Content sorting method and apparatus for content pushing, and electronic device and medium

Abstract

The present disclosure relates to a content sorting method and apparatus for content pushing, and an electronic device and a medium. The method comprises: acquiring target content to be labeled, and determining the type of the target content. The method further comprises: determining a priority coefficient of the target content on the basis of the type of the target content and a plurality of target parameters, wherein the priority coefficient is a binary integer of a predetermined length, and the plurality of target parameters at least comprise a content quality score, a content timeliness score and an accessibility level score. The method further comprises: determining the sorting of the target content on the basis of the priority coefficient; and on the basis of the sorting, sending, to a labeling platform, information for indicating the target content, wherein the labeling platform is used for generating a label of the target content.

Description

Content sorting method, device, electronic device and medium for content push

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on July 21, 2023, with application number 202310906723.7 and invention name “Content sorting method, device, electronic device and medium for content push”, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present disclosure generally relates to the field of big data technology, and more specifically, to a content sorting method, apparatus, electronic device, and medium for content push. Background Art

[0004] As the amount of content on content platforms that provide audio, video, graphics, and text continues to grow, it becomes increasingly important to properly categorize content and push personalized content to users. To this end, more and more content platforms are beginning to use tagging mechanisms.

[0005] Content platforms can tag content when acquiring or generating it, allowing them to display relevant content to users based on the tags they select. Content platforms can also tag users and push content with the same tags to users, enabling personalized push notifications. Currently, content tags can be generated through tagging platforms.

[0006] Summary of the Invention

[0007] Embodiments of the present disclosure provide a content sorting method, apparatus, electronic device, and medium for content push.

[0008] According to the first aspect of the disclosure, a content sorting method for content push is provided. The method includes obtaining target content to be annotated. The method also includes determining the type of the target content. The method also includes determining a priority coefficient of the target content based on the type of the target content and a plurality of target parameters, wherein the priority coefficient is a binary integer of a predetermined length, and wherein the plurality of target parameters include at least a content quality score, a content timeliness score, and a visibility level score. The method also includes determining the sorting of the target content based on the priority coefficient. In addition, the method also includes sending information indicating the target content to an annotation platform based on the sorting, wherein the annotation platform is used to generate a label for the target content.

[0009] In the second aspect of the disclosure, a content sorting device for content push is provided. The device includes an acquisition module configured to acquire target content to be annotated. The device also includes a type determination module configured to determine the type of the target content. The device also includes a priority determination module configured to determine the priority coefficient of the target content based on the type of the target content and a plurality of target parameters, the priority coefficient being a binary integer of a predefined length, and wherein the plurality of target parameters include at least a content quality score, a content timeliness score, and a visibility score. The device also includes a ranking module configured to determine the ranking of the target content based on the priority coefficient. In addition, the device also includes a sending module configured to send information indicating the target content to an annotation platform based on the ranking, the annotation platform being used to generate a label for the target content.

[0010] In a third aspect of the present disclosure, an electronic device is provided, comprising a processor and a memory coupled to the processor, wherein the memory has instructions stored therein, and when the instructions are executed by the processor, the electronic device executes the method according to the first aspect.

[0011] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer-executable instructions, wherein the computer-executable instructions are executed by a processor to implement the method according to the first aspect.

[0012] This summary is intended to introduce a selection of concepts in a simplified form that are further described below in the detailed description. It is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0014] FIG1 illustrates a schematic diagram of an example environment in which various embodiments of the present disclosure may be implemented;

[0015] FIG2 shows a schematic flow chart of a content sorting method for content push according to certain embodiments of the present disclosure;

[0016] FIG3 is a schematic diagram showing a scenario of determining labels with finer granularity for content classification in an embodiment of the present disclosure;

[0017] FIG4 shows a schematic diagram of priority coefficients according to certain embodiments of the present disclosure;

[0018] FIG5 is a schematic diagram showing a process of determining a priority coefficient of target content according to certain embodiments of the present disclosure;

[0019] FIG6 shows another schematic diagram of priority coefficients according to certain embodiments of the present disclosure;

[0020] FIG7 shows a block diagram of a content ranking apparatus according to some embodiments of the present disclosure; and

[0021] FIG8 illustrates a block diagram of an electronic device according to certain embodiments of the present disclosure.

[0022] Throughout the drawings, the same or similar reference numbers denote the same or similar elements. DETAILED DESCRIPTION

[0023] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions.

[0024] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0025] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. can refer to different or the same objects, unless explicitly stated otherwise. Other explicit and implicit definitions may also be included below.

[0026] In order to achieve personalized push and classified display of content such as articles, pictures, and videos, you can annotate the content and users with tags, and push and display the content by matching the tags between the content and the user. At present, the content in the content platform is usually annotated with tags, which can indicate the category of the content. Content-based tags can achieve personalized push and display of content. In some cases, these contents will be provided to users who have higher requirements for content classification granularity, such as enterprise-level users. At this time, if content is pushed to users or different categories of content are displayed based on the original tags of the content, the content presented to users will not be the finely classified content required by users because the classification granularity of the original tags of the content is not fine enough. Users will need to perform further screening to obtain the content they originally needed, which will increase the cost of users. Therefore, in order to meet user needs, it is necessary to generate more fine-grained tags for content.

[0027] Manual annotation on a tagging platform can generate more granular labels for appropriate content. However, the platform's limited number of annotators and their processing power limit the efficiency of tagging content. Furthermore, content platforms host a vast amount of content, and its quality varies widely. Due to this limited efficiency, tagging platforms are unable to generate more granular labels for high-quality content in a timely manner, resulting in users being unable to access high-quality content in a timely manner.

[0028] To this end, an embodiment of the present disclosure provides a content sorting method for content push, which determines a priority coefficient for the content based on the quality, timeliness and visibility of the content, and sorts the content based on the priority coefficient, and sends it to the annotation platform according to the sorting. This allows content with a higher priority to be sent to the annotation platform first to generate tags, so that content with a higher priority can be pushed to users in a timely manner, users can obtain higher quality and more effective content in a timely manner, and the user experience can be improved.

[0029] Figure 1 shows a schematic diagram of an example environment 100 in which multiple embodiments of the present disclosure can be implemented. As shown in Figure 1, the example environment 100 may include a content pool 110, a content processing device 120, and an annotation platform 140. The content pool 110 may be one or more memories, such as a memory in a content platform server, or an independently set memory, and content data may be stored in the content pool 110. In the embodiments of the present disclosure, content may include but is not limited to video content, audio content, text content, picture content, graphic content, etc., and content may be stored, processed or transmitted in the form of data packets, and a content may be uniquely associated with an identifier (ID). A label of a content may be, for example, a field indicating the category to which the content belongs, and the field may be included in a data packet of a content.

[0030] The content processing device 120 may be a computing system, a single server, a distributed server, or a cloud-based server. It may also be a user terminal, a mobile device, a computer, etc., and the present disclosure does not limit this. In an embodiment of the present disclosure, the content processing device 120 may obtain multiple contents from the content pool 110, which may include the target content 110-1. The content processing device may determine the order of the multiple contents and send the contents to the annotation platform 140 according to the order. For example, the content processing device may arrange the contents into a queue 130. After obtaining the target content 110-1 from the content pool 110, the content processing device 120 may determine the order of the target content 110-1 in the queue 130 and send information indicating the target content 110-1 to the annotation platform 140 according to the order in the queue 130. In an embodiment of the present disclosure, the content processing device 120 can generate a priority coefficient for the target content 110-1, which can be a binary integer of a predetermined length. The content processing device 120 can determine the ranking of the target content 110-1 in the queue 130 based on the priority coefficient of the target content 110-1.

[0031] In the example environment 100, the annotation platform 140 can be a computing system, a single server, a distributed server, or a cloud-based server, or can be a user terminal, a mobile device, a computer, etc. The annotation platform 140 can receive information indicating target content 110-1 from a content processing device and generate tags for the target content 110-1. In some embodiments, the annotation platform can include multiple annotation queues, each of which can correspond to a type of content, and each annotation queue can generate different types of tags.

[0032] It should be understood that the above description describes the architecture and functionality of the example environment 100 for illustrative purposes only and does not imply any limitation on the scope of the present disclosure. In some embodiments, the content pool 110, content processing device 120, and annotation platform 140 in the example environment 100 can be independent of each other or combined with each other. The embodiments of the present disclosure can also be applied to other environments with different structures and / or functions.

[0033] The following describes in detail the methods provided by the embodiments of the present disclosure in conjunction with Figures 2 to 6. For ease of understanding, the specific data mentioned in the following description are exemplary and are not intended to limit the scope of protection of the present disclosure. It is understood that the embodiments described below may also include additional actions not shown and / or may omit the actions shown, and the scope of the present disclosure is not limited in this respect.

[0034] FIG2 illustrates a schematic flow chart of a content ranking method 200 for content push according to certain embodiments of the present disclosure. Method 200 may be executed by a content processing device, which may be a computing system, a single server, a distributed server, or a cloud-based server. It may also be a user terminal, a mobile device, a computer, or the like, and may be implemented via software and / or hardware. For example, the content processing device may be the aforementioned content processing device 120. Referring to FIG2 , illustratively, method 200 may include blocks 210 to 250, which are described in detail below.

[0035] In box 210, the content processing device obtains the target content to be marked. The content processing device can obtain the target content to be marked from the content pool of the content platform. The content pool can be, for example, the content pool 110 shown in Figure 1. The target content in the content pool can be obtained by the content platform from the user device, or it can be generated by the content platform. The target content can include but is not limited to video content, graphic content or audio content. In some embodiments, the content processing device can send a content acquisition request to the content platform, so that the content platform sends the target content to the content processing device based on the request. In some embodiments, the content platform can send content to the content processing device at a predefined period, for example, sending 20 contents per hour, so that the content processing device can obtain the target content from the content platform. In some embodiments, the content processing device can obtain the content input by the user from the content platform in real time as the target content to be marked.

[0036] In block 220, the content processing device determines the type of the target content. The content processing device may parse the acquired target content and determine the target content type, for example, whether the target content is video content or graphic content. In some embodiments, the data packet of the target content includes format data indicating the type of the target content. The content processing device may parse the data packet of the target content, acquire the format data, determine the format of the target content, and determine the type of the target content based on the format of the target content.

[0037] In box 230, the content processing device determines the priority coefficient of the target content based on the type of the target content and multiple target parameters. The priority coefficient is a binary integer of a predetermined length, and the multiple target parameters include at least a content quality score, a content timeliness score, and a visibility score. The content quality score, the content timeliness score, and the visibility score are all obtained by the content processing device from the content platform. For example, they can be included in the data packet of the target content, or the content processing device can obtain them independently from the content platform. The content quality score is a numerical value related to the quality of the content. In some embodiments, a higher content quality score represents a higher content quality. The visibility score can indicate how easy it is for the target content to be obtained by the public. In some embodiments, a higher visibility score indicates that the target content is easier for the public to obtain through various information channels.

[0038] The content timeliness score indicates the effective duration of the target content. In some embodiments, the content timeliness score may be positively correlated with the effective duration of the target content. In some embodiments, the effective duration of the content is indicated in the target content. For example, the target content is graphic content, and the graphic content indicates the weather three days after the content is released. The effective duration of the content is 3 days. In some embodiments, the effective duration of the content is calculated by a predefined effective duration model. The effective duration model can determine the effective duration of the content based on the influence of the target content. For example, if the target content indicates that there is international news, the effective duration of the content can be determined to be one month. If the target content indicates local news, the effective duration of the content can be determined to be 1 day. It should be understood that the enumeration of target parameters in the embodiments of the present disclosure is only schematic, and the priority coefficient can also be determined based on more target parameters. The embodiments of the present disclosure do not limit the meaning of each target parameter and the method for determining the target parameter.

[0039] In some embodiments, different types of target content may correspond to different target parameters and different priority coefficient determination rules. In some embodiments, the target content is graphic content, and the target parameters also include the author's popularity score and the release time of the graphic content. The priority coefficient determination rule corresponding to the graphic content may determine the priority coefficient of the graphic content based on the author's popularity score, the content quality score, the content timeliness score, the visibility score, and the release time.

[0040] In some embodiments, the target content is video content, and the target parameters also include the author quality level and the release time of the video content. The priority coefficient determination rule corresponding to the video content can determine the priority coefficient of the video content based on the author quality level, content quality score, content timeliness score, visibility score and release time.

[0041] In block 240, the content processing device determines the order of the target content based on the priority coefficient. In an embodiment of the present disclosure, the content processing device can obtain multiple contents, each of which can correspond to a priority coefficient. The content processing device can queue the multiple contents based on the priority coefficients of the multiple contents. The priority coefficient is a binary integer of a predetermined length, so the priority coefficients of each content can be directly compared to determine the order of the content in the queue. In some embodiments, the content processing device arranges the multiple contents into a queue, with the content with the larger priority coefficient at the front and the content with the smaller priority coefficient at the back.

[0042] In block 250, the content processing device sends information indicating the target content based on the ranking of the target content to a tagging platform, which is used to generate a tag for the target content. After determining the ranking of the target content in the queue, the content processing device may send information indicating the target content, such as the ID of the target content, to the tagging platform in the order in which it appears in the queue. This allows the tagging platform to process the target content in an order determined based on the priority coefficients of the target content and generate tags for the target content. In some embodiments, if the target content has a higher priority coefficient and is ranked higher in the queue, the target content may be sent to the tagging platform first, allowing the tagging platform to promptly determine tags for the target content.

[0043] Based on the above technical content, by determining the priority coefficient of the target content, and sending the target content to the labeling platform according to the priority coefficient to generate a label for the target content, content with a higher priority can be processed earlier and tagged. When pushing content based on tags, since the target content is tagged first, the target content can be pushed to the user faster, so that the user can obtain the higher priority content in a timely manner. The target parameters used to determine the priority coefficient include the content quality score, content timeliness score and visibility score of the target content, so that the ranking of the target content will be related to the quality and timeliness of the target content, and then the user can get priority to obtain content with higher quality, stronger timeliness and more difficult to obtain from other content platforms, thereby improving the user experience.

[0044] In some embodiments, in the aforementioned box 210, the target content to be annotated has been marked with a label. For the sake of convenience, the label is called the first label. In the aforementioned box 250, the labeling platform to which the target content is sent is used to generate a label for the target content with a finer classification granularity than the first label. For the sake of convenience, the label is called the second label. In the embodiments of the present disclosure, the coarseness of the classification granularity of the label is relative. For example, in the label "film and television entertainment" and the label "movie reviews", the classification granularity of the label "film and television entertainment" is coarser, and the classification granularity of the label "movie reviews" is finer. In some embodiments, after the content processing device obtains the second label generated by the annotation platform, it can mark the target content with the second label, thereby generating the annotated target content. The content processing device can store the annotated target content in a memory, which can be a memory configured by the content processing device, or an independently set memory or cloud memory. In this way, the content platform can obtain the annotated target content from the memory and recommend content with a finer classification granularity to the user based on the second label.

[0045] As an example, FIG3 shows a schematic diagram of a scenario 300 for determining labels with finer granularity for content classification in an embodiment of the present disclosure. Referring to FIG3 , in the scenario 300 shown in FIG3 , target content 310 to be annotated is labeled with a coarse-grained label. After a content processing device 320 obtains the target content 310, it can determine the type of the target content 310 and determine the priority coefficient of the target content 310. Based on the priority coefficient, the content processing device 320 can determine the ranking of the target content 310 and send information indicating the target content 310 to the annotation platform 330 according to the ranking. The annotation platform 330 generates a fine-grained label for the target content 310 and sends the fine-grained label to the content processing device 320. The content processing device 320 can then label the target content with a third label, thereby generating annotated target content 340. The content processing device 320 can then store the annotated target content in a memory.

[0046] In some embodiments, the tagging platform to which the target content is sent in block 250 includes multiple tagging queues, and different tagging queues can generate tags for different types of content. Prior to block 250, the content processing device can also determine a target tagging queue corresponding to the target content in the tagging platform, so that the content processing device can send the target content to the target tagging queue. For example, the target content to be tagged can be tagged with a first tag. The content processing device can obtain the queue tag of the tagging queue from the tagging platform and, based on a match between the first tag of the target content and the queue tag of the tagging queue, determine a target tagging queue with the same tag for the target content. In some embodiments, the number of content sent to the tagging queues in the tagging platform per unit time is less than or equal to a predefined threshold. Different tagging queues can have different thresholds. For example, the tagging platform can include a tagging queue with a queue tag of "Film and Entertainment" and a tagging queue with a queue tag of "Science and Technology." The number of content sent to the tagging queue with the queue tag of "Film and Entertainment" per hour is less than or equal to 20, while the number of content sent to the tagging queue with the queue tag of "Science and Technology" per hour is less than or equal to 40. In some embodiments, the annotation platform includes a plurality of annotation queues, and the target parameter of the target content further includes a relevance score indicating a relevance between the target content and the target annotation queue.

[0047] In some embodiments, in the aforementioned box 230, different contents correspond to different priority determination rules. After determining the type of the target content, the content processing device can obtain the priority coefficient determination rule corresponding to the type based on the type of the target content. In some embodiments, the priority coefficient determination rule can be obtained from a cloud server, and the content processing device can send a rule acquisition request corresponding to the type of the target content to the cloud server, and receive a rule acquisition response from the cloud server, thereby obtaining the priority coefficient determination rule corresponding to the type of the target content from the cloud server. In some embodiments, different priority coefficient determination rules corresponding to different types are stored in the local memory of the content processing device, and the content processing device can obtain the priority coefficient determination rule corresponding to the type of the target content from the local server. The priority coefficient determination rule can be presented in the form of a predefined function, model or formula. For example, the priority coefficient determination rule can be shown as formula (1): P = VL×W1+DT×W2+QS×W3 (1)

[0048] Among them, P is the priority coefficient of the target content, VL is the visibility score, W1 is the weight of the visibility score, DT is the content timeliness score, W2 is the weight of the content timeliness score, QS is the content quality score, and W3 is the weight of the content quality score.

[0049] In some embodiments, after obtaining multiple target parameters for determining priority coefficients, the content processing device may process the target parameters to determine parameter values ​​corresponding to the target parameters, and then determine the priority coefficient of the target content based on the multiple parameter values ​​and the priority coefficient determination rule. In this case, the priority coefficient determination rule may be as shown in formula (2): P = f(VL) × W1 + g(DT) × W2 + h(QS) × W3 (2)

[0050] The parameters in formula (2) may correspond to the parameters in formula 1. In formula (2), f(VL) represents processing the visibility score to obtain a parameter value corresponding to the visibility score. In some embodiments, the smaller the content visibility score, the larger the value of the target parameter corresponding to the content visibility score. For example, the parameter value corresponding to the content visibility score may be five integers of "0", "1", "2", "3", and "4", and the content visibility score is an integer ranging from 0 to 100. The content processing device may determine that the parameter value is 0 when the content visibility score is greater than 69, that is, f(VL>69)=0; the content processing device may determine that the parameter value is 1 when the content visibility score is less than or equal to 69 and greater than 60, that is, f(69≥VL>60)=1. Correspondingly, f(60≥VL>49)=2, f(49≥VL>40)=3, and f(VL≤40)=4.

[0051] In formula (2), g(DT) represents processing the content timeliness score to obtain a parameter value corresponding to the content timeliness score. In some embodiments, the smaller the content timeliness score, the larger the value of the target parameter corresponding to the content timeliness score. For example, the parameter values ​​corresponding to the content timeliness score are three integers "1", "2", and "3", and the content timeliness score indicates the effective time of the content. For example, a content timeliness score of 1 indicates that the content is effective for 1 day, and a content timeliness score of 5 indicates that the content is effective for 5 days. The content processing device can determine that the parameter value is 1 when the content timeliness score is greater than 3, that is, g(DT>3)=1; the content processing device can determine that the parameter value is 2 when the content timeliness score is greater than 1 and less than or equal to 3, that is, g(3≥DT>1)=2; the content processing device can determine that the parameter value is 3 when the content timeliness score is less than or equal to 1, that is, g(DT≤1)=3.

[0052] In formula (2), h(VL) represents processing the content quality score to obtain a parameter value corresponding to the content quality score. In some embodiments, the content quality score is a decimal with three significant digits, ranging from greater than or equal to 0 to less than or equal to 1, and the parameter value corresponding to the content quality score is an integer ranging from 1 to 1000, so h(VL) = 1000 × VL.

[0053] It should be understood that the above description of the calculation and value range of each parameter in formula (2) is only illustrative and cannot be construed as limiting the embodiments of the present disclosure. It should also be understood that formulas (1) and (2) are merely examples given with the target parameters being the content quality score, the content timeliness score, and the visibility score. In some embodiments, the priority coefficient is also related to other target parameters (such as the relevance score). In this case, formulas (1) and (2) may also include other target parameters.

[0054] The above formula (2) is explained using the calculation of decimal numbers as an example. In an embodiment of the present disclosure, the content processing device can convert the decimal number into a binary number as the priority coefficient of the target content. In some embodiments, the priority coefficient includes fields corresponding to different target parameters. For example, the priority coefficient of the target content can be as shown in Figure 4. Referring to Figure 4, the priority coefficient 400 may include field 410, field 420 and field 430, which may correspond to target parameters of high to low importance. As an example, the importance of the target parameters from high to low is content quality score, content timeliness score and visibility score, then field 410 may correspond to the content quality score, field 420 may correspond to the content timeliness score, and field 430 may correspond to the visibility score. The priority coefficient includes fields corresponding to different target parameters, so that the target parameter with high importance will directly determine the size of the priority coefficient of the target content. When determining the order of two different target contents based on the priority coefficient, since the target parameter with the highest importance corresponds to the leftmost field in the priority coefficient, the size of the target parameter with the highest importance will directly determine the order of the two target parameters. Only when the target parameters with the highest importance of the two target contents are the same, other target parameters may affect the order of the two target contents. It should be understood that the priority coefficient and the fields in the priority coefficient shown in Figure 4 are only an illustration of an embodiment of the present disclosure and cannot be a limitation of the present disclosure. The present disclosure does not limit the length of the priority coefficient, and its length can be predefined, for example, it can be 64 bits in length. The present disclosure does not limit the number of target parameters, nor does it limit the number of fields corresponding to different target parameters in the priority coefficient, nor does it limit the length of the field, nor does it limit the target parameters to which each field specifically corresponds.

[0055] In some embodiments, the target content is graphic content, and the multiple target parameters of the target content include content quality score, author popularity score, content timeliness score, visibility score and release time. The priority coefficient of the target content includes fields corresponding to these target parameters, and from left to right corresponds to content quality score, author popularity score, content timeliness score, visibility score and release time.

[0056] In some embodiments, the target content is video content, and the multiple target parameters of the target content include a content quality score, an author quality rating, a content timeliness score, a visibility score, and a release time. The author quality rating may include a premium rating and a standard rating, the premium rating may be represented by an integer 1, and the standard rating may be represented by an integer 0. The priority coefficient of the target content includes fields corresponding to these target parameters, and from left to right, they correspond to the content quality score, the author popularity score, the content timeliness score, the visibility score, and the release time.

[0057] In some embodiments, the priority coefficient also includes a 1-bit ranking bit. This ranking bit is located before all fields corresponding to multiple target parameters of the target content in the priority coefficient. In some embodiments, the ranking bit can also be the leftmost significant bit in the priority coefficient. The ranking bit is pre-configured to a value of 1. The content processing device can determine the author of the target content. The author of the target content can, for example, be indicated by a field in the metadata of the target content's data packet. The content processing device can determine the author of the content sent to the annotation platform and count the number of contents sent to the annotation platform. If a predefined threshold number of contents with the same author as the current target content have been continuously sent to the annotation platform, the content processing device can set the ranking bit in the priority coefficient of the current target content to 0, thereby significantly reducing the value of the priority coefficient. In this way, if a predefined number of contents with the same author are continuously sent to the annotation platform, the priority coefficients determined by the content processing device for other contents by that author will be significantly reduced, and the ranking determined for other contents by that author will be at the end of the content queue and will be sent to the annotation platform last. In this way, content with the same author will not be sent to the annotation platform in a centralized manner, thereby avoiding continuous recommendation of a large amount of content with the same author to users, and users will not repeatedly obtain homogeneous content.

[0058] The above content, in conjunction with Figures 2 to 4, illustrates the content sorting method provided by an embodiment of the present disclosure. Next, taking graphic content as an example, in conjunction with Figure 5, the method for determining the priority coefficient of target content in an embodiment of the present disclosure is illustrated. Figure 5 is a schematic diagram of a process 500 for determining the priority coefficient of target content according to certain embodiments of the present disclosure. The process 500 shown in Figure 5 can be executed by a content processing device, which can be, for example, the content processing device 120 in Figure 1. As shown in Figure 5, the process 500 can include blocks 510 to 550.

[0059] In block 510, the content processing device determines that the target content is graphic content. As described in block 220, the content processing device can parse the target content's data packets to obtain the target content's format data, thereby determining that the target content is graphic content. In block 520, the tagging platform used to generate tags for the target content includes multiple tagging queues, and the content processing device can determine the target tagging queue to which the target content will be sent.

[0060] In box 530, the content processing device obtains multiple target parameters of the target content, wherein the multiple target parameters include content quality score, relevance score, author popularity score, content timeliness score, visibility score and release time. These target parameters can be obtained by the content processing device from the content platform, or they can be determined by the content processing device by parsing the data packet of the target content. In box 540, the content processing device obtains the priority coefficient determination rule corresponding to the graphic content based on the type of the target content. It should be understood that the order of boxes 530 and boxes 540 shown in Figure 5 is only schematic, and the present disclosure does not limit the order in which boxes 530 and boxes 540 are executed. In some embodiments, the content processing device may execute box 530 first and then box 540. In some embodiments, the content processing device may execute box 530 and box 540 at the same time.

[0061] In box 550, the content processing device determines the priority coefficient of the target content based on multiple target parameters and priority coefficient determination rules, and the priority coefficient is a binary integer of a predetermined length. In some embodiments, the content processing device can determine the parameter value corresponding to the target parameter based on the target parameter. For the sake of convenience, the parameter value is distinguished as parameter value AE below. Exemplarily, in the target parameter, the content quality score is a decimal with three significant digits in the value range greater than or equal to 0 and less than or equal to 1, and the relevance score is a decimal with three significant digits in the value range greater than or equal to 0 and less than or equal to 1. The content quality score and the relevance score can correspond to a parameter value A together. When the relevance score is greater than 0.5 and the content quality score is greater than 0.2, the value of parameter value A is 1000 times the value of the content quality score. Otherwise, the value of parameter A can be 0, that is, parameter value A is an integer between 0-1000. In another example, the content obtained by the annotation platform is content published within 3 days. The parameter value E corresponding to the publication time is the time difference between the publication time of the target content and the time 0:00 three days ago, in seconds. That is, the value of the parameter value E is an integer in the range of 0-259200 (60×60×24×3=259200). In some embodiments, the value of the parameter value B corresponding to the author's popularity score is an integer in the range of 0-250000, the value of the parameter value C corresponding to the content timeliness score is an integer of 1, 2, or 3, and the value of the parameter value D corresponding to the visibility score is an integer of 0, 1, 2, 3, or 4.

[0062] Through predefined rules, the content processing device can convert multiple target parameters of the target content into parameter values ​​AE. The content processing device can determine the priority coefficient based on the priority determination rule. For example, the priority coefficient determination rule can be shown as formula (3): P = A × 2 43 +B×2 24 +C×2 21 +D×2 18 +E (3)

[0063] Among them, P is the parameter value corresponding to the priority coefficient, and the content processing device converts it into a binary number, that is, obtains the priority coefficient of the target content. The priority coefficient obtained by formula (3) includes the fields corresponding to each target parameter. In some embodiments, the length of the priority coefficient is 64 bits, and the content processing device can add a sorting bit before the field determined by the target parameter. Exemplarily, the priority coefficient of the target content determined based on the above scheme can be shown in Figure 6. In Figure 6, the priority coefficient is a binary number with a length of 64 bits, which includes a field 610 corresponding to the release time, a field 620 corresponding to the visibility score, a field 630 corresponding to the content timeliness score, a field 640 corresponding to the author's popularity score, a field 650 corresponding to the content quality score and relevance score, and a sorting bit 660 of 1 bit length. There is also a reserved field before the sorting 660. The length of field 610 is 18 bits, so it can carry all the values ​​of the parameter value E (2 18 =262144>259200); the length of field 620 is 3 bits and can carry 2 3 = 8 possible values ​​of parameter value D; field 630 is 3 bits long and can carry 8 possible values ​​of parameter value C; field 640 is 19 bits long and can carry 2 possible values ​​of parameter value C. 19 = 524288 possible values ​​of parameter value B. The length of field 610 is 10 bits and can carry 2 10 = 1024 possible parameter values ​​A. The length of each field is related to the priority coefficient determination rule. In some embodiments, the length of each field corresponding to multiple target parameters may be determined first, and then the priority coefficient determination rule may be determined based on the length.

[0064] Based on the above technical content, the content processing device can determine a priority coefficient for the target content. The priority coefficient is related to the quality, relevance, author popularity, content timeliness and visibility of the target content, and the quality and relevance of the content have the greatest weight. In this way, content with higher quality and more relevant to the annotation queue can be sent to the annotation queue of the annotation platform first, which can improve the annotation rate of content in the annotation queue and ensure that higher quality content is recommended to users first.

[0065] Different types of target content can correspond to different priority coefficient determination rules, and the fields corresponding to the target parameters in the priority coefficient can also have different lengths. In some embodiments, the type of the target content is video content, the target parameters include content quality score, relevance score, author quality score, content timeliness score, visibility score, and release time, and the content processing device can determine the parameter values F-J corresponding to the target parameters respectively. Among them, the content quality score and the relevance score jointly correspond to the parameter value F, the author quality score corresponds to the parameter value G, the content timeliness score corresponds to the parameter value H, the visibility score corresponds to the parameter value I, and the release time corresponds to the parameter value J. The calculation methods and value ranges of the parameter values F, H, and I are the same as those in the foregoing box 550. Different from the graphic content, the target parameters of the video content include the author quality score, and the author quality score can correspond to the author quality label in the data packet of the target content. For example, the author quality label can indicate that the author quality of the target content is high-quality and ordinary. The author quality score of the high-quality target content can be 1, and the author quality score of the ordinary quality can be 2. Correspondingly, the parameter value G also takes the value of 1 or 2. If the target content has no author quality label, the parameter value G can take the value of 0. Correspondingly, the length of the field corresponding to the author quality score in the priority coefficient can be 2 bits, which can carry the parameter value G with 2 2 =4 kinds of values. The content obtained by the annotation platform can be the content whose release time is within the past 30 days. The parameter value J corresponding to the release time is the time difference between the release time of the target content and the time zero point 30 days ago, and the unit is seconds. That is, the value of the parameter value E is an integer within the range of 0-2592000 (60×60×24×30=2592000). Correspondingly, the length of the field corresponding to the release time in the priority coefficient can be 22 bits, so as to be able to carry all the values of the parameter value G (2 22 =<4194304>2592000). In this case, the priority coefficient determination rule can be as shown in formula (4): P=F×2 30 +G×2 28 +H×2 25 +I×X2 22 +J (4)

[0066] Among them, P is the parameter value corresponding to the priority coefficient, and the content processing device converts it into a binary number, that is, the priority coefficient of the target content is obtained.

[0067] It should be understood that the process 500 shown in Figure 5 and the priority coefficient 600 shown in Figure 6 are merely examples of embodiments of the present disclosure and cannot be a limitation of the present disclosure. The embodiments of the present disclosure can also be implemented in other ways. The above description of graphic content or video content is also only an example given for schematic purposes. The target content can also be other types of content, and the corresponding priority coefficients and priority coefficient determination rules can also be presented in other forms. This application does not limit this. In some embodiments, the process 500 can be implemented in combination with the aforementioned method 200. For example, box 510 can be executed after box 210, and box 240 can be executed after box 550.

[0068] Figure 7 shows a block diagram of a content sorting device 700 according to certain embodiments of the present disclosure. As shown in Figure 7, the content sorting device 700 includes an acquisition module 710, which is configured to acquire target content to be annotated. The content sorting device 700 also includes a type determination module 720, which is configured to determine the type of the target content. The content sorting device 700 also includes a priority determination module 730, which is configured to determine the priority coefficient of the target content based on the type of the target content and multiple target parameters, wherein the priority coefficient is a binary integer of a predefined length, and wherein the multiple target parameters include at least a content quality score, a content timeliness score, and a visibility score. The content sorting device 700 also includes a sorting module 740, which is configured to determine the ranking of the target content based on the priority coefficient. In addition, the content sorting device 700 also includes a sending module 750, which is configured to send information indicating the target content to an annotation platform based on the ranking, and the annotation platform is used to generate a label for the target content.

[0069] It should be understood that the modules in the embodiments of the present application are merely schematic diagrams provided for ease of explanation. The present application does not limit the specific forms of the modules in the content sorting device 700. The modules in the content sorting device 700 can be independent of each other, and different modules can also be combined with each other. Each module can be implemented through software and / or hardware.

[0070] FIG8 shows a block diagram of an electronic device 800 according to some embodiments of the present disclosure, and the electronic device 800 may be the device or apparatus described in the embodiments of the present disclosure. As shown in FIG8 , the electronic device 800 includes a central processing unit (CPU) and / or a graphics processing unit (GPU) 801, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 802 or computer program instructions loaded from a storage unit 808 into a random access memory (RAM) 803. In RAM 803, various programs and data required for the operation of the device 800 can also be stored. CPU / GPU 801, ROM 802, and RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804. Although not shown in FIG8 , the electronic device 800 may also include a coprocessor.

[0071] Multiple components in the electronic device 800 are connected to the I / O interface 805, including an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0072] The various methods or processes described above may be executed by the CPU / GPU 801. For example, in some embodiments, the methods may be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the CPU / GPU 801, one or more steps or actions in the methods or processes described above may be performed.

[0073] In some embodiments, the methods and processes described above may be implemented as a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present disclosure.

[0074] Computer-readable storage medium can be a tangible device that can keep and store the instructions used by the instruction execution device.Computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device or any suitable combination thereof.More specific examples (non-exhaustive list) of computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a convex structure in a groove having instructions stored thereon, and any suitable combination thereof.Computer-readable storage medium used herein is not interpreted as a transient signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagated by waveguides or other transmission media (for example, light pulses by fiber optic cables), or electrical signals transmitted by wires.

[0075] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0076] The computer program instructions for performing the disclosed operation can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data or source code or the object code written in any combination of one or more programming languages, programming languages ​​include object-oriented programming languages, and conventional procedural programming languages.Computer-readable program instructions can be performed completely on a user's computer, partially on a user's computer, performed as an independent software package, partly on a user's computer and partly on a remote computer, or performed completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer by any type of network-including local area network (LAN) or wide area network (WAN), or can be connected to an external computer (such as utilizing an internet service provider to connect by the internet). In certain embodiments, by utilizing the state information of computer-readable program instructions to carry out personalized customization electronic circuits, such as programmable logic circuits, field programmable gate arrays (FPGAs) or programmable logic arrays (PLA), this electronic circuit can perform computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0077] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0078] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0079] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and the part of the module, program segment or instruction contains one or more executable instructions for realizing the prescribed logical function. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart, can be implemented by a special hardware-based system that performs the prescribed function or action, or can be implemented by a combination of special hardware and computer instructions.

[0080] The embodiments of the present disclosure have been described above. The above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, practical applications, or technical improvements to existing technologies, or to enable other persons skilled in the art to understand the embodiments disclosed herein.

[0081] Some example implementations of the present disclosure are listed below.

[0082] Example 1. A content sorting method for content push, comprising:

[0083] Obtain the target content to be marked;

[0084] determining the type of the target content;

[0085] determining a priority coefficient of the target content based on the type of the target content and a plurality of target parameters, wherein the priority coefficient is a binary integer of a predetermined length, and the plurality of target parameters include at least a content quality score, a content timeliness score, and a visibility score;

[0086] determining a ranking of the target content based on the priority coefficient; and

[0087] Based on the ranking, information indicating the target content is sent to a tagging platform, and the tagging platform is used to generate a tag for the target content.

[0088] Example 2. The method of example 1, wherein determining the priority coefficient of the target content comprises:

[0089] obtaining the plurality of target parameters of the target content;

[0090] Based on the type of the target content, obtaining a priority coefficient determination rule; and

[0091] The priority coefficient is determined based on the plurality of target parameters and the priority coefficient determination rule.

[0092] Example 3. The method of any one of Examples 1-2, wherein determining the priority coefficient based on the plurality of target parameters and the priority coefficient determination rule comprises:

[0093] parsing the plurality of target parameters to determine a plurality of parameter values ​​corresponding to each of the plurality of target parameters; and

[0094] The priority coefficient is determined based on the multiple parameter values ​​and the weight of each target parameter in the multiple target parameters, and the priority coefficient includes a field indicating the multiple target parameters.

[0095] Example 4. The method according to any one of Examples 1-3, wherein the type of the target content is graphic content, the multiple target parameters further include the author popularity score of the graphic content and the publishing time of the graphic content, and

[0096] The fields in the priority coefficient correspond from left to right to: the content quality score, the author popularity score, the content timeliness score, the visibility score, and the publishing time.

[0097] Example 5. The method according to any one of Examples 1-4, wherein the type of the target content is video content, the multiple target parameters further include the author quality level of the video content and the release time of the video content, and

[0098] The fields in the priority coefficient correspond from left to right to: the content quality score, the author quality level, the content timeliness score, the visibility score, and the publishing time.

[0099] Example 6. The method of any one of Examples 1-5, wherein the priority coefficient includes a 1-bit ranking bit with a value of 1, the ranking bit being a significant bit located at the leftmost end of the priority coefficient, and

[0100] Determining the priority coefficient of the target content further includes:

[0101] When there are a first threshold number of continuously sent contents with the same author as the current target content among the contents already sent to the annotation platform, the value of the ranking bit in the priority coefficient of the current target content is set to 0.

[0102] Example 7. The method of any one of Examples 1-6, wherein the annotation platform includes a plurality of annotation queues, the method further comprising:

[0103] Determining a target annotation queue corresponding to the target content; and

[0104] The information indicating the target content is sent to the annotation platform, including:

[0105] Information indicating the target content is sent to the target annotation queue.

[0106] Example 8. The method of any one of Examples 1-7, wherein the plurality of target parameters further comprises a relevance score indicating a relevance between the target content and the target annotation queue determined for the target content.

[0107] Example 9. The method according to any one of Examples 1-8, wherein the amount of information indicating the target content sent to the target annotation queue within a unit time is less than or equal to a second quantity threshold.

[0108] Example 10. The method according to any one of Examples 1-9, wherein the target content to be annotated is marked with a first tag, and the method further comprises:

[0109] Acquire a second label corresponding to the target content from the annotation platform, where the second label has a finer classification granularity than the first label; and

[0110] The second tag is associated with the target content and stored as the marked target content.

[0111] Example 11. A content sorting device for content push, comprising:

[0112] An acquisition module, configured to acquire target content to be annotated;

[0113] a type determination module, configured to determine the type of the target content;

[0114] a priority determination module configured to determine a priority coefficient of the target content based on the type of the target content and a plurality of target parameters, wherein the priority coefficient is a binary integer of a predefined length, and the plurality of target parameters include at least a content quality score, a content timeliness score, and a visibility score;

[0115] a ranking module configured to determine a ranking of the target content based on the priority coefficient; and

[0116] The sending module is configured to send information indicating the target content to a tagging platform based on the ranking, and the tagging platform is used to generate a tag for the target content.

[0117] Example 12. The apparatus of Example 11, wherein the priority coefficient determination module comprises:

[0118] A first acquisition submodule is configured to acquire the multiple target parameters of the target content;

[0119] A second acquisition submodule is configured to acquire a priority coefficient determination rule based on the type of the target content; and

[0120] The first priority determination submodule is configured to determine the priority coefficient based on the multiple target parameters and the priority coefficient determination rule.

[0121] Example 13. The apparatus of any of Examples 11-12, wherein the first priority coefficient determination submodule comprises:

[0122] a target parameter parsing module configured to parse the plurality of target parameters to determine a plurality of parameter values ​​corresponding to each of the plurality of target parameters; and

[0123] The second priority determination submodule is configured to determine the priority coefficient based on the multiple parameter values ​​and the weight of each target parameter in the multiple target parameters, where the priority coefficient includes a field indicating the multiple target parameters.

[0124] Example 14. The apparatus according to any one of Examples 11-13, wherein the type of the target content is graphic content, the multiple target parameters further include a popularity score of the author of the graphic content and a publishing time of the graphic content, and

[0125] The fields in the priority coefficient correspond from left to right to: the content quality score, the author popularity score, the content timeliness score, the visibility score, and the publishing time.

[0126] Example 15. The apparatus of any one of Examples 11-14, wherein the type of the target content is video content, the multiple target parameters further include an author quality rating of the video content and a release time of the video content, and

[0127] The fields in the priority coefficient correspond from left to right to: the content quality score, the author quality level, the content timeliness score, the visibility score, and the publishing time.

[0128] Example 16. The apparatus of any one of Examples 11-15, wherein the priority coefficient includes a 1-bit ranking bit with a value of 1, the ranking bit being a leftmost significant bit of the priority coefficient, and

[0129] The priority determination module includes:

[0130] The ranking bit adjustment module is configured to set the value of the ranking bit in the priority coefficient of the current target content to 0 when there is a first threshold number of contents sent continuously by the same author as the current target content in the content that has been sent to the annotation platform.

[0131] Example 17. The apparatus of any of Examples 11-16, wherein the annotation platform comprises a plurality of annotation queues, the apparatus further comprising:

[0132] a marking queue determining module, configured to determine a target marking queue corresponding to the target content; and

[0133] The sending module includes:

[0134] The first sending submodule is configured to send information indicating the target content to the target marking queue.

[0135] Example 18. The apparatus of any of Examples 11-17, wherein the plurality of target parameters further comprises a relevance score indicating a relevance between the target content and the target annotation queue determined for the target content.

[0136] Example 19. The apparatus according to any one of Examples 11-18, wherein the amount of information indicating the target content sent to the target annotation queue within a unit time is less than or equal to a second quantity threshold.

[0137] Example 20. The apparatus according to any one of Examples 11-19, wherein the target content to be annotated is marked with a first tag, and the apparatus further comprises:

[0138] a label acquisition module configured to acquire a second label corresponding to the target content from the annotation platform, wherein the second label has a finer classification granularity than the first label; and

[0139] The storage module is configured to associate the second tag with the target content and store them as the marked target content.

[0140] Example 21. An electronic device comprising:

[0141] processor; and

[0142] A memory coupled to the processor, the memory having instructions stored therein, wherein when the instructions are executed by the processor, the electronic device performs actions, the actions comprising:

[0143] Obtain the target content to be marked;

[0144] determining the type of the target content;

[0145] determining a priority coefficient of the target content based on the type of the target content and a plurality of target parameters, wherein the priority coefficient is a binary integer of a predetermined length, and the plurality of target parameters include at least a content quality score, a content timeliness score, and a visibility score;

[0146] determining a ranking of the target content based on the priority coefficient; and

[0147] Based on the ranking, information indicating the target content is sent to a tagging platform, and the tagging platform is used to generate a tag for the target content.

[0148] Example 22. The electronic device of Example 21, wherein determining the priority coefficient of the target content comprises:

[0149] obtaining the plurality of target parameters of the target content;

[0150] Based on the type of the target content, obtaining a priority coefficient determination rule; and

[0151] The priority coefficient is determined based on the plurality of target parameters and the priority coefficient determination rule.

[0152] Example 23. The electronic device of any one of Examples 21-22, wherein determining the priority coefficient based on the plurality of target parameters and the priority coefficient determination rule comprises:

[0153] parsing the plurality of target parameters to determine a plurality of parameter values ​​corresponding to each of the plurality of target parameters; and

[0154] The priority coefficient is determined based on the multiple parameter values ​​and the weight of each target parameter in the multiple target parameters, and the priority coefficient includes a field indicating the multiple target parameters.

[0155] Example 24. The electronic device according to any one of Examples 21-23, wherein the type of the target content is graphic content, the multiple target parameters further include a popularity score of the author of the graphic content and a publishing time of the graphic content, and

[0156] The fields in the priority coefficient correspond from left to right to: the content quality score, the author popularity score, the content timeliness score, the visibility score, and the publishing time.

[0157] Example 25. An electronic device according to any one of Examples 21-24, wherein the type of the target content is video content, the multiple target parameters further include an author quality rating of the video content and a release time of the video content, and

[0158] The fields in the priority coefficient correspond from left to right to: the content quality score, the author quality level, the content timeliness score, the visibility score, and the publishing time.

[0159] Example 26. The electronic device according to any one of Examples 21-25, wherein the priority coefficient includes a 1-bit ranking bit with a value of 1, the ranking bit being a significant bit located at the leftmost end of the priority coefficient, and

[0160] Determining the priority coefficient of the target content further includes:

[0161] When there are a first threshold number of continuously sent contents with the same author as the current target content among the contents already sent to the annotation platform, the value of the ranking bit in the priority coefficient of the current target content is set to 0.

[0162] Example 27. The electronic device of any of Examples 21-26, wherein the annotation platform includes a plurality of annotation queues, and the actions further comprise:

[0163] Determining a target annotation queue corresponding to the target content; and

[0164] The information indicating the target content is sent to the annotation platform, including:

[0165] Information indicating the target content is sent to the target annotation queue.

[0166] Example 28. An electronic device according to any of Examples 21-27, wherein the plurality of target parameters further comprises a relevance score indicating a relevance between the target content and the target annotation queue determined for the target content.

[0167] Example 29. An electronic device according to any one of Examples 21-28, wherein the amount of information indicating the target content sent to the target annotation queue within a unit time is less than or equal to a second quantity threshold.

[0168] Example 30. The electronic device according to any one of Examples 21-29, wherein the target content to be annotated is marked with a first tag, and the action further comprises:

[0169] Acquire a second label corresponding to the target content from the annotation platform, where the second label has a finer classification granularity than the first label; and

[0170] The second tag is associated with the target content and stored as the marked target content.

[0171] Example 31. A computer-readable storage medium having computer-executable instructions stored thereon, wherein the computer-executable instructions are executed by a processor to implement the method according to any one of Examples 1 to 10.

[0172] Example 32. A computer program product tangibly stored on a computer-readable medium and comprising computer-executable instructions that, when executed by a device, cause the device to perform the method of any one of Examples 1 to 10.

[0173] Although the present disclosure has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A content sorting method for content push, comprising: Obtain the target content to be marked; determining the type of the target content; Determining a priority coefficient of the target content based on the type of the target content and a plurality of target parameters, the priority coefficient being a binary integer of a predetermined length, and the plurality of target parameters comprising at least a content quality score, a content timeliness score, and a visibility score; Based on the priority coefficient, determining the ranking of the target content; as well as Based on the ranking, information indicating the target content is sent to a tagging platform, and the tagging platform is used to generate a tag for the target content.

2. The method according to claim 1, wherein determining the priority coefficient of the target content comprises: Acquire the plurality of target parameters of the target content; Based on the type of the target content, obtaining a priority coefficient determination rule; as well as The priority coefficient is determined based on the plurality of target parameters and the priority coefficient determination rule.

3. The method according to claim 2, wherein determining the priority coefficient based on the plurality of target parameters and the priority coefficient determination rule comprises: parsing the plurality of target parameters to determine a plurality of parameter values ​​corresponding to each of the plurality of target parameters; as well as The priority coefficient is determined based on the multiple parameter values ​​and the weight of each target parameter in the multiple target parameters, and the priority coefficient includes a field indicating the multiple target parameters.

4. The method according to claim 1, wherein the type of the target content is graphic content, the multiple target parameters further include the popularity score of the author of the graphic content and the release time of the graphic content, and The fields in the priority coefficient correspond from left to right to: score, the author popularity score, the content timeliness score, the visibility score and the publishing time.

5. The method according to claim 1, wherein the type of the target content is video content, the multiple target parameters further include the author quality level of the video content and the release time of the video content, and The fields in the priority coefficient correspond from left to right to: the content quality score, the author quality level, the content timeliness score, the visibility score, and the publishing time.

6. The method according to claim 2, wherein the priority coefficient includes a 1-bit ranking bit with a value of 1, and the ranking bit is a significant bit located at the leftmost end of the priority coefficient, and Determining the priority coefficient of the target content further includes: When there are a first threshold number of continuously sent contents with the same author as the current target content among the contents that have been sent to the annotation platform, the value of the ranking bit in the priority coefficient of the current target content is set to 0.

7. The method according to any one of claims 1 to 6, wherein the annotation platform comprises a plurality of annotation queues, the method further comprising: Determine a target annotation queue corresponding to the target content; as well as The information indicating the target content is sent to the annotation platform, including: Information indicating the target content is sent to the target annotation queue.

8. The method of claim 7, wherein the plurality of target parameters further comprises a relevance score indicating a relevance between the target content and the target annotation queue determined for the target content. 9 . The method according to claim 7 , wherein the amount of information indicating the target content sent to the target annotation queue within a unit time is less than or equal to a second amount threshold.

10. The method according to claim 1, wherein the target content to be annotated is marked with a first tag, and the method further comprises: Acquire a second tag corresponding to the target content from the annotation platform, The second label has a finer classification granularity than the first label; as well as The second tag is associated with the target content and stored as the marked target content.

11. A content sorting device for content push, comprising: An acquisition module, configured to acquire target content to be annotated; A type determination module, configured to determine the type of the target content; a priority determination module configured to determine a priority coefficient of the target content based on the type of the target content and a plurality of target parameters, the priority coefficient being a binary integer of a predefined length, and the plurality of target parameters comprising at least a content quality score, a content timeliness score, and a visibility score; A ranking module, configured to determine the ranking of the target content based on the priority coefficient; as well as The sending module is configured to send information indicating the target content to a labeling platform based on the sorting, and the labeling platform is used to generate a label for the target content.

12. An electronic device comprising: processor; as well as A memory coupled to the processor, the memory having instructions stored therein, wherein when the instructions are executed by the processor, the electronic device executes the method according to any one of claims 1 to 10.

13. A computer-readable storage medium having computer-executable instructions stored thereon, wherein the computer-executable instructions are executed by a processor to implement the method according to any one of claims 1 to 10.

Images