the present disclosure, when the device 101 deployed with SSP triggers a request for delivery to the device 102 deployed with ADX, the device 102 deployed with ADX can trigger a prompt request to the device 103 deployed with DSP, so that the device 103 deployed with DSP triggers corresponding requests to multiple devices 104 connected thereto, for example, triggering corresponding requests to the device 104-1 corresponding to advertiser 1, to the device 104-2 corresponding to advertiser 2, and to the device 104-3 corresponding to advertiser 3, so that each advertiser determines whether to feedback the advertising creativity and bid based on its corresponding device 104 to the device 103 deployed with DSP based on the actual situation.

[0112] In the disclosed embodiment, the device 102 with ADX can receive the advertising ideas and bids corresponding to multiple advertisers fed back by the device 103 with DSP, that is, receive at least one object to be submitted for review, and then the device 102 with ADX can determine whether each object to be submitted for review meets the preset screening conditions; wherein the preset screening conditions include at least one of the first filtering sub-condition, the submission truncation sub-condition, and the material screening sub-condition. Then, based on the objects to be submitted for review that meet the preset screening conditions, a filtered object set can be constructed, and then the filtered object set can be sent to the review center to obtain the submission result.

[0113] in, Figure 1The device 101 with SSP deployed, the device 102 with ADX deployed, the device 103 with DSP deployed, and other devices 104 may be mobile phones, tablet computers (PADs), personal computers (PCs), smart TVs, smart watches, smart speakers, smart car devices, wearable devices, etc., but are not limited to them. It can also be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server or cloud server cluster that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms, but is not limited to them.

[0114] Of course, the method provided in the embodiment of the present disclosure is not limited to Figure 1 The application scenarios shown may also be used in other possible application scenarios, and the embodiments of the present disclosure are not limited thereto.

[0115] Exemplary Methods

[0116] To further illustrate the technical solution provided by the embodiments of the present disclosure, this is described in detail below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiments of the present disclosure provide method operation steps as shown in the following embodiments or drawings, more or fewer operation steps may be included in the method based on routine or no creative labor. In the steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided by the embodiments of the present disclosure. The method may be executed in the order of the method shown in the embodiments or drawings or in parallel during the actual processing process or when the device is executed.

[0117] See also Figure 2 , Figure 2 FIG. 1 is a flowchart of a task processing method in an embodiment of the present disclosure. The method process may be performed by an electronic device, such as Figure 1 The device 102 with ADX deployed therein is executed, and the specific implementation process of the method is as follows:

[0118] Step 201: Receive at least one object to be submitted for review.

[0119] In the embodiment of the present disclosure, the electronic device may receive at least one object to be submitted for review fed back by a device equipped with a DSP, wherein the object to be submitted for review may be understood as an advertisement creative to be delivered by an advertiser or an agent.

[0120] In the disclosed embodiment, an advertising creative may include at least one of text, picture, and video. That is, the advertising creative may include at least one of the three elements of text, picture, and video, and these three elements may be used alone or in combination to create more vivid and attractive advertising content. In digital advertising, these elements may also be innovatively used in the form of interactive advertising, animation effects, etc. to enhance user engagement and brand communication effects.

[0121] In the disclosed embodiments, the text element is the core of the information conveyed by the advertisement. It can be a title, description, slogan or slogan, etc., which is used to attract the attention of the target audience, convey the key selling points of the product or service, and call for action. For example, the text of a product advertisement may be: "Quality assurance, bringing warmth and comfort to your home". Optionally, the text may also contain information such as a landing page or a jump link, where the link can be a Hypertext Transfer Protocol (HTTP) link or a mobile deep link (deeplinking, mobile linking) link.

[0122] In the disclosed embodiments, the image element plays a role in visual attraction and information transmission in the advertisement. Carefully selected images can make the advertisement more attractive and help the audience understand the content of the advertisement more quickly. For example, a restaurant advertisement may include delicious food pictures to attract the attention of potential customers.

[0123] In the disclosed embodiments, the video element is a powerful tool to convey information and emotions through dynamic images and sounds. Videos can show product usage scenarios, brand stories, customer testimonials, etc. to attract viewers more vividly. For example, a car advertisement can show a car driving on a mountain road to demonstrate the car's driving performance and ride comfort.

[0124] Step 202: Determine whether each object to be submitted for review meets the preset screening condition; wherein the preset screening condition includes at least one of the first filtering sub-condition, the submission for review cut-off sub-condition, and the material screening sub-condition.

[0125] Step 203: construct a screened object set based on the objects to be submitted for review that meet the preset screening conditions.

[0126] In the embodiment of the present disclosure, after the electronic device receives at least one object to be reviewed, it can determine whether each object to be reviewed meets the preset screening conditions. That is to say, in the embodiment of the present disclosure, after receiving the object to be reviewed, the object to be reviewed is not directly sent to the review center, but the object to be reviewed is first screened.

[0127] In the disclosed embodiment, the electronic device can determine whether the object to be submitted for review meets the preset screening condition according to whether the object to be submitted for review meets at least one of the first filtering sub-condition, the submission and review truncation sub-condition, and the material screening sub-condition. That is, if the object to be submitted for review meets any one of the first filtering sub-condition, the submission and review truncation sub-condition, and the material screening sub-condition, the object to be submitted for review can be used as an object in the object set after screening; if the object to be submitted for review meets any two of the first filtering sub-condition, the submission and review truncation sub-condition, and the material screening sub-condition, the object to be submitted for review can be used as an object in the object set after screening; and if the object to be submitted for review meets all of the sub-conditions in the first filtering sub-condition, the submission and review truncation sub-condition, and the material screening sub-condition, the object to be submitted for review can be used as an object in the object set after screening.

[0128] The following first introduces a solution in which if the object to be submitted for review satisfies any one of the first filtering sub-condition, the submission truncation sub-condition, and the material screening sub-condition, the object to be submitted for review can be used as an object in the filtered object set.

[0129] In a possible implementation, if the object to be submitted for review satisfies the first filtering sub-condition, it is determined that the object to be submitted for review meets the preset screening condition, and the object to be submitted for review is used as an object in the screened object set.

[0130] In this exemplary embodiment, the electronic device can determine the number of times each object to be submitted for review has been requested; when it is determined that the number of times the first object to be submitted for review has been requested is not less than a preset threshold, it is determined that the first filtering sub-condition is met, and the first object to be submitted for review is used as an object in the filtered object set. The number of times requested can be understood as the number of times the device with a DSP deployed feedbacks the object to be reviewed. For example, if the device with a DSP deployed feedbacks the number of times the advertising creative A corresponding to advertiser 1 is fed back 2 times, then the number of times the advertising creative A is requested can be determined to be 2 times.

[0131] In this exemplary embodiment, since ADX handles the advertisements returned by DSP, i.e., the objects to be submitted for review, as follows: if the advertisements returned for the first time are in the state of pending review, they will be submitted for review, but the first advertisement returned will be filtered by the "pending review" state, and this part of the material accounts for a large proportion. If DSP does not return it for the second time, there will be no second exposure opportunity. This part of the submission for review does not generate any revenue. Therefore, in order to filter out advertisements that do not generate revenue, i.e., those that do not need to be delivered in the future, ADX will mark the status of these advertisements, i.e., determine the number of times each advertisement has been requested. When it is determined that the number of times an advertisement has been requested is greater than a preset threshold, it can be understood that the advertiser is more determined to deliver the advertisement, and the advertisement can be used as an advertisement in the filtered object set. The object set determined in this way greatly reduces the number of invalidly delivered advertisements, thereby reducing the amount of review for ADX's subsequent price comparison and other processing, and improving the processing efficiency of ADX.

[0132] In a possible implementation, if the object to be submitted for review satisfies the submission for review cutoff sub-condition, it is determined that the object to be submitted for review meets the preset screening condition, and the object to be submitted for review is used as an object in the screened object set.

[0133] In this exemplary embodiment, considering that for ADX, generally only one advertisement wins for a request triggered by SSP, while there are hundreds of advertisements recalled from DSP, if the unsuccessful advertisements do not win in other subsequent advertisement requests, then these advertisements will not generate actual revenue if submitted for review. In view of this, it is necessary to adjust the advertisement filtering order and truncate the submitted advertisements, so that only the advertisements that will have a chance of winning in the future are submitted for review. Among them, ADX can perform the following advertisement filtering order for the advertisements recalled by DSP: compare the prices of the advertisements, and when it is determined that the comparison passes, send the advertisements to the review center. Compared with the advertisement filtering order of sending to the review center first and then comparing in the related art, this method can give priority to submitting for review those advertisements that are more likely to win, thereby reducing the number of invalid advertisements submitted for review. When ADX determines that an advertisement has no possibility of winning in other subsequent advertisement requests, the system will truncate it from the submission queue and no longer submit it for review.

[0134] In this exemplary embodiment, the electronic device can determine the push information of each object to be submitted for review; wherein the push information is used to characterize the possibility of the object to be submitted for review being pushed for display; the push information can be understood as the aforementioned possibility of winning. And, when it is determined that the push information of the second object to be submitted for review is within the preset range and it is determined that the submission for review cutoff sub-condition is met, the second object to be submitted for review is used as an object in the filtered object set.

[0135] Optionally, the electronic device may determine the exposure rate and click rate of each object to be submitted for review; and determine the push information of each object to be submitted for review according to the exposure rate, click rate and respective weights of each object to be submitted for review.

[0136] For example, the historical performance is determined based on the exposure rate of the advertisement in the previous period, and the relevance is reflected through the click-through rate (CTR). The above two are combined with the bidding information to obtain the final ranking score, and the push information of the advertisement is determined based on the ranking score.

[0137] Assume that the comprehensive ranking score of the advertisement is represented by Shistorty, the exposure rate is represented by e, the click rate is represented by c, and the bid is represented by p. In order to balance the importance of exposure rate, click rate and bid, a weight we is assigned to the exposure rate and a weight wc is assigned to the click rate, wherein we+wc=1, and 0.15 is the assumed highest click rate. The final ranking score is calculated by the following formula 1.

[0138] Shistorty=p*(e*we+Max(wc,c / 0.15*wc))Formula 1.

[0139] For example, if the exposure rate of an ad in the past hour is 90%, the click rate is 5%, the exposure rate weight we = 0.8, the click rate weight wc = 0.2, and the bid for this ad is 200 points / thousand impressions, then its historical performance comprehensive score is:

[0140] Shistorty=200*(0.9*0.8+Max(0.2,0.05 / 0.15*0.2))=157.

[0141] In a possible implementation, if the object to be submitted for review satisfies the material screening sub-condition, it is determined that the object to be submitted for review meets the preset screening condition, and the object to be submitted for review is used as an object in the screened object set.

[0142] In this exemplary embodiment, the electronic device can perform a segmentation operation on the object to be submitted for review, obtain a subunit corresponding to the object to be submitted for review, and the subunit includes at least one of text, picture, and video; obtain a screening subunit corresponding to the object to be submitted for review according to the subunit corresponding to the object to be submitted for review and the material screening subcondition; and use the screening subunit as an object in the screened object. In other words, if the object to be submitted for review only segments any one of text, picture, and video, then only the item is screened; if the object to be submitted for review segments multiple items of text, picture, and video, then multiple comprehensive screenings can be performed.

[0143] The following only introduces the scheme for screening only one of the text, pictures and videos that are segmented from the object to be reviewed. The separate execution of the scheme for performing multiple comprehensive screenings can refer to the corresponding sub-units, which will not be repeated here.

[0144] Optionally, if the sub-unit is text, the text corresponding to the object to be reviewed is regularized to obtain a first text, and the first text is hashed to obtain a first hash value; when it is determined that the first hash value is inconsistent with the hash value of the text content retrieved in the review result library, the first text is used as the screening sub-unit corresponding to the object to be reviewed.

[0145] Specifically, the content of the segmented text sub-unit is regularized, for example, invisible content such as leading and trailing whitespace characters are removed, and then the content of the processed text sub-unit can be hashed using MD5 to obtain the hash value of the content of the text sub-unit. Furthermore, the hash value of the text content can be retrieved in the audit result library. If the content identical to the hash value is found and the audit is passed, there is no need to submit the text sub-unit for review again. If the content identical to the hash value is found and the audit is not passed, the text sub-unit is filtered out. If the content identical to the hash value is not found, the text sub-unit is used as a screening sub-unit. It should be noted that the content of the text sub-unit also includes key information such as the landing page, which needs to be considered and processed during the processing.

[0146] Optionally, if the subunit is a picture, considering that the picture contains multiple contents, at least one of the following processes may be performed:

[0147] Processing one: Hash processing is performed on the Uniform Resource Locator (URL) of the image corresponding to the object to be submitted for review to obtain a second hash value; when it is determined that the second hash value is inconsistent with the hash value of the Uniform Resource Locator of the image in the material library, the Uniform Resource Locator of the image is used as the screening sub-unit corresponding to the object to be submitted for review.

[0148] For example, you can select the MD5 hash function to convert the URL of the image into a hash value of fixed length, and filter the URL of the image by determining whether the same material has been reviewed in the material library. This screening process can be implemented using the MD5 hash algorithm library and database query statements.

[0149] Processing 2: Hash processing is performed on the content of the picture corresponding to the object to be submitted for review to obtain a third hash value; when it is determined that the third hash value is inconsistent with the hash value of the content of the picture in the material library, the content of the picture is used as the screening sub-unit corresponding to the object to be submitted for review.

[0150] For example, read the image into memory in binary form, and then generate a unique hash value for the image data through a specific algorithm (such as MD5). This value is like the "fingerprint" of the image. If the image content is modified, even if it is a minor change, its hash value will also change. The hash value is used to search the material library to see if the same material has been reviewed, so as to filter the content of the image.

[0151] Processing three: Perform key recognition and extraction processing on the pictures corresponding to the objects to be submitted for review, and determine the key words corresponding to the pictures corresponding to the objects to be submitted for review; use the key words as the screening sub-units corresponding to the objects to be submitted for review.

[0152] For example, images are divided into DSP's DPA (Dynamic Product Ads) material recognition. For image materials generated by URL splicing text, they need to be operated according to DSP's recognition rules. The focus can be on analyzing and processing the URL, extracting key information from it, and then converting the image into text for review.

[0153] Processing 4: Replace the specific logo in the image of the object to be reviewed. If the replacement content corresponding to the specific logo does not exist in the replacement library, the specific logo is used as the screening sub-unit corresponding to the object to be reviewed. The replacement library includes general specific logos that have been reviewed and meet relevant regulations.

[0154] For example, for the specific logo of an e-commerce application (Application, APP) or brand corresponding to the same advertiser, you can search in the replacement library to see whether there is replacement content (such as a LOGO) corresponding to the specific logo, that is, replace the specific logo with a universal specific logo that has been reviewed and complies with relevant regulations. There is no need to repeatedly send the specific logo for review every time, thereby reducing the amount of review sent.

[0155] Processing five: grayscale processing is performed on the image corresponding to the object to be submitted for review to obtain a grayscale image corresponding to the object to be submitted for review; the pure color background of the grayscale image is filtered to obtain a processed image corresponding to the object to be submitted for review; the processed image is aggregated to obtain an aggregated image, and the aggregated image is used as a screening sub-unit corresponding to the object to be submitted for review.

[0156] For example, through a specific formula such as Gray = 0.299*R+0.587*G+0.114*B, a color image is converted into a grayscale image with only one channel, and the pixel value is between 0 and 255. Since advertising images usually have a standard size such as 1280*720, they can be divided into 12 standard blocks of images, each of which is 320*240, so as to obtain a grayscale image. If the color recognition algorithm is used to determine that the grayscale image is a solid color background, 2 blocks of solid color background can be filtered out of the 12 blocks of elements. That is, the solid color is removed. Furthermore, the same units of the 10 blocks of images can be identified, for example, the contents of the 10 filtered blocks of images are hashed respectively, and the corresponding review status is searched in the material library. If an audit result is found, it is quickly reviewed and passed or not. In addition, the vector verification technology is used to judge the similarity of the filtered images to avoid repeated submission for review. For example, an image feature extraction algorithm can be used to convert the image into a vector form, and then the similarity between the vectors is calculated. If the similarity is high, it can be determined as the same or similar picture and filtered out to avoid repeated submission for review. In addition, the sliding window technology can be used to aggregate the pictures. For example, within 5 seconds, if there are 3 pictures of the remaining 4 / 12, the 3 pictures are spliced ​​into one picture and the picture is used as the screening sub-unit.

[0157] In this exemplary embodiment, the above processing can realize non-submission or partial submission of pictures for review, thereby saving resources.

[0158] Optionally, if the sub-unit is a video, similar frames in the video corresponding to the object to be submitted for review are determined; based on the frame cut interval and similar frames, the submission frames in the video corresponding to the object to be submitted for review are determined, and the submission frames are used as the screening sub-unit corresponding to the object to be submitted for review.

[0159] In the process of video review, it is a common method to cut frames at fixed time. For example, cut frames every 2 seconds. Figure 1 The frequency of frames is determined by capturing a series of images from the video to determine whether the entire video can pass the review. This method helps to efficiently and comprehensively control the video quality. This exemplary embodiment provides a solution for skipping frames to reduce the number of frame captures of the entire video and reduce the cost of the overall review.

[0160] The skip frame capture scheme provided by this exemplary embodiment can first use image processing and computer vision technology to compare adjacent frames captured from the video and calculate the similarity between them. Optionally, the vector similarity method in the image processing logic can be used to calculate the similarity between adjacent frames. Further, a threshold is set for the calculated similarity to determine which frames can be regarded as similar frames, so that similar frames in the video corresponding to the object to be submitted for review can be determined. For example, when the similarity is higher than a set threshold, these frames can be marked as similar frames.

[0161] Furthermore, after determining similar frames in the video corresponding to the object to be submitted for review, a strategy for skipping frames can be formulated. Optionally, for frames with high similarity, a skipping frame method can be used to reduce the amount of video data and improve processing efficiency. In other words, similar frames can be screened and only the changed frames are retained as the frames to be submitted for review in the video corresponding to the object to be submitted for review, thereby reducing the overall number of frame cuts and further reducing the resource consumption in the final review of the object to be submitted for review.

[0162] In this exemplary embodiment, an appropriate frame-cutting interval can be calculated based on the similarity result and the skip frame-cutting strategy. That is, the frame-cutting interval can be dynamically adjusted according to the change in similarity, thereby ensuring that the changes in important content in the object to be submitted for review can be captured, and insignificant similar frames can be skipped. After determining the frame-cutting interval, the video can be subjected to an actual skip frame-cutting operation according to the frame-cutting interval to determine the submission frame in the video corresponding to the object to be submitted for review. Optionally, the skip frame-cutting operation can be implemented by a video processing library (such as OpenCV), a video editing tool, or a custom video processing program.

[0163] In the disclosed embodiment, if the object to be submitted for review satisfies any two of the first filtering sub-condition, the submission and review truncation sub-condition, and the material screening sub-condition, the object to be submitted for review can be used as an object in the filtered object set. In other words, when a relatively strict pre-review is performed on the object to be reviewed, the object to be submitted for review can be required to meet any two of the first filtering sub-condition, the submission and review truncation sub-condition, and the material screening sub-condition, thereby reducing the number of reviews sent to the review center.

[0164] In the disclosed embodiment, if the object to be submitted for review satisfies the first filtering sub-condition, the submission and review truncation sub-condition, and the material screening sub-condition at the same time, the object to be submitted for review can be used as an object in the filtered object set. In other words, the object to be reviewed is strictly pre-reviewed, and in order to improve the subsequent delivery efficiency of the object to be reviewed, the object to be submitted for review can be required to meet the first filtering sub-condition, the submission and review truncation sub-condition, and the material screening sub-condition.

[0165] In a possible implementation, the ad space can also be screened based on its characteristics. For example, some ad spaces do not have text, and some do not have the advertiser's corresponding LOGO. Based on these characteristics, units that do not need to be submitted for review can be eliminated. For example, for a specific ad space, if its rules clearly state that text content should not be displayed, then the submission of text units can be skipped directly during the submission process, thereby saving review resources. For another example, if a certain ad space does not need to display a LOGO, a logical judgment can be made before submission for review, and the sub-image containing the LOGO of the ad space will not be submitted for review.

[0166] Step 204: Send the screened object set to the review center to obtain the review result.

[0167] In the disclosed embodiment, the ADX may send the screened object set to the review center to obtain the review result, and send the corresponding object to the SSP according to the review result to deliver the advertiser's advertisement.

[0168] Exemplary Devices

[0169] The exemplary embodiment of the present disclosure also provides a task processing device. Figure 3 As shown, the task processing device 300 includes the following program modules:

[0170] A receiving unit 301 is used to receive at least one object to be submitted for review;

[0171] A screening unit 302 is used to determine whether each of the objects to be submitted for review meets a preset screening condition; wherein the preset screening condition includes at least one of a first filtering sub-condition, a submission cut-off sub-condition, and a material screening sub-condition; and, based on the objects to be submitted for review that meet the preset screening condition, a screened object set is constructed;

[0172] The review unit 303 is used to send the screened object set to the review center to obtain the review result.

[0173] In a possible implementation, if the preset screening condition is a first filtering sub-condition, the screening unit 302 is used to:

[0174] Determine the number of times each object to be submitted for review has been requested;

[0175] When it is determined that the number of times the first object to be submitted for review has been requested is not less than a preset threshold, it is determined that the first filtering sub-condition is satisfied, and the first object to be submitted for review is used as an object in the filtered object set.

[0176] In a possible implementation manner, if the preset screening condition is a submission for review cutoff sub-condition, the screening unit 302 is used to:

[0177] Determine push information for each object to be submitted for review; wherein the push information is used to indicate the possibility of the object to be submitted for review being pushed for display;

[0178] When it is determined that the push information of the second review object is within the preset range and the review cutoff sub-condition is met, the second review object is used as an object in the filtered object set.

[0179] In a possible implementation manner, if the preset screening condition is a submission for review cutoff sub-condition, the screening unit 302 is used to:

[0180] Determine the exposure and click rate of each object to be reviewed;

[0181] According to the exposure rate, click rate and respective weights of each object to be submitted for review, push information for each object to be submitted for review is determined.

[0182] In a possible implementation manner, if the preset screening condition is a material screening sub-condition, the screening unit 302 is used to:

[0183] For each object to be submitted for review, perform the following operations:

[0184] Perform a segmentation operation on the object to be submitted for review to obtain a subunit corresponding to the object to be submitted for review, wherein the subunit includes at least one of text, picture, and video;

[0185] According to the sub-unit corresponding to the object to be submitted for review and the material screening sub-condition, obtaining the screening sub-unit corresponding to the object to be submitted for review;

[0186] The screening subunit is used as an object in the screened objects.

[0187] In a possible implementation manner, if the preset screening condition is a material screening sub-condition, the screening unit 302 is used to:

[0188] If the subunit is a text, regularizing the text corresponding to the object to be submitted for review to obtain a first text, and performing hash processing on the first text to obtain a first hash value;

[0189] When it is determined that the first Hash value is inconsistent with the Hash value of the text content retrieved in the audit result library, the first text is used as a screening subunit corresponding to the object to be submitted for review.

[0190] In a possible implementation manner, if the preset screening condition is a material screening sub-condition, the screening unit 302 is used to:

[0191] If the subunit is a picture, performing hash processing on the uniform resource locator of the picture corresponding to the object to be submitted for review to obtain a second hash value;

[0192] When it is determined that the second Hash value is inconsistent with the Hash value of the uniform resource locator of the picture in the material library, the uniform resource locator of the picture is used as the screening sub-unit corresponding to the object to be submitted for review.

[0193] In a possible implementation manner, if the preset screening condition is a material screening sub-condition, the screening unit 302 is used to:

[0194] If the subunit is a picture, performing hash processing on the content of the picture corresponding to the object to be submitted for review to obtain a third hash value;

[0195] When it is determined that the third hash value is inconsistent with the hash value of the content of the picture in the material library, the content of the picture is used as the screening sub-unit corresponding to the object to be submitted for review.

[0196] In a possible implementation manner, if the preset screening condition is a material screening sub-condition, the screening unit 302 is used to:

[0197] If the subunit is a picture, performing key recognition and extraction processing on the picture corresponding to the object to be submitted for review, and determining the key words corresponding to the picture corresponding to the object to be submitted for review;

[0198] The key words are used as screening sub-units corresponding to the object to be submitted for review.

[0199] In a possible implementation manner, if the preset screening condition is a material screening sub-condition, the screening unit 302 is used to:

[0200] If the subunit is a picture, grayscale processing is performed on the picture corresponding to the object to be submitted for review to obtain a grayscale picture corresponding to the object to be submitted for review;

[0201] Filter the pure color background of the grayscale image to obtain a processed image corresponding to the object to be submitted for review;

[0202] The processed images are aggregated to obtain an aggregated image, and the aggregated image is used as a screening sub-unit corresponding to the object to be submitted for review.

[0203] In a possible implementation manner, if the preset screening condition is a material screening sub-condition, the screening unit 302 is used to:

[0204] If the subunit is a video, determining similar frames in the video corresponding to the object to be submitted for review;

[0205] According to the frame cut-off interval and the similar frames, a frame to be submitted for review in the video corresponding to the object to be submitted for review is determined, and the frame to be submitted for review is used as a screening sub-unit corresponding to the object to be submitted for review.

[0206] The specific details of each part of the above-mentioned device have been described in detail in the implementation method of the method part. The undisclosed details can be found in the implementation method of the method part, so they will not be repeated here.

[0207] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the exemplary embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0208] Exemplary Program Products

[0209] The exemplary embodiments of the present disclosure also provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, the task processing method described above is implemented.

[0210] In one embodiment, the computer program product may be a tangible product containing a computer program, such as a computer-readable storage medium storing a computer program. The readable storage medium may be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, or other signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory (Flash), mechanical hard disk (HDD), solid-state drive (SSD), and the like. Exemplarily, the computer program product may be implemented as a non-volatile storage medium storing a computer program, such as a read-only memory, a NAND flash memory, and the like.

[0211] In one embodiment, the computer program product may be an intangible product including a computer program. Exemplarily, the computer program product may be implemented as a virtual digital product, such as a digital file storing an executable file, an installation package, etc. of the computer program.

[0212] The code of the computer program can be written in one or more programming languages. Programming languages ​​such as C language, Java, C++, etc. The program code can be executed entirely on the user computing device, or partially on the user computing device, or as a separate software package, or partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, such as a local area network (LAN), a wide area network (WAN), etc., or can be connected to an external computing device (e.g., an Internet connection provided by an operator).

[0213] Computer programs can be carried or transmitted through electrical, magnetic, optical, electromagnetic, infrared and other signals. Electronic devices can convert signals carrying computer programs into digital signals to run computer programs. When a computer program runs on an electronic device, its code is used to enable the electronic device to execute (more specifically, the processor of the electronic device can execute) the method steps of various exemplary embodiments of the present disclosure, such as the above-mentioned task processing method, which includes the following steps: Step 201: Receive at least one object to be submitted for review; Step 202: Determine whether each object to be submitted for review meets the preset screening conditions; wherein the preset screening conditions include at least one of the first filtering sub-condition, the submission truncation sub-condition and the material screening sub-condition; Step 203: Construct a screened object set based on the objects to be submitted for review that meet the preset screening conditions; Step 204: Send the screened object set to the review center to obtain the submission result.

[0214] By implementing the above method steps through a computer program, at least one object to be submitted for review can be received, and then a judgment is performed on each object to be submitted for review, that is, whether each object to be submitted for review meets the preset screening conditions; wherein the preset screening conditions include at least one of the first filtering sub-condition, the submission for review truncation sub-condition, and the material screening sub-condition; that is, in the embodiment of the present disclosure, the objects to be submitted for review can be screened from multiple aspects, such as whether it is the first triggered object to be submitted for review, whether the sub-content of the object to be submitted for review itself has been submitted for review, etc., so as to fully review and screen the objects to be submitted for review, and avoid the situation where the objects to be submitted for review are submitted for review repeatedly. Further, a screened object set can be constructed according to the objects to be submitted for review that meet the screening conditions, and then the screened object set can be sent to the review center to obtain the submission result. In this way, not only can the processing volume of the review center be reduced, the processing efficiency of the review center be improved, and the submission result can be quickly obtained, but also the review pass rate of the object set can be improved, and the occurrence of invalid submissions for review can be reduced.

[0215] Exemplary Electronic Devices

[0216] The exemplary embodiments of the present disclosure also provide an electronic device. The electronic device may include a processor and a memory. The memory stores executable instructions of the processor, such as a computer program. The processor executes the method steps of various exemplary embodiments of the present disclosure by executing the executable instructions.

[0217] Reference below Figure 4 , the electronic device is exemplarily described in the form of a general-purpose computing device. It should be understood that Figure 4 The electronic device 400 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0218] like Figure 4 As shown, the electronic device 400 may include: a processor 410 , a memory 420 , a bus 430 , an I / O (input / output) interface 440 , a network adapter 450 , and a display 480 .

[0219] The memory 420 may include a volatile memory, such as a RAM 421, a cache unit 422, and may also include a non-volatile memory, such as a ROM 423. The memory 420 may also include one or more program modules 424, such program modules 424 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or a combination thereof may include the implementation of a network environment. For example, the program module 424 may include each module in the above-mentioned device.

[0220] The processor 410 may include one or more processing units. For example, the processor 410 may include an AP (Application Processor), a modem processor, a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor and / or an NPU (Neural-Network Processing Unit), etc.

[0221] The processor 410 can be used to execute executable instructions stored in the memory 420, such as the above-mentioned task processing method, which includes the following steps: Step 201: Receive at least one object to be submitted for review; Step 202: Determine whether each object to be submitted for review meets the preset screening conditions; wherein the preset screening conditions include at least one of the first filtering sub-conditions, the submission cutoff sub-conditions and the material screening sub-conditions; Step 203: Construct a screened object set based on the objects to be submitted for review that meet the preset screening conditions; Step 204: Send the screened object set to the review center to obtain the submission result.

[0222] By executing the above method steps by the processor 410, at least one object to be submitted for review can be received, and then a judgment is performed on each object to be submitted for review, that is, whether each object to be submitted for review meets the preset screening conditions; wherein the preset screening conditions include at least one of the first filtering sub-condition, the submission for review truncation sub-condition, and the material screening sub-condition; that is, in the embodiment of the present disclosure, the objects to be submitted for review can be screened from multiple aspects, such as whether it is the first triggered object to be submitted for review, whether the sub-content of the object to be submitted for review itself has been submitted for review, etc., so as to fully review and screen the objects to be submitted for review, and avoid the situation where the objects to be submitted for review are submitted for review repeatedly. Further, a screened object set can be constructed according to the objects to be submitted for review that meet the screening conditions, and then the screened object set can be sent to the review center to obtain the submission result. In this way, not only can the processing volume of the review center be reduced, the processing efficiency of the review center be improved, and the submission result can be quickly obtained, but also the review pass rate of the object set can be improved, and the occurrence of invalid submissions for review can be reduced.

[0223] The bus 430 is used to realize the connection between different components of the electronic device 400, and may include a data bus, an address bus, and a control bus.

[0224] The electronic device 400 can communicate with one or more external devices 500 (eg, a keyboard, a mouse, an external controller, etc.) through the I / O interface 440 .

[0225] The electronic device 400 can communicate with one or more networks through the network adapter 440. For example, the network adapter 440 can provide mobile communication solutions such as 3G / 4G / 5G, or wireless communication solutions such as wireless LAN, Bluetooth, near field communication, etc. The network adapter 450 can communicate with other modules of the electronic device 400 through the bus 430.

[0226] The electronic device 400 may display the task processing status and the like through the display 480 .

[0227] although Figure 4Not shown, other hardware and / or software modules may also be provided in the electronic device 400, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0228] As can be seen from the above, the technical solution of the present disclosure can be implemented as a method, an apparatus, a system, a computer program product, a storage medium, an electronic device, etc. Those skilled in the art can understand that various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software, such as being respectively referred to as a "circuit", "module" or "system".

[0229] It should be understood that the present disclosure is not limited to the specific method steps or structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from the scope thereof. Those skilled in the art will easily think of other embodiments based on the specific embodiments provided by the present disclosure. Therefore, the specific embodiments provided by the present disclosure are only exemplary, and the scope and spirit of the present disclosure are indicated by the claims, and any variations, uses or adaptive changes of the present disclosure should be covered, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the technical field that are not disclosed in the present disclosure.

Claims

1. A task processing method, characterized in that: The method comprises: Receive at least one object to be reviewed; Determine whether each of the objects to be submitted for review meets a preset screening condition; wherein the preset screening condition includes at least one of a first filtering sub-condition, a submission for review cut-off sub-condition, and a material screening sub-condition; Constructing a screened object set based on the objects to be submitted for review that meet the preset screening conditions; The screened object set is sent to the review center to obtain the review result.

2. The method according to claim 1, characterized in that If the preset screening condition is the first filtering sub-condition, a screened object set is constructed based on the objects to be submitted for review that meet the preset screening condition, including: Determine the number of times each object to be submitted for review has been requested; When it is determined that the number of times the first object to be submitted for review has been requested is not less than a preset threshold, it is determined that the first filtering sub-condition is satisfied, and the first object to be submitted for review is used as an object in the filtered object set.

3. The method according to claim 1, characterized in that If the preset screening condition is a cut-off condition for submission for review, a screened object set is constructed based on the objects to be submitted for review that meet the preset screening condition, including: Determine push information for each object to be submitted for review; wherein the push information is used to indicate the possibility of the object to be submitted for review being pushed for display; When it is determined that the push information of the second review object is within the preset range and the review cutoff sub-condition is met, the second review object is used as an object in the filtered object set.

4. The method according to claim 3, characterized in that Determine the push information for each object to be reviewed, including: Determine the exposure and click rate of each object to be reviewed; According to the exposure rate, click rate and respective weights of each object to be submitted for review, push information for each object to be submitted for review is determined.

5. The method according to claim 1, characterized in that If the preset screening condition is a material screening sub-condition, a screened object set is constructed based on the objects to be submitted for review that meet the preset screening condition, including: For each object to be submitted for review, perform the following operations: Perform a segmentation operation on the object to be submitted for review to obtain a subunit corresponding to the object to be submitted for review, wherein the subunit includes at least one of text, picture, and video; According to the sub-unit corresponding to the object to be submitted for review and the material screening sub-condition, obtaining the screening sub-unit corresponding to the object to be submitted for review; The screening subunit is used as an object in the screened objects.

6. The method according to claim 5, characterized in that If the subunit is a text, obtaining the screening subunit corresponding to the object to be submitted for review according to the subunit corresponding to the object to be submitted for review and the material screening subcondition includes: Regularizing the text corresponding to the object to be submitted for examination to obtain a first text, and performing hash processing on the first text to obtain a first hash value; When it is determined that the first Hash value is inconsistent with the Hash value of the text content retrieved in the audit result library, the first text is used as a screening subunit corresponding to the object to be submitted for review.

7. The method according to claim 5, characterized in that If the sub-unit is a picture, obtaining the screening sub-unit corresponding to the object to be submitted for review according to the sub-unit corresponding to the object to be submitted for review and the material screening sub-condition includes: Performing hash processing on the uniform resource locator of the image corresponding to the object to be submitted for review to obtain a second hash value; When it is determined that the second Hash value is inconsistent with the Hash value of the uniform resource locator of the picture in the material library, the uniform resource locator of the picture is used as the screening sub-unit corresponding to the object to be submitted for review.

8. A task processing device, characterized in that: The device comprises: A receiving unit, configured to receive at least one object to be submitted for review; A screening unit, used to determine whether each of the objects to be submitted for review meets a preset screening condition; wherein the preset screening condition includes at least one of a first filtering sub-condition, a submission cut-off sub-condition, and a material screening sub-condition; and, based on the objects to be submitted for review that meet the preset screening condition, construct a screened object set; The review unit is used to send the screened object set to the review center to obtain the review result.

9. An electronic device, characterized in that: include: processor; A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 7 by executing the executable instructions.

10. A computer program product having a computer program stored thereon, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images