An information scheduling method, device, apparatus and computer readable storage medium

Abstract

The application provides an information scheduling method, device and equipment and a computer readable storage medium. The method comprises the following steps: when receiving push information pushed to a user, extracting to-be-audited information from the push information, and extracting real-time feedback data corresponding to the to-be-audited information from real-time behavior data corresponding to the push information; determining a scheduling index corresponding to the to-be-audited information based on the real-time feedback data; the scheduling index represents an abnormal influence degree of the to-be-audited information; determining a real-time scheduling sequence of the to-be-audited information by using the scheduling index corresponding to the to-be-audited information; and auditing and scheduling the to-be-audited information according to the real-time scheduling sequence. Through the application, the stability of an online environment can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to information processing technology, and in particular, to an information scheduling method and device, equipment and a computer readable storage medium. BACKGROUND

[0002] When using a social application, a user often actively subscribes to some information sources. When a new push information is published by an information source, the social application can quickly obtain the push information and aggregate the push information into a push information stream, and push the push information to the user who subscribes to the information source, so that the user can obtain the push information published by the information source in a timely manner.

[0003] The push information will have a certain impact on the user. In order to maintain the online environment, it is necessary to find out the push information with adverse effects and take it off the shelf by means of post-audit. In related technologies, the push information to be audited is mainly audited according to time sequence. In this way, the audit sequence of the abnormal push information published later will inevitably be later, so that the possibility of timely auditing of such abnormal push information is relatively low, which leads to low efficiency of auditing abnormal push information, and ultimately leads to low stability of the online environment. SUMMARY

[0004] The embodiments of the present application provide an information scheduling method, device, equipment and computer readable storage medium, which can improve the stability of the online environment.

[0005] The technical solutions of the embodiments of the present application are as follows:

[0006] The embodiments of the present application provide an information scheduling method, which comprises:

[0007] When receiving the push information pushed to the user, extracting the to-be-audited information from the push information, and extracting the real-time feedback data corresponding to the to-be-audited information from the real-time behavior data corresponding to the push information;

[0008] Based on the real-time feedback data, determining the scheduling index corresponding to the to-be-audited information; the scheduling index represents the abnormal influence degree of the to-be-audited information;

[0009] Using the scheduling index corresponding to the to-be-audited information, determining the real-time scheduling sequence of the to-be-audited information;

[0010] According to the real-time scheduling sequence, auditing and scheduling the to-be-audited information.

[0011] The embodiments of the present application provide an information scheduling device, which comprises:

[0012] The data extraction module is configured to extract to-be-audited information from the push information received by the user and extract real-time feedback data corresponding to the to-be-audited information from real-time behavior data corresponding to the push information.

[0013] The index determination module is configured to determine a scheduling index corresponding to the to-be-audited information based on the real-time feedback data, wherein the scheduling index represents an abnormal influence degree of the to-be-audited information.

[0014] The sequence determination module is configured to determine a real-time scheduling sequence of the to-be-audited information by using the scheduling index corresponding to the to-be-audited information.

[0015] The audit scheduling module is configured to perform audit scheduling on the to-be-audited information according to the real-time scheduling sequence.

[0016] In some embodiments of the present application, the index determination module is further configured to construct an index weight corresponding to the to-be-audited information according to the real-time feedback data and a scheduling index calculation rule, wherein the index weight represents an abnormal degree of the to-be-audited information, the scheduling index calculation rule is a temporary index calculation rule with the best scheduling effect selected from a plurality of temporary index calculation rules, and the scheduling index corresponding to the to-be-audited information is calculated by using the index weight corresponding to the to-be-audited information.

[0017] In some embodiments of the present application, the real-time feedback data includes an information rejection quantity, an information publishing quantity, and a click quantity.

[0018] The index determination module is further configured to obtain an information source rejection rate corresponding to the to-be-audited information by comparing the information rejection quantity and the information publishing quantity, wherein the information rejection quantity represents a number of information of an information source corresponding to the to-be-audited information that is uninstalled, the information publishing quantity represents a total number of information published by the information source, and the index weight corresponding to the to-be-audited information is obtained by performing logarithmic operation on the information source rejection rate and the click quantity according to the scheduling index calculation rule, wherein the click quantity represents a number of times that the to-be-audited information is displayed.

[0019] In some embodiments of the present application, the real-time feedback data includes an information rejection quantity, an information publishing quantity, a click quantity, and a click quantity growth rate.

[0020] The index determination module is further configured to obtain an information source rejection rate corresponding to the to-be-audited information by comparing the information rejection amount and the information publishing amount; perform weight adjustment on the information source rejection rate to obtain an adjusted information source rejection rate; and perform logarithmic operation on the adjusted information source rejection rate, the click volume, and the click volume growth rate according to the scheduling index calculation rule to obtain the index weight corresponding to the to-be-audited information. The click volume growth rate represents a growth rate of the click volume of the to-be-audited information.

[0021] In some embodiments of the present application, the index determination module is further configured to calculate a first index component by using the click volume and a preset weight configuration parameter; calculate a second index component by using the click volume growth rate and the preset weight configuration parameter; multiply the first index component, the second index component, and the adjusted information source rejection rate to obtain an intermediate multiplication result corresponding to the to-be-audited information; and perform logarithmic operation on the intermediate multiplication result to obtain the index weight corresponding to the to-be-audited information.

[0022] In some embodiments of the present application, the index determination module is further configured to perform weight reduction on the index weight corresponding to the to-be-audited information to obtain a weight-reduced index weight; and calculate the scheduling index corresponding to the to-be-audited information by using the weight-reduced index weight.

[0023] In some embodiments of the present application, the data extraction module is further configured to select the real-time feedback data from the real-time behavior data according to a comparison result of the real-time behavior data and a real-time data threshold; the real-time behavior data is real-time data returned by a user for the pushed information, and the real-time behavior data includes at least one of a real-time click volume and a real-time comment volume; and the corresponding to-be-audited information is filtered from the pushed information by using the real-time feedback data.

[0024] In some embodiments of the present application, the data extraction module is further configured to compare the obtained historical behavior data corresponding to the pushed information with a historical data threshold to obtain a historical data comparison result; the historical behavior data includes at least one of a historical click volume, a historical negative feedback volume, a historical click growth rate, and a historical browsing time length; the to-be-audited information is filtered from the pushed information according to the historical data comparison result; and the real-time feedback data corresponding to the to-be-audited information is filtered from the real-time behavior data.

[0025] In some embodiments of the present application, the sequence determination module is further configured to determine an index determination sequence of the to-be-audited information according to a publishing time of the obtained to-be-audited information; and the index determination sequence indicates an order of determining the scheduling index corresponding to the to-be-audited information.

[0026] Correspondingly, the index determination module is further configured to determine the scheduling index corresponding to the information to be audited according to the real-time feedback data in the index determination order.

[0027] In some embodiments of the present application, the information scheduling apparatus further comprises a rule selection module.

[0028] The data extraction module is further configured to acquire at least one test auditing information and at least one test feedback data corresponding to the at least one test auditing information, and divide the at least one test auditing information into at least two test information sets.

[0029] The index determination module is further configured to calculate a test index weight corresponding to the test auditing information in each test information set according to the test feedback data corresponding to the test auditing information in each test information set and the temporary index calculation rule corresponding to each test information set, and construct a test scheduling index corresponding to the test auditing information in each test information set by using the test index weight.

[0030] The auditing scheduling module is further configured to schedule the test auditing information in each test information set according to the order of the test scheduling index.

[0031] The rule selection module is further configured to acquire scheduling effect data of the test auditing information in each test information set, the scheduling effect data describing the auditing scheduling situation of the test auditing information in each test information set, and select the best scheduling index calculation rule from the temporary index calculation rules corresponding to each test information set according to the scheduling effect data.

[0032] In some embodiments of the present application, the rule selection module is further configured to determine the scheduling effect corresponding to each test information set according to the scheduling effect data, and select the temporary index calculation rule corresponding to the test information set with the best scheduling effect as the scheduling index calculation rule.

[0033] In some embodiments of the present application, the order determination module is further configured to update the real-time scheduling order of the information to be audited based on the latest feedback data corresponding to the information to be audited, and obtain an updated scheduling order.

[0034] Correspondingly, the auditing scheduling module is further configured to schedule the information to be audited according to the updated scheduling order.

[0035] An information scheduling device is provided in the embodiments of the present application, which comprises:

[0036] a memory, configured to store executable information scheduling instructions;

[0037] a processor, configured to execute the executable information scheduling instructions stored in the memory, so as to implement the information scheduling method provided in the embodiments of the present application.

[0038] The embodiments of the present application provide a computer readable storage medium, which stores executable information scheduling instructions, and is used to cause the processor to execute the information scheduling method provided in the embodiments of the present application.

[0039] The embodiments of the present application have the following beneficial effects:

[0040] The information scheduling device can use the real-time feedback data corresponding to the information to be audited to construct the scheduling index corresponding to the information to be audited, so as to determine the abnormal influence degree of the information to be audited according to the user feedback, and then determine the real-time scheduling sequence of the information to be audited according to the abnormal influence degree of the information to be audited, that is, determine the sequence of the information to be audited in the audit. In this way, the information to be audited with large abnormal influence can be audited first, even if the abnormal information is published at a later time, it can also be audited in time, thereby improving the audit efficiency of the abnormal information, reducing the influence of the abnormal information on the online environment as much as possible, and improving the stability of the online environment. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 is an optional architecture schematic diagram of the information scheduling system 100 provided in the embodiments of the present application;

[0042] Figure 2 is a structure schematic diagram of the information scheduling device in the information scheduling system 100 provided in the embodiments of the present application; Figure 1

[0043] Figure 3 is an optional flow schematic diagram of the information scheduling method provided in the embodiments of the present application; Figure 1 ;

[0044] Figure 4 is an optional flow schematic diagram of the information scheduling method provided in the embodiments of the present application; Figure 2 ;

[0045] Figure 5 is an optional flow schematic diagram of the information scheduling method provided in the embodiments of the present application; Figure 3 ;

[0046] Figure 6 is a process example of extracting real-time feedback data and information to be audited provided in the embodiments of the present application; Figure 1 ;

[0047] Figure 7 ​is a process example provided by the embodiment of the present application for extracting real-time feedback data and information to be audited Figure 2 ;

[0048] Figure 8 is an optional flowchart of the information scheduling method provided by the embodiment of the present application Figure 4 ;

[0049] Figure 9 is a process example diagram for determining the scheduling index provided by the embodiment of the present application

[0050] FIG. 10(a) is a process example diagram for auditing the subscription content provided by the embodiment of the present application

[0051] FIG. 10(b) is a process example diagram for selecting the priority algorithm provided by the embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be described in further detail below with reference to the accompanying drawings, and the described embodiments should not be regarded as limiting the present application. All other embodiments obtained by those of ordinary skill in the art without making creative labor fall within the scope of protection of the present application.

[0053] In the following description, “some embodiments” are described, which describe a subset of all possible embodiments, but it can be understood that “some embodiments” can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0054] In the following description, the term “first\second” is only to distinguish similar objects, and does not represent a specific order of the objects. It can be understood that “first\second” can be interchanged in a specific order or sequence as allowed, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0056] The related data collection and processing in the embodiments of the present application should strictly comply with the requirements of relevant laws and regulations, obtain the informed consent or separate consent of the personal information subject, and carry out subsequent data use and processing behavior within the scope of authorization of laws and regulations and the personal information subject.

[0057] Before the embodiments of the present application are described in further detail, terms and names involved in the embodiments of the present application are explained, and the terms and names involved in the embodiments of the present application are applicable to the following explanations.

[0058] 1) Cloud Technology refers to a hosting technology that unifies a series of resources such as hardware, software, network, etc. in a wide area network or a local area network to realize data calculation, storage, processing and sharing.

[0059] Cloud Technology is a general term for network technology, information technology, integration technology, management platform technology, application technology, etc. based on the cloud computing business model application, which can form a resource pool, and be used on demand, flexibly and conveniently. Cloud computing technology will become an important support. The background service of a technical network system requires a large amount of computing and storage resources, such as video websites, picture websites and more portals. With the high development and application of the Internet industry, every item may have its own identification mark in the future, and it needs to be transmitted to the background system for logical processing. Different levels of data will be processed separately, and various industry data will need strong system support, which can only be realized through cloud computing.

[0060] 2) Push information aggregation refers to aggregating different information sources subscribed by a user, i.e. push information of different information sources. Push information aggregation can help users continuously obtain the latest subscription sources, i.e. the latest information published by information sources.

[0061] 3) Push information flow represents the information flow presented to the user after push information aggregation. The push information flow is generally displayed on the display interface of the user terminal, and in the push information flow, the title and cover of each push information are usually displayed, and the title and cover have a jump link, and when the user clicks the title or cover, the user can jump to the detail page of the push information.

[0062] 4) Review mainly refers to, after the push information is pushed to the terminal of the user, judging whether the push information is abnormal content that brings discomfort to the user according to the different dimensions of the user's reaction to the push information, for example, judging whether the push information is a safe and sensitive topic, false information, etc. When the review judges that the push information is bad content, the bad content needs to be deleted in time, so as to avoid the bad content from continuing to spread online and causing adverse effects.

[0063] 5) Information scheduling is to determine the audit priority of each push information that needs to be audited in the case of multiple push information that needs to be audited, so that the more urgent push information can be audited first.

[0064] 6) Page View (PV), also known as click volume, reflects the number of pages clicked by users. PV is a main indicator for measuring an information source or even a push information. In other words, PV measures the degree of user acceptance of the text and image content page.

[0065] 7) Video View (VV), reflecting the number of times a video is played, the more times a video is played, the more easily the video is accepted by the public. Therefore, VV also reflects the degree of user acceptance of video content.

[0066] Social applications provide great convenience for user communication and exchange. Various information sources are registered on social applications to enable various push information to spread on social applications, thereby improving the browsing volume of push information. When using social applications, users often actively subscribe to some information sources of interest in various information sources registered on social applications, so as to timely obtain content of interest. After the information source publishes the latest push information, the social application will start the push information aggregation process, that is, the latest push information is aggregated in the push information stream corresponding to the user who subscribes to the information source, so as to timely push the latest push information to the user who subscribes to the information source.

[0067] Users also generate feedback of different dimensions in the process of browsing push information. However, not all push information can bring positive effects to users, for example, some information channels may maliciously publish false information as the latest information message, or the push information involves sensitive topics. If these abnormal push information is allowed to spread on the network, it will have adverse effects on information security, public opinion security, and even user experience. In order to solve this problem, it is necessary to find abnormal push information by means of review, so as to timely delete these abnormal push information.

[0068] In related technologies, each push information is reviewed according to the time sequence of each push information, that is, the review order is determined according to the publication time of each push information, so as to realize first review for first publication and later review for later publication. However, considering the online environment, the problematic push information needs to be reviewed and removed in time. If the review is based on the time sequence, the review order of the abnormal push information published later will be later, so that the limited review manpower cannot be arranged for the most urgent content, which finally leads to low efficiency of reviewing abnormal push information, and further makes the online environment unstable.

[0069] Meanwhile, due to the difficulty in timely auditing of the abnormal push information, the abnormal push information is difficult to be timely taken down, so that the abnormal push information still has the opportunity to spread on the network, continuously brings adverse effects to users, and thus affects the overall product experience.

[0070] In addition, when the auditing order of the various push information is determined in chronological order, if the auditing speed is lower than the submission speed of the push information, the push information to be audited will accumulate, so that some push information to be audited cannot be audited in real time, and thus the real-time degree of the push information auditing is low.

[0071] Embodiments of the present application provide an information scheduling method, device, equipment and computer readable storage medium, which can improve the stability of online environment. The following describes an exemplary application of the information scheduling device provided by the embodiments of the present application. The information scheduling device provided by the embodiments of the present application can be implemented as a terminal or a server. The server can be a standalone physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud service, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, and big data and artificial intelligence platform. The terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal and the server can be directly or indirectly connected through wired or wireless communication, which is not limited in the present application. The following will describe an exemplary application of the information scheduling device.

[0072] Referring to Figure 1 , Figure 1 is an optional architecture diagram of the information scheduling system 100 provided by the embodiments of the present application. To realize an information scheduling application, the terminal (exemplarily showing the terminal 400-1 and the terminal 400-2) is connected to the information scheduling device 200 through the network 300. The network 300 can be a wide area network or a local area network, or a combination of the two. The information scheduling device 200 is also equipped with a database 500, which is used to provide data services for the information scheduling device 200.

[0073] The terminal 400-1 (information source side) is used to edit push information and send the push information to the information scheduling device 200 for publishing. The administrator of each information source will click the publish button provided on the graphical interface 400-11 of the terminal 400-1 after editing the push information, publish the push information through the network 300, and send the push information to the information scheduling device 200.

[0074] The terminal 400 - 2 (information display side) is used to display the published push information on the graphical interface 400 - 21 , obtain the user's corresponding real-time behavior data on the push information, and then send the real-time behavior data to the information scheduling device 200 .

[0075] When the information scheduling device 200 receives the push information pushed to the user, it extracts the real-time feedback data corresponding to the information to be reviewed from the real-time behavior data corresponding to the push information. Next, the information scheduling device 200 will determine the scheduling index corresponding to the information to be reviewed based on the real-time feedback data, where the scheduling index represents the degree of abnormal impact of the information to be reviewed. After that, the information scheduling device 200 uses the scheduling index corresponding to the information to be reviewed to determine the real-time scheduling order of the information to be reviewed. Finally, the information scheduling device 200 will perform review scheduling on the information to be reviewed based on the real-time scheduling data, for example, sending the information to be reviewed to the reviewer's work terminal for review.

[0076] See also Figure 2 , Figure 2 This embodiment of the present application provides Figure 1 The structural diagram of the information scheduling device in Figure 2 The information scheduling device 200 shown includes: at least one processor 210, a memory 250, at least one network interface 220 and a user interface 230. The various components in the information scheduling device 200 are coupled together via a bus system 240. It is understood that the bus system 240 is used to achieve connection and communication between these components. In addition to including a data bus, the bus system 240 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 240 is not described in detail. Figure 2 Various buses are labeled as bus system 240 .

[0077] The processor 210 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0078] The user interface 230 includes one or more output devices 231 that enable presentation of media content, including one or more speakers and / or one or more visual display screens. The user interface 230 also includes one or more input devices 232, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

[0079] The memory 250 can be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard drives, optical drives, and the like. The memory 250 optionally includes one or more storage devices remotely located from the processor(s) 210.

[0080] The memory 250 includes volatile memory or nonvolatile memory, and can also include both volatile and nonvolatile memory. Nonvolatile memory can be read only memory (ROM), volatile memory can be random access memory (RAM). The memory 250 described in embodiments of the present application is intended to include any suitable type of memory.

[0081] In some embodiments, the memory 250 is capable of storing data to support various operations, examples of which include programs, modules, and data structures or a subset or superset thereof, which are described below.

[0082] The operating system 251 includes systems programs for handling various basic system services and for performing hardware dependent tasks, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks;

[0083] The network communication module 252 is configured to communicate with other computing devices via one or more network interfaces 220 (wired or wireless), examples of which include Bluetooth, wireless fidelity (Wi-Fi), universal serial bus (USB), and the like;

[0084] The presentation module 253 is configured to enable presentation of information via one or more output devices 231 (e.g., a display screen, a speaker, and the like) associated with the user interface 230 (e.g., a user interface for operating peripheral devices and displaying content and information);

[0085] The input processing module 254 is configured to detect and interpret one or more user inputs or interactions from one or more input devices 232.

[0086] In some embodiments, the information scheduling apparatus provided by embodiments of the present application can be implemented in software, Figure 2An information scheduling device 255 stored in the memory 250 is shown, which can be software in the form of programs and plug-ins, including the following software modules: data extraction module 2551, indicator determination module 2552, sequence determination module 2553, audit scheduling module 2554 and rule selection module 2555. These modules are logical and can therefore be arbitrarily combined or further split according to the functions implemented.

[0087] The functions of each module will be described below.

[0088] In other embodiments, the information scheduling device provided in the embodiments of the present application can be implemented in hardware. As an example, the information scheduling device provided in the embodiments of the present application can be a processor in the form of a hardware decoding processor, which is programmed to execute the information scheduling method provided in the embodiments of the present application. For example, the processor in the form of a hardware decoding processor can adopt one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs) or other electronic components.

[0089] Illustratively, an embodiment of the present application provides an information scheduling device, including:

[0090] A memory for storing executable information scheduling instructions;

[0091] The processor is used to implement the information scheduling method provided in the embodiment of the present application when executing the executable information scheduling instruction stored in the memory.

[0092] The information scheduling method provided by the embodiment of the present application will be described below in conjunction with exemplary applications and implementations of the information scheduling device provided by the embodiment of the present application. It should be noted that the embodiment of the present application can be implemented with the help of cloud technology.

[0093] See also Figure 3 , Figure 3 This is an optional process diagram of the information scheduling method provided in the embodiment of the present application. Figure 1 , will combine Figure 3 The steps shown are explained.

[0094] S101, when receiving the push information pushed to the user, extracting the to-be-audited information from the push information, and extracting the real-time feedback data corresponding to the to-be-audited information from the real-time behavior data corresponding to the push information.

[0095] The embodiment of the application is implemented in the scenario of auditing the published push information, for example, auditing the published hot articles or auditing the published short videos. In this scenario, the information scheduling device receives the push information pushed to the user by the information source, that is, when receiving the push information, it is judged that the information auditing needs to be started, and thus the information scheduling process is started. At this time, the information scheduling device extracts the push information that needs to be audited again from the push information, and obtains the to-be-audited information. At the same time, the information scheduling device also obtains the real-time feedback data corresponding to the to-be-audited information from the real-time behavior data corresponding to the push information.

[0096] It should be noted that the push information in the embodiment of the application can be published after being audited, or directly published without being audited. However, for a certain published push information, whether it is audited when published or not, the push information is extremely likely to cause a certain degree of influence when being clicked and browsed by the user or in the process of network transmission, and whether the influence is harmful to the online environment needs to be further audited to determine. Therefore, some push information needs to be audited as to-be-audited information after being published.

[0097] It can be understood that the to-be-audited information can be text and image information, for example, hot articles, hot pictures, etc., or video information, for example, short videos recorded by the user, news release videos, etc., or audio information, for example, hot songs, recorded content, etc.

[0098] In some embodiments of the application, the to-be-audited information can be all published push information, and at this time, the information scheduling is implemented for all published push information. In other embodiments, the to-be-audited information can also be some push information selected from all published push information, that is, the information scheduling device selects the push information with a wide range of dissemination, for example, the number of views reaches a certain threshold or the number of comments and forwards reaches a certain threshold (such push information has great influence and needs to be focused on in the audit), or the push information with potential adverse effects, for example, the number of negative feedbacks reaches a threshold or the push information leads public opinion to a negative direction, and then selects the part of the push information as the to-be-audited information. Of course, the information scheduling device can also obtain the to-be-audited information through other ways, which is not limited in the embodiment of the application.

[0099] It should be noted that the real-time behavior data is data obtained by counting the feedback of the user at the current time for the push information, for example, the number of comments, the number of negative feedback, the total duration of the user staying on the page of the information to be reviewed, the number of positive feedback, the number of clicks, the number of plays, and the like. Similarly, the real-time feedback data is data obtained by counting the feedback of the user at the current time for the information to be reviewed, and the real-time feedback data can reflect the propagation degree of the information to be reviewed at the current time, the emotional tendency of the user at the current time for the information to be reviewed, and the like.

[0100] It can be understood that in some embodiments of the present application, the information scheduling device can start the information scheduling process immediately after receiving the push information. In other embodiments, the information scheduling device can also start the information scheduling process when the push information is received and a preset time is reached.

[0101] S102, determining the scheduling index corresponding to the information to be reviewed based on the real-time feedback data.

[0102] After the information scheduling device obtains the real-time feedback data, the user feedback corresponding to the information to be reviewed is used to determine the scheduling index corresponding to the information to be reviewed. Since the real-time feedback data can reflect the propagation degree of the information to be reviewed at the current time and the emotional tendency of the user at the current time for the information to be reviewed, the propagation degree reflects the influence of the information to be reviewed, and the emotional tendency of the user for the information to be reviewed reflects whether the information to be reviewed has a positive or negative impact, therefore, the scheduling index constructed by using the real-time feedback data represents the abnormal influence of the information to be reviewed.

[0103] It should be noted that in the embodiments of the present application, the form of the scheduling index can be an abnormal influence level, for example, high abnormality, moderate abnormality, normality, and the like. The form of the scheduling index can also be an abnormal influence score, for example, 10000 points, 0 points, 500 points, and the like.

[0104] In some embodiments of the present application, when the scheduling index is in the form of an abnormal influence level, the information scheduling device can directly determine whether the to-be-audited information has a positive or negative influence (for example, a negative influence when the number of negative feedbacks is greater than the number of positive feedbacks) according to the size relationship between the number of positive feedbacks and the number of negative feedbacks in the real-time feedback data corresponding to the to-be-audited information, and determine the influence size of the to-be-audited information (for example, a large influence when any one of the number of comments, the total duration of the user staying on the page of the to-be-audited information, the click volume, and the play volume exceeds the preset threshold) according to the size relationship between the number of comments, the total duration of the user staying on the page of the to-be-audited information, the click volume, the play volume, and the preset threshold. Then, the to-be-audited information is classified according to whether it has a negative or positive influence and whether it has a large or small influence, and the obtained level is the scheduling index. For example, when the to-be-audited information has a negative influence and a large influence, the scheduling index is determined to be high abnormality, and when the to-be-audited information has a positive influence and a small influence, the scheduling index is determined to be normal.

[0105] When the scheduling index is in the form of an abnormal influence score, the information scheduling device can perform operations on the real-time feedback data according to a scheduling index calculation rule, so as to determine the scheduling index of the to-be-audited information. Further, this scheduling index calculation rule can be a temporary index calculation rule with the best effect selected from a plurality of different temporary index calculation rules according to the scheduling effect of the audit scheduling in the test phase.

[0106] S103, determining a real-time scheduling order of the to-be-audited information by using the scheduling index corresponding to the to-be-audited information.

[0107] After obtaining the scheduling index corresponding to the to-be-audited information, the information scheduling index can determine the order of the to-be-audited information in the audit according to the scheduling index, that is, the abnormal influence degree of the to-be-audited information, so that the information scheduling device obtains the real-time scheduling order of the to-be-audited information, so as to subsequently perform audit scheduling according to the real-time scheduling order.

[0108] It should be noted that, in practice, in order to maintain the online environment as much as possible, it is necessary to audit the push information with a large influence and a negative influence as soon as possible, that is, to audit the push information with a large abnormal influence as soon as possible. As can be seen, the information scheduling device determines the audit priority of the to-be-audited information by using the abnormal influence degree, which can realize the audit of the to-be-audited information with a large abnormal influence, that is, a large adverse influence, first.

[0109] It can be understood that when the scheduling index is the abnormal influence score of the audit, the information scheduling device can directly sort the scheduling indexes corresponding to the to-be-audited information in descending order according to the sorting result, and the sorting result is the real-time scheduling order of the to-be-audited information.

[0110] When the scheduling index is the abnormal influence level, the information scheduling device can first sort the to-be-audited information corresponding to the highest abnormal influence level in the order of the publishing time, to obtain the sub-scheduling order corresponding to the highest abnormal influence level, and then sort the to-be-audited information corresponding to the second highest abnormal influence level in the order of the publishing time, to obtain the sub-scheduling order corresponding to the second highest abnormal influence level, until the sorting of all abnormal influence levels is completed, to obtain the sub-scheduling order corresponding to the abnormal influence level, and finally arrange the sub-scheduling orders in the order of the abnormal influence level from high to low, to finally obtain the real-time scheduling order of the to-be-audited information.

[0111] For example, when the abnormal influence level is high abnormality and normal, the information scheduling device first sorts the to-be-audited information 1 and the to-be-audited information 2 corresponding to the high abnormality in the order of the time, and the obtained sub-scheduling order is <to-be-audited information 2, to-be-audited information 1>; the information scheduling device sorts the to-be-audited information 3 and the to-be-audited information 4 corresponding to the normal in the order of the time, and the obtained sub-scheduling order is <to-be-audited information 3, to-be-audited information 4>. Finally, the information scheduling device arranges the two sub-scheduling orders in the order of high abnormality and normal, and the obtained real-time scheduling order is <to-be-audited information 2, to-be-audited information 1, to-be-audited information 3, to-be-audited information 4>.

[0112] S104, auditing and scheduling the to-be-audited information according to the real-time scheduling order.

[0113] After obtaining the real-time scheduling order, the information scheduling device can assign the to-be-audited information to the terminal of the auditing personnel or the machine device capable of automatically auditing the information in sequence according to the real-time scheduling order, so as to complete the auditing and scheduling of the to-be-audited information. In this way, the to-be-audited information with high auditing urgency can be audited first, the auditing efficiency of the abnormal consultation information is improved, the to-be-audited information with problems can be located and processed in time, and the stability of the online environment is ensured.

[0114] It should be noted that in some embodiments of the present application, automatic auditing of information can be performed by the information scheduling device. At this time, when the information scheduling device schedules the information to be audited according to the real-time scheduling sequence, it can become: according to the real-time scheduling sequence, the information to be audited is audited one by one. At this time, the information scheduling device can use computer vision technology, such as object recognition technology and face recognition technology, to determine whether the information to be audited has any illegal images. It can use natural language processing technology, such as entity extraction and semantic understanding, to analyze whether the information to be audited has any illegal text content. It can use speech recognition technology to determine whether the information to be audited has any illegal speech. Thus, the information to be audited is extracted, and the information to be audited is removed, thereby ensuring the stability of the online environment and also ensuring the user experience.

[0115] In the embodiments of the present application, the information scheduling device can use the real-time feedback data corresponding to the information to be audited to construct the scheduling index corresponding to the information to be audited, thereby determining the abnormal influence degree of the information to be audited according to the user feedback, and then determining the real-time scheduling sequence of the information to be audited according to the abnormal influence degree of the information to be audited, that is, determining the order of the information to be audited during the audit. In this way, the information to be audited with a large abnormal influence will be audited first, even if the abnormal information is published later. It can be audited in time, thereby improving the auditing efficiency of the abnormal information and minimizing the impact of the abnormal information on the online environment, thereby improving the stability of the online environment.

[0116] In some embodiments of the present application, the information scheduling device audits the information to be audited according to the real-time scheduling sequence, and after the information to be audited is audited, it can be determined whether the information to be audited needs to be removed. When the information to be audited needs to be removed, the information scheduling device will delete the information to be audited from the online environment. At this time, when the user triggers the display link for displaying the information to be audited in the information stream, the information scheduling device will feedback to the terminal that the information to be audited has been removed, that is, the terminal sends a removal prompt information for the information to be audited to the terminal, and the terminal displays the removal prompt information corresponding to the information to be audited; when the information to be audited does not need to be removed, the information scheduling device will not delete the information to be audited from the online environment. At this time, when the user triggers the display link for displaying the information to be audited on the terminal, the terminal will normally display the information to be audited. It can be understood that the display link of the information to be audited can be the title, cover picture, video cover, etc. of the information to be audited, which is not limited in the present application.

[0117] In some embodiments of the present application, the push information stream is displayed in a first preset area of the display interface of the terminal. When the terminal displays the offline prompt information, it can enter an offline prompt page for display, or a floating window can be popped up on the push information stream for display. Similarly, when the terminal displays the information to be reviewed, it can enter an information display interface for display, or a floating window can be popped up on the push information stream for display, which is not limited in the present application.

[0118] Referring to Figure 4 , Figure 4 is an optional flowchart of the information scheduling method provided by the embodiments of the present application Figure 2 In some embodiments of the present application, based on the real-time feedback data, the scheduling index corresponding to the information to be reviewed is determined, that is, the specific implementation process of S102 can include S1021-S1022, as follows:

[0119] S1021, according to the real-time feedback data and the scheduling index calculation rule, the index weight corresponding to the information to be reviewed is determined.

[0120] When the information scheduling device determines the scheduling index, it will first parse the index calculation parameters from the real-time feedback data, and then calculate these index calculation parameters according to the scheduling index calculation rule, so as to determine the index weight corresponding to the information to be reviewed. It should be noted that the index weight represents the abnormality degree of the information to be reviewed. That is, the information scheduling device determines the index weight of the information to be reviewed, which actually judges the abnormality degree of the information to be reviewed according to the index calculation parameters of the information to be reviewed. This abnormality degree can refer to the fact that the propagation range of the information to be reviewed is too wide, that is, it causes great influence in the public, or it refers to the fact that the information to be reviewed has potential adverse effects.

[0121] In some embodiments of the present application, the index calculation parameters can include the click volume and the browsing volume of the information to be reviewed, and can also include related parameters of the information source of the information to be reviewed (i.e., the information source of the information to be reviewed), such as the number of information rejected or offline by the information source, the total number of information published by the information source, and the increase rate of the click volume and the browsing volume, which are not limited in the present application.

[0122] It should be noted that in the embodiments of the present application, the scheduling index calculation rule is the temporary index calculation rule with the best scheduling effect selected from a plurality of temporary index calculation rules, so that a more accurate scheduling index can be obtained in the information scheduling process.

[0123] S1022, the scheduling index corresponding to the information to be reviewed is calculated by using the index weight corresponding to the information to be reviewed.

[0124] After constructing the indicator weight corresponding to the information to be reviewed, the information scheduling device first obtains the preset calculation parameters used to calculate the scheduling indicator. Then, it uses the preset parameters and the indicator weight to jointly calculate the scheduling indicator. Because the indicator weight represents the degree of abnormality of the information to be reviewed, and the degree of abnormality of the information to be reviewed can reflect the impact caused by it, the information scheduling device can construct a scheduling indicator based on the indicator weight to represent the degree of impact caused by the abnormality of the information to be reviewed.

[0125] In some embodiments of the present application, the preset calculation parameters may include a preset proportion construction parameter, a preset difference parameter, and a preset index score. In this case, the information scheduling device may first use the opposite number of the index weight as the exponent and the natural number e as the exponent to construct an index result, then sum the index result and the preset proportion construction parameter, and then use the summation result as the denominator and the preset proportion construction parameter as the numerator to calculate the proportion result. Next, the information scheduling device subtracts the proportion result from the preset difference parameter to obtain a difference result, and then multiplies the difference result by the preset index score. The product obtained is the scheduling index.

[0126] It is understood that the specific values ​​of the preset proportion construction parameter, the preset difference parameter, and the preset index score can all be set according to actual circumstances. For example, the preset proportion construction parameter can be 1 or 2; the preset difference parameter can be 0.5 or 0.3; and the preset index score can be 20,000 or 5,000.

[0127] For example, this application provides a formula for calculating the scheduling index, see formula (1):

[0128] (1)

[0129] in, is the indicator weight, 1 is the empirical value of the preset proportion construction parameter, 0.5 is the empirical value of the preset difference parameter, 20000 is the empirical value of the preset indicator score, and score is the scheduling indicator. After obtaining the specific value of the indicator weight, the information scheduling device can substitute the specific value of the indicator weight into formula (1) to obtain the specific value of the scheduling indicator.

[0130] In an embodiment of the present application, the information scheduling device can determine the indicator weight that can characterize the degree of abnormality of the information to be reviewed based on real-time feedback data and scheduling indicator calculation rules, so that the degree of abnormal impact can be accurately analyzed based on the degree of abnormality of the information to be reviewed, thereby improving the accuracy of the scheduling indicator.

[0131] In some embodiments of the present application, the real-time feedback data includes the information rejection amount, the information publishing amount and the click amount, at this time, according to the real-time feedback data and the scheduling index calculation rule, the index weight corresponding to the information to be audited is determined, that is, the specific implementation process of S1021 can include: S201-S202, as follows:

[0132] S201, the information source rejection rate corresponding to the information to be audited is obtained by comparing the information rejection amount with the information publishing amount.

[0133] Among them, the information rejection amount represents the number of information of the information source corresponding to the information to be audited that is taken down, and the information publishing amount represents the total number of information published by the information source;

[0134] When the real-time feedback data includes the information rejection amount, the information publishing amount and the click amount, the information scheduling device will determine the abnormality degree of the information to be audited by referring to the information source factor and the propagation factor at the same time according to these parameters. At this time, when constructing the index weight, the information scheduling device will first use the information rejection amount as the numerator and the information publishing amount as the denominator to perform ratio calculation, and the ratio result obtained is the information source rejection rate.

[0135] It can be understood that the information source rejection rate is the proportion of the information taken down to the published information, and the information taken down is generally the information that has a bad influence on the public, therefore, the information source rejection rate can indirectly indicate the possibility of potential bad influence of the content published by the information source, whether it needs to be focused on during the audit. For example, when the information source rejection rate of a certain information source is high, it means that the information source often publishes some abnormal push information, therefore, the information to be audited belonging to the information source has a high potential bad influence.

[0136] In some other embodiments of the present application, the information scheduling device can also construct the information source rejection rate based on the Bayesian average algorithm, that is, the information rejection amount and the information publishing amount are subjected to Bayesian average to obtain the information source rejection rate. At this time, the information scheduling device can first obtain the preset numerator parameter and the preset denominator parameter of the Bayesian average, then sum the information rejection amount and the preset numerator parameter to obtain the numerator sum result, sum the information publishing amount and the preset denominator parameter to obtain the denominator sum result, and finally compare the numerator sum result with the denominator sum result to obtain the ratio, which is the information source rejection rate constructed based on the Bayesian average algorithm.

[0137] It can be understood that the specific values of the preset numerator parameter and the preset denominator parameter can be set according to actual conditions, for example, the preset numerator parameter is set to 1 or 2.5, and the preset denominator parameter is set to 3 or 5, which is not limited in the present application.

[0138] S202. Perform a logarithmic operation on the information source rejection rate and click volume according to the scheduling indicator calculation rules to obtain the indicator weight corresponding to the information to be reviewed.

[0139] After constructing the information source rejection rate, the information scheduling device may further multiply the information source rejection rate corresponding to the information to be reviewed by the number of clicks on the information to be reviewed, and then use the first product obtained by the multiplication as the logarithm, and perform a logarithmic operation with a preset base. The resulting logarithmic operation result is the indicator weight of the information to be reviewed. In other embodiments, the information scheduling device may further first obtain a preset weight construction parameter, add the number of clicks and the preset weight construction parameter to obtain a sum, and then multiply the sum by the information source rejection rate to obtain a second product. Thereafter, use the second product as the logarithm, and perform a logarithmic operation with a preset base. The operation result is the indicator weight.

[0140] It is understandable that the preset base may be a natural number e, or other specified values, such as 10 or 2.

[0141] It should be noted that in the embodiment of the present application, regardless of whether the information to be reviewed is video information, graphic information or audio information, it can be displayed and played through the user's click operation. Therefore, the number of clicks reflects the number of times the user plays or browses the information to be reviewed, that is, the number of clicks represents the number of times the information to be reviewed is displayed.

[0142] It's understandable that there's a positive correlation between indicator weight and click volume, as well as between indicator weight and information source rejection rate. This is because a high click volume indicates that more users viewed the pending information, leading to widespread dissemination. A high information source rejection rate indicates that the corresponding information source frequently publishes objectionable content, thus increasing the potential for negative impact. Widespread dissemination and a high potential for negative impact both indicate a high degree of abnormality in the pending information.

[0143] For example, the embodiment of the present application provides a formula for constructing indicator weights, see formula (2):

[0144] (2)

[0145] in, The number of clicks on the information to be reviewed. is the amount of information rejection, is the amount of information released, is the preset weight construction parameter, 1 is the empirical value of the preset numerator parameter, 5 is the empirical value of the preset denominator parameter, is the information source rejection rate constructed based on the Bayesian average algorithm, The index weight is obtained. After the information scheduling device obtains the specific values of the click volume, the information rejection volume, and the information publishing volume, the specific value of the index weight can be calculated.

[0146] In the embodiments of this application, when the real-time feedback data includes the information rejection volume, the information publishing volume, and the click volume, the information scheduling device can first calculate the information source rejection rate, so as to determine whether the information source frequently publishes content with adverse effects, and then determine the abnormal degree of the information to be audited according to the information source rejection rate and the click volume. In this way, the information scheduling device can obtain the index weight based on user feedback, determine the abnormal situation of the information to be audited from the perspective of the information source and the click volume, and thus obtain the index weight, so as to subsequently determine the abnormal influence degree of the information to be audited from the perspective of the information source and the click volume.

[0147] Referring to Figure 5 , Figure 5 is an optional flowchart of the information scheduling method provided in the embodiments of this application Figure 3 In some embodiments of this application, the real-time feedback data includes the information rejection volume, the information publishing volume, the click volume, and the click volume growth rate. In this case, according to the real-time feedback data and the scheduling index calculation rule, the index weight corresponding to the information to be audited is determined, that is, the specific implementation process of S1021 can include: S203-S205, as follows.

[0148] S203, compare the information rejection volume with the information publishing volume to obtain the information source rejection rate corresponding to the information to be audited.

[0149] In the embodiments of this application, the scheduling index calculation rule is to determine the index weight by focusing on the propagation factor. At this time, in the index calculation parameters corresponding to the scheduling index calculation rule, in addition to the information rejection volume, the information publishing volume, and the click volume, the information volume growth rate is also included. In this step, the information scheduling device can directly compare the information rejection volume with the information publishing volume to obtain the information source rejection rate, or can construct the information source rejection rate based on the Bayesian average algorithm, which is not limited in this application.

[0150] S204, weight adjustment is performed on the information source rejection rate to obtain an adjusted information source rejection rate.

[0151] After obtaining the information source rejection rate, the information scheduling device performs weight adjustment on the information source rejection rate, so that the influence of the information source rejection rate in the construction process of the index weight changes, and an adjusted information source rejection rate is obtained. Further, the information scheduling device can reduce the weight of the information source rejection rate to obtain the adjusted information source rejection rate.

[0152] In some embodiments of the present application, the information scheduling device can perform exponential operation on the information source rejection rate to adjust the weight of the information source rejection rate, for example, taking the information source rejection rate as the base number and performing exponential operation on a preset exponent to obtain the adjusted information source rejection rate. The preset exponent can be set according to actual conditions, for example, 0.1, 0.3, or even 0.01, which is not limited in the present application.

[0153] In some other embodiments of the present application, the information scheduling device can also perform multiplication operation on the information source rejection rate to adjust the weight of the information source rejection rate. For example, multiplying the information source rejection rate by a preset weight adjustment parameter, and taking the product as the adjusted information source rejection rate. The preset weight adjustment parameter can be set according to actual conditions, for example, 0.2 or 0.05, which is not limited in the present application.

[0154] Of course, in some embodiments, the information scheduling device can also directly set the preset weight adjustment parameter to 0, that is, directly using the click volume and the click volume growth rate to construct the index weight.

[0155] S205, according to the scheduling index calculation rule, performing logarithmic operation on the adjusted information source rejection rate, the click volume, and the click volume growth rate to obtain the index weight corresponding to the information to be audited.

[0156] After obtaining the adjusted information source rejection rate, the information scheduling device can first multiply the click volume, the click volume growth rate, and the adjusted information source rejection rate to obtain a third product, and then perform logarithmic operation on the third product with a preset base number, and take the result of the logarithmic operation as the index weight.

[0157] In some other embodiments, when performing logarithmic operation on the adjusted information source rejection rate, the click volume, and the click volume growth rate to obtain the index weight corresponding to the information to be audited, the information scheduling device can also obtain a preset weight construction parameter, calculate a first index component using the click volume and the preset weight construction parameter, calculate a second index component using the click volume growth rate and the preset weight construction parameter, multiply the first index component, the second index component, and the adjusted information source rejection rate to obtain an intermediate multiplication result corresponding to the information to be audited, and then perform logarithmic operation on the intermediate multiplication result to obtain the index weight corresponding to the information to be audited.

[0158] Further, the information scheduling device can add the click volume and the preset weight construction parameter to obtain the first index component, or subtract the click volume and the preset weight construction parameter to obtain the first index component. Similarly, the information scheduling device can add the click volume growth rate and the preset weight construction parameter to obtain the second index component, or subtract the click volume growth rate and the preset weight construction parameter to obtain the second index component.

[0159] It should be noted that the click volume growth rate represents the growth rate of the click volume of the to-be-audited information, which can represent how fast the to-be-audited information is propagated, and both the click volume and the click volume growth rate can represent the propagation of the to-be-audited information.

[0160] It can be understood that there is a positive correlation between the index weight and the click volume growth rate. This is because when the click volume growth rate of the to-be-audited information is large, it means that the propagation is very rapid, and such rapidly propagated information is likely to be abnormal, so when the click volume growth rate is large, the index weight will also increase accordingly.

[0161] Exemplarily, the embodiment of the present application provides another formula for constructing the index weight, as shown in formula (3):

[0162] (3)

[0163] wherein, the click volume of the to-be-audited information, the information rejection volume, the information publishing volume, the preset weight construction parameter, 1 is an empirical value of a preset numerator parameter, and 5 is an empirical value of a preset denominator parameter, the click volume growth rate of the to-be-audited information, the preset weight adjustment parameter, the adjusted information source rejection rate, the index weight. After the information scheduling device knows the specific values of the above parameters, it can substitute the specific values of the parameters into formula (3), so as to obtain the specific value of the index weight.

[0164] In the embodiments of the present application, the information scheduling device can adjust the weight of the information source rejection rate after calculating the information source rejection rate, and then adjust the weight of the information source rejection rate, so that when constructing the index weight, the click volume and the click volume growth rate, i.e., the propagation factor of the information to be audited, can be considered to determine the abnormality degree of the information to be audited, so that in the subsequent process, the influence of the information to be audited on the public can be considered to determine whether the information to be audited needs to be audited first. In this way, the high-influence bad content can be found early, and the online environment is further maintained, and the user's subscription and push information use experience is ensured.

[0165] In some embodiments of the present application, the index weight corresponding to the information to be audited is used to calculate the scheduling index corresponding to the information to be audited, i.e., the specific implementation process of S1022 can include: S301-S302, as follows:

[0166] S301, the index weight corresponding to the information to be audited is reduced to obtain the reduced index weight.

[0167] In practice, due to the construction method of the index weight and other reasons, the index weight corresponding to the information to be audited is relatively close, i.e., the index weight corresponding to the information to be audited is concentrated in a small interval, which makes it difficult to determine the scheduling index in subsequent processes. For example, the scheduling index is concentrated around 2000, so that the audit scheduling based on the scheduling index is difficult to achieve good results. In order to avoid such problems, the information scheduling device can use a pre-set weight reduction parameter to reduce the index weight corresponding to the information to be audited when calculating the scheduling index corresponding to the information to be audited, to obtain the reduced index weight.

[0168] In the present application, the information scheduling device can multiply the pre-set weight reduction parameter and the index weight to obtain the product as the reduced index weight; the information scheduling device can also use the pre-set weight reduction parameter as the index and the index weight as the base number to perform exponential operation, at this time, the obtained exponential operation result is the reduced index weight.

[0169] It can be understood that the pre-set weight reduction parameter can be set to 0.2, or -0.1, or other values according to actual conditions, which are not limited in the present application.

[0170] S302, the reduced index weight is used to calculate the scheduling index corresponding to the information to be audited.

[0171] After obtaining the downgraded indicator weight, the information scheduling device obtains the preset proportion construction parameter, preset difference parameter, and preset indicator score. It then constructs the index result using the opposite of the downgraded indicator weight as the exponent and the natural number e as the exponent. The index result and the preset proportion construction parameter are then summed, and the sum is used as the denominator, with the preset proportion construction parameter as the numerator to calculate the proportion result. The information scheduling device then subtracts the proportion result from the preset difference parameter to obtain the difference result. This difference result is then multiplied by the preset indicator score. The resulting product is the scheduling indicator.

[0172] For example, the embodiment of the present application provides another formula for calculating the scheduling index, as shown in formula (4):

[0173] (4)

[0174] in, is the indicator weight, 1 is the empirical value of the preset proportion construction parameter, 0.5 is the empirical value of the preset difference parameter, 20000 is the empirical value of the preset indicator score, b is the preset de-weighting parameter, and score is the scheduling indicator. After obtaining the specific values ​​of the above parameters, the information scheduling device can substitute the specific values ​​of the indicator weight into Equation (4) to obtain the specific value of the scheduling indicator.

[0175] In an embodiment of the present application, the information scheduling device can also reduce the weight of the indicators corresponding to the information to be audited, and then use the reduced weight of the indicators to calculate the scheduling indicators, so that the scheduling indicators can be numerically differentiated, which is convenient for subsequent audit scheduling based on the scheduling indicators.

[0176] In some embodiments of the present application, the information to be reviewed is extracted from the push information, and the real-time feedback data corresponding to the information to be reviewed is extracted from the real-time behavior data corresponding to the push information. That is, the specific implementation process of S101 may include: S1011-S1012, as follows:

[0177] S1011 . Selecting real-time feedback data from the real-time behavior data based on a comparison result between the real-time behavior data and the real-time data threshold.

[0178] The information scheduling device acquires a preset real-time data threshold, and then compares the real-time behavior data with the real-time data threshold to determine the size relationship between the real-time behavior data and the real-time data threshold. Then, the information scheduling device takes the determined size relationship as the comparison result of the real-time behavior data and the real-time data threshold. Finally, the information scheduling device selects the real-time behavior data greater than the real-time data threshold as the real-time feedback data, or selects the real-time behavior data equal to the real-time data threshold as the real-time feedback data according to the comparison result.

[0179] It can be understood that the push information is all the push information that has been published, i.e., all the push information that exists online, and the user can generate various dimension feedbacks on these push information, and these feedbacks are real-time data. Therefore, the real-time behavior data is the real-time data returned by the user on the push information.

[0180] In the embodiments of the present application, the real-time behavior data includes at least one of real-time click volume and real-time comment volume. The real-time click volume indicates the propagation of the initial information, and the real-time comment volume indicates the influence of the initial information. The real-time behavior data can include only the real-time click volume of the push information, or only the real-time comment volume of the push initial information, and of course, the real-time behavior data can also include the real-time click volume and the real-time comment volume of the push information. In other embodiments of the present application, the real-time behavior data can also include other information, such as real-time like volume, real-time comment volume, etc.

[0181] Further, when the information scheduling device compares the real-time behavior data with the real-time data threshold, it actually compares the content contained in the real-time behavior data with the real-time data threshold. Moreover, the real-time data threshold should correspond to the content contained in the real-time behavior data, for example, when the real-time behavior data includes only the real-time click volume, the real-time data threshold is the real-time click volume threshold, when the real-time behavior data includes only the real-time comment volume, the real-time data threshold is the real-time comment volume threshold, and when the real-time behavior data includes both the real-time click volume and the real-time comment volume, the real-time data threshold includes the real-time click volume threshold and the real-time comment volume threshold.

[0182] It can be understood that the real-time data threshold can be set according to actual conditions, for example, the real-time comment volume threshold can be set to 100, or the real-time click volume threshold can be set to 1000, etc., which is not limited in the present application.

[0183] In some embodiments of the present application, the information scheduling device can select real-time data with real-time click volume greater than or equal to a real-time volume threshold to obtain real-time feedback data, or select real-time data with real-time comment volume greater than or equal to a real-time volume threshold to obtain real-time feedback data, or select real-time data with both real-time click volume and real-time comment volume greater than or equal to a real-time volume threshold to obtain real-time feedback data.

[0184] S1012, filtering corresponding information to be audited from the push information by using the real-time feedback data.

[0185] Since the real-time feedback data is selected real-time behavior data, the real-time behavior data and the push information have a corresponding relationship. After obtaining the real-time feedback data, the information scheduling device can extract push information corresponding to the real-time feedback data from the push information based on the corresponding relationship between the real-time behavior data and the push information, and then take the extracted prompt information as the information to be audited.

[0186] For example, the embodiments of the present application provide a process example of extracting real-time feedback data and information to be audited Figure 1 , referring to Figure 6 , the information scheduling device first obtains push information 6-1 and real-time behavior data 6-2, and the push information 6-1 and the real-time behavior data 6-2 have a corresponding relationship. The information scheduling device compares each data in the real-time behavior data 6-2 with the real-time data threshold 6-3, so as to select the real-time feedback data 6-21 greater than or equal to the real-time data threshold from the real-time behavior data 6-2. Then, the information scheduling device selects the information to be audited 6-11 corresponding to the real-time feedback data 6-21 from the push information 6-1.

[0187] In the embodiments of the present application, the information scheduling device can directly select push information with greater influence and faster spread at the current time according to the size relationship between the real-time behavior data corresponding to the push information and the real-time data threshold, so as to take these push information as the information to be audited, so that the push information with greater influence and faster spread at the current time can be audited subsequently.

[0188] In some embodiments of the present application, the information to be audited is extracted from the push information, and the real-time feedback data corresponding to the information to be audited is extracted from the real-time behavior data corresponding to the push information, that is, the specific implementation process of S101 can include: S1013-S1015, as follows:

[0189] S1013, comparing the obtained historical behavior data corresponding to the push information with the historical data threshold to obtain a historical data comparison result.

[0190] In addition to selecting the information to be audited based on the real-time feedback of the user to the published push information, the information scheduling device can also select the information to be audited based on the historical feedback of the user to the published push information. At this time, the information scheduling device also needs to obtain the historical behavior data corresponding to the push information, that is, data reflecting the historical feedback of the user to the push information. The information scheduling device obtains the historical data threshold, and then compares the historical behavior data corresponding to the push information with the historical data threshold. In this way, the size relationship between the historical behavior data corresponding to the push information and the historical data threshold can be determined, and thus the historical data comparison result corresponding to the push information is obtained.

[0191] It should be noted that the historical behavior data includes at least one of the historical click volume, the historical negative feedback volume (the number of steps, reports, etc.), the historical click growth rate, and the historical browsing time length, that is, the information scheduling device can take any one of the historical click volume, the historical negative feedback volume, the historical click growth rate, and the historical browsing time length as the historical behavior data, or take multiple ones of the historical click volume, the historical negative feedback volume, the historical click growth rate, and the historical browsing time length as the historical data.

[0192] It should be noted that when the information scheduling device compares the historical behavior data corresponding to the push information with the historical data threshold, it is actually comparing the content contained in the historical behavior data with the historical data threshold. Further, the historical data threshold can correspond to the content contained in the historical behavior data, that is, the historical data threshold can be a historical click volume threshold, a historical negative feedback volume threshold, a historical click growth rate threshold, and a historical browsing time length threshold, etc.

[0193] It can be understood that the specific value of the historical data threshold can be set according to actual conditions, for example, the historical negative feedback volume threshold is set to 500, or the historical click growth rate is set to 1000 / h, etc., which is not limited in the present application.

[0194] S1014, selecting the information to be audited from the push information according to the historical data comparison result.

[0195] After obtaining the historical data comparison result, the information scheduling device selects the information with the historical behavior data greater than the historical data threshold from the push information. At this time, the selected information is the information to be audited.

[0196] S1015, selecting the real-time feedback data corresponding to the information to be audited from the real-time behavior data.

[0197] Since there is a corresponding relationship between the push information and the real-time behavior data, and the information to be audited is the push information whose historical behavior data is greater than the historical data threshold, the information scheduling device can select the real-time behavior data corresponding to the information to be audited as the real-time feedback data corresponding to the information to be audited according to the corresponding relationship between the push information and the real-time behavior data.

[0198] For example, the embodiment of the present application provides a process example of extracting real-time feedback data and information to be audited Figure 2 As shown in Figure 7 , the information scheduling device first extracts the push information 7-1, the real-time behavior data 7-2 corresponding to the push information, and the historical behavior data 7-3 of the push information. Then, the information scheduling device compares the historical behavior data corresponding to the push information with the historical data threshold 7-4, so as to select the historical data 7-31 greater than the historical data threshold 7-4 from the total historical behavior data 7-3. Then, the information scheduling device selects the information to be audited 7-11 corresponding to the historical data 7-31 from the push information 7-1. Finally, the information scheduling device selects the behavior data corresponding to the information to be audited 7-11 from the real-time behavior data according to the corresponding relationship between the push information and the real-time behavior data. These behavior data are the real-time feedback data 7-21.

[0199] In the embodiment of the present application, the information scheduling device can select the push information with greater influence in the historical time and faster spread according to the size relationship between the historical behavior data corresponding to the push information and the historical data threshold, so as to select the push information as the information to be audited, and then select the real-time feedback data corresponding to the information to be audited from the real-time behavior data, so as to facilitate subsequent auditing of the push information with greater influence in the historical time and faster spread.

[0200] Referring to Figure 8 , Figure 8 is an optional flowchart of the information scheduling method provided by the embodiment of the present application Figure 4 In some embodiments of the present application, after extracting the information to be audited from the push information, and extracting the real-time feedback data corresponding to the information to be audited from the real-time behavior data corresponding to the push information, and before determining the scheduling index corresponding to the information to be audited based on the real-time feedback data, that is, after S101 and before S102, the method further includes: S105, as follows:

[0201] S105, determining the index determination order of the information to be audited according to the publishing time of the information to be audited.

[0202] The index determination order indicates the order of determining the scheduling index corresponding to the information to be audited.

[0203] In practice, there are more information in the to-be-audited information that is likely to be more, and the information scheduling device will also determine the order of constructing the scheduling index for the to-be-audited information according to the publishing time of the to-be-audited information when constructing the scheduling index. At this time, the information scheduling device will acquire the publishing time of the to-be-audited information, and then sort the information in the to-be-audited information according to the publishing time, and the obtained sorting result is the index determination order of the to-be-audited information. Correspondingly, the process of the information scheduling device and the implementation of the feedback data to construct the scheduling index corresponding to the to-be-audited information, that is, the process of S102, will be changed to: determining the scheduling index corresponding to the to-be-audited information according to the index determination order and using the real-time feedback data. In this way, the scheduling index of the to-be-audited information published first can be constructed first under the condition of scheduling the to-be-audited information based on the abnormal influence degree, and then the to-be-audited information is audited and scheduled by using the scheduling index, so that the publishing time of the to-be-audited information can be considered during scheduling, and the time fairness of scheduling is improved.

[0204] In some embodiments of the present application, the information scheduling device can sort the to-be-audited information according to the principle of publishing time from front to back. In this way, the to-be-audited information can be audited in time as much as possible under the condition of auditing and scheduling according to the abnormal influence degree, so that the to-be-audited information is not accumulated, thereby improving the real-time performance of auditing abnormal information.

[0205] In another embodiment, the information scheduling device can also sort the to-be-audited information according to the principle of publishing time from back to front. In this way, the newly published problem pushing information can be audited as quickly as possible.

[0206] For example, the embodiment of the present application provides a process example diagram for determining the scheduling index, as shown in Figure 9 As shown in the figure, the information scheduling device obtains three to-be-audited information, namely to-be-audited information 9-1 published at 12:00, to-be-audited information 9-2 published at 13:06, and to-be-audited information 9-3 published at 10:58. The information scheduling device will sort the to-be-audited information 9-1, the to-be-audited information 9-2 and the to-be-audited information 9-3 according to the order of the publishing time, so as to obtain the to-be-audited order (index determination order): to-be-audited information 9-3, to-be-audited information 9-1, to-be-audited information 9-2. Finally, the information scheduling device will determine the scheduling index of the to-be-audited information according to the order.

[0207] In the embodiments of the present application, the information scheduling device can sort the index determination order of the to-be-audited information according to the publishing time of the to-be-audited information, and then determine the scheduling index of the to-be-audited information according to the index scheduling order, so that the publishing time of the to-be-audited information can be considered during scheduling, and the time fairness of scheduling can be improved.

[0208] In some embodiments of the present application, before determining the index weight corresponding to the to-be-audited information according to the real-time feedback data and the scheduling index calculation rule, that is, before S1021, the method can further include: S1023-S1027, as follows:

[0209] S1023, obtain at least one test audit information and at least one test feedback data corresponding to the at least one test audit information, and divide the at least one test audit information into at least two test information sets.

[0210] The embodiments of the present application are applied in the test phase, and select the best index calculation rule from a plurality of temporary index calculation rules. At this time, the information scheduling device will first obtain one or more published push information, and take these push information as test audit information, and obtain the feedback data corresponding to these test audit information. Then, the information scheduling device takes the obtained push information as test audit information, and takes the feedback data corresponding to the test audit information as test feedback data. In this way, the information scheduling device can obtain at least one test audit information and at least one test feedback data. Then, the information scheduling device will divide the at least one test audit information into different test information sets, that is, perform bucketing on the at least one test audit information. It should be noted that the temporary index calculation rule corresponding to each test information set is different, that is, each test information set has its own audit scheduling manner, so as to select the scheduling index calculation rule according to the scheduling effect of each test information set subsequently.

[0211] It can be understood that the test audit information can be specified published push information, for example, specified news, articles or videos, etc. The test audit information can also be any published push information, which is not limited in the present application.

[0212] It should be noted that the information scheduling device can randomly divide the test audit information into at least two test information sets, or divide the information in the test audit information located in the whitelist into the test information set corresponding to the whitelist, and divide the information located in the blacklist into the test information set corresponding to the blacklist.

[0213] In some embodiments of the present application, the at least two test information sets can further include a test information set scheduled according to time sequence, so that the scheduling effect of each temporary index calculation rule can be compared with the scheduling effect corresponding to time sequence, thereby judging the effect of the relative time sequence of each temporary index calculation rule.

[0214] S1024, according to the test feedback data corresponding to the test audit information in each test information set and the temporary index calculation rule corresponding to each test information set, calculating the test index weight corresponding to the test audit information in each test information set.

[0215] The information scheduling device respectively constructs the scheduling index of each test audit information in each test information set according to the temporary index calculation rule corresponding to each test information set, thereby obtaining the test weight index corresponding to each test audit information in each test information set.

[0216] It can be understood that the temporary index calculation rule corresponding to each test information set can be to construct the test index weight based on the information rejection rate and the click volume, or to determine the test index weight by focusing on the propagation factor, which is not limited in the present application.

[0217] S1025, using the test index weight to construct the test scheduling index corresponding to the test audit information in each test information set, and scheduling the test audit information in each test information set according to the order of the test scheduling index.

[0218] After obtaining the test index weight, the audit scheduling device uses the test index weight corresponding to each test audit information in each test information set to construct the corresponding test scheduling index for each test audit information in each test information set, and then schedules each test audit information in each test information set according to the obtained test scheduling index.

[0219] S1026, collecting the scheduling effect data of the test audit information in each test information set.

[0220] The scheduling effect data describes the scheduling effect of the test audit information in each test information set.

[0221] After the information scheduling device completes the audit scheduling of each test audit information in each test information set, the information scheduling device respectively acquires scheduling effect data corresponding to each test audit information in each test information set, so as to subsequently judge the scheduling effect of each test information set by using the scheduling effect data, and further judge the effect of the temporary index calculation rule corresponding to each test information set.

[0222] It can be understood that the scheduling effect data can include the click volume of the test audit information, and the time length during which the test audit information is published and audited. In this way, the information scheduling device can determine whether the test audit information with abnormal influence is audited in time. The scheduling effect data can also include effect data indicating whether the test audit information has bad influence, the click volume growth rate of the test audit information, and the user portrait with the most clicks on the test audit information. In this way, the information scheduling device can determine in which user portrait the test audit information is propagated faster.

[0223] S1027, according to the scheduling effect data, selecting the best scheduling index calculation rule from the temporary index calculation rules corresponding to each test information set.

[0224] The information scheduling device finally reads the scheduling effect data to determine the scheduling situation of each test audit information in each test information set, so as to select the best temporary index calculation rule from the temporary index calculation rules corresponding to each test information set as the final scheduling index calculation rule according to the scheduling situation of each test audit information, that is, whether each test audit information is audited in time.

[0225] In the embodiments of the present application, the information scheduling device can select a temporary index calculation rule with the best audit scheduling effect as the final scheduling index calculation rule according to the audit scheduling effects of the multiple temporary index calculation rules, so as to construct the scheduling index based on the scheduling index calculation rule with the best scheduling effect, thereby ensuring the effect of the audit scheduling.

[0226] In some embodiments of the present application, the specific implementation process of S1027, that is, selecting the best scheduling index calculation rule from the temporary index calculation rules corresponding to each test information set according to the scheduling effect data, can include S1027a-S1027b, as follows:

[0227] S1027a, determining the scheduling effect of each test information set according to the scheduling effect data.

[0228] S1027b, taking the temporary index calculation rule corresponding to the test information set with the best scheduling effect as the scheduling index calculation rule.

[0229] The information scheduling device first determines the scheduling effect of each test information set according to the effect scheduling data corresponding to each test audit information in each test information set, and then compares the scheduling effects of each test information set with each other to determine which test information set has the best scheduling effect. Then, the information scheduling device obtains the temporary index calculation rule corresponding to the test information set with the best scheduling effect, and uses the temporary index calculation rule as the scheduling index calculation rule for determining the scheduling index of the actual audit information.

[0230] In the embodiments of the present application, the information scheduling device can first determine the scheduling effect corresponding to each test information set according to the scheduling effect data, and then screen the scheduling index calculation rule according to the scheduling effect, so that the scheduling index calculation rule with the best scheduling effect can be understood to determine the scheduling index of the audit information.

[0231] In some embodiments of the present application, after determining the real-time scheduling order of the audit information by using the scheduling index corresponding to the audit information, and before scheduling the audit information according to the real-time scheduling order, that is, after S103 and before S104, the method can further include: S106, as follows:

[0232] S106, update the real-time scheduling order of the audit information based on the obtained latest feedback data corresponding to the audit information, to obtain an updated scheduling order.

[0233] After determining the real-time scheduling order, the information scheduling device can further obtain the latest user feedback corresponding to the audit information to obtain the latest feedback data corresponding to the audit information. Then, the information scheduling device determines the latest scheduling index corresponding to the audit information according to the scheduling index calculation rule using the latest feedback data, and then updates the real-time scheduling data based on the latest scheduling index to obtain an updated scheduling order. At this time, the specific implementation process of scheduling the audit information according to the real-time scheduling order, that is, S104, will correspondingly change to scheduling the audit information according to the updated scheduling order. In this way, the real-time update of the scheduling order corresponding to the audit information can be realized, so that the latest scheduling order can be used for audit scheduling.

[0234] In the embodiments of the present application, the information scheduling device can also update the real-time scheduling order corresponding to the audit information according to the latest feedback data, so that the latest real-time scheduling order can be used for subsequent audit scheduling, further improving the audit efficiency of abnormal push information.

[0235] In the following, an exemplary application of the embodiments of the present application in an actual application scenario will be described.

[0236] The embodiment of the present application is implemented in the scenario of auditing and scheduling subscription content according to user behavior data. Referring to FIG. 10(a), FIG. 10(a) is a process example diagram for auditing subscription content provided by the present application. The background 10-A (information scheduling device) continuously obtains subscription content (push information) recommended to the terminal 10-C of the user from different information sources 10-B. During browsing, the user also continuously generates feedback of different dimensions, which is user behavior data. The background 10-A collects the user behavior data (real-time behavior data). The background 10-A discovers that the subscription content hits the established review (audit) strategy, such as hot article review, feedback review, suspected low-quality, random inspection, etc., through real-time triggering or timing triggering, and then reviews the subscription content (to-be-audited information) that hits the review strategy. At this time, the subscription content that hits the review strategy is the submission content. The background 10-A calculates the priority data (scheduling index) of the submission content by using the determined priority algorithm (scheduling index calculation rule), and delivers the submission content to the audit personnel according to the priority order (real-time scheduling order) to perform scheduling and auditing. In addition, the background 10-A also continuously collects user behavior data (obtains the latest feedback data), such as negative feedback, comments, PV / VV, etc., so that the priority of the submission content is continuously updated (obtains the updated scheduling order) when the submission content is under review. After the audit personnel complete the review of the submission content and determine that the submission content needs to be taken down, the background 10-A takes down the submission content online, and sends a take-down prompt text “the content has been taken down” to the terminal 10-C when the user clicks the title or cover of the submission content on the terminal 10-C.

[0237] Before starting the review and scheduling, the background can also use online content to test the scheduling effect of each priority algorithm (temporary index calculation rule), so as to select the best priority algorithm and obtain the determined priority algorithm. FIG. 10(b) is a process example diagram for selecting a priority algorithm provided by the present application. Referring to FIG. 10(b), the process can be divided into:

[0238] S401, information recommendation; each recommendation side (information source) pushes subscription information (push information) to the user side.

[0239] S402, recommended information warehousing; each recommendation side sends the subscription information to the background, and the background stores the subscription information into the database.

[0240] S403, behavior data collection; the background collects real-time data (real-time behavior data) of the reaction of the user to the subscription information, such as comments, negative feedback, dwell time, PV / VV, etc., and stores these data into the database.

[0241] S404, extract the content for submission; the background pushes some content online to the submission pool according to the post-submission strategy. Further, the post-submission strategy mainly includes the following two types:

[0242] 1) Timing strategy (offline real-time order to get real-time data of users) (based on historical behavior data to filter information to be audited): the historical negative feedback amount of content is greater than a certain threshold, the historical report amount is greater than a certain threshold (the historical negative feedback amount and the historical report amount are collectively referred to as the historical negative feedback amount); the historical PV / VV growth rate (historical click growth rate) of the content is greater than a certain threshold (historical data threshold); the historical browsing time of the content is less than a certain threshold.

[0243] 2) Real-time strategy (based on real-time data to filter information to be audited): the real-time PV / VV (real-time click volume) of the content is greater than a certain threshold (real-time data threshold); the real-time comment amount of the content is greater than a certain threshold.

[0244] S405, bucketing.

[0245] The background distributes the content for submission to different content buckets (at least two test information sets) according to the established strategy (white list, random classification, etc.). The content bucket includes experiment bucket 1-experiment bucket i, and the control bucket (the control bucket is scheduled in chronological order), each experiment bucket is configured with a priority algorithm (temporary index calculation rule corresponding to each test information set).

[0246] S406, in-bucket sorting (not shown); the background uses the priority algorithm of the experiment bucket to which the content belongs to calculate the priority data (test scheduling index) of the content for submission in each bucket according to the content pool time sequence (the publication time of each information to be audited), and sorts the priority order in the bucket with the priority data.

[0247] S407, audit update (not shown); when the content for submission is in the experiment bucket, it will continuously obtain real-time priority and update its priority order in the bucket.

[0248] S408, order taking; the audit personnel obtain the content for submission from different content buckets according to the priority order, and review.

[0249] S409, data collection; the background collects the review data reported by the audit personnel and performs report analysis to select the best priority algorithm.

[0250] It should be noted that the review should meet these characteristics: idempotency, that is, the same content will only enter the same experimental barrel, and the experimental barrel scheduling of compatible content should always remain the same; real-time, real-time user behavior data should always be obtained, and real-time priority data should be given, and the priority scheduling order in the barrel should be updated; fairness, the priority data is calculated according to the order of content delivery (determined order).

[0251] In the foregoing manner, the background can effectively identify problem content (abnormal push information) in the submitted content that has a greater impact on the online, and limit processing of content that has a greater impact on the online, so that such content can be timely taken down, reducing the impact of such content on user experience online, and optimizing user experience.

[0252] The following continues to illustrate an exemplary structure of the information scheduling apparatus 255 provided by the embodiments of the present application as a software module. In some embodiments, as shown in FIG. 25, the software module stored in the information scheduling apparatus 255 of the memory 250 can include: Figure 2

[0253] A data extraction module 2551 is configured to extract, when receiving push information pushed to a user, to-be-audited information from the push information, and extract real-time feedback data corresponding to the to-be-audited information from real-time behavior data corresponding to the push information.

[0254] An index determination module 2552 is configured to determine a scheduling index corresponding to the to-be-audited information based on the real-time feedback data; the scheduling index represents an abnormal influence degree of the to-be-audited information.

[0255] A sequence determination module 2553 is configured to determine a real-time scheduling sequence of the to-be-audited information by using the scheduling index corresponding to the to-be-audited information.

[0256] An audit scheduling module 2554 is configured to perform audit scheduling on the to-be-audited information according to the real-time scheduling sequence.

[0257] In some embodiments of the present application, the index determination module 2552 is further configured to determine an index weight corresponding to the to-be-audited information according to the real-time feedback data and a scheduling index calculation rule; the index weight represents an abnormal degree of the to-be-audited information, and the scheduling index calculation rule is a temporary index calculation rule with the best scheduling effect selected from a plurality of temporary index calculation rules; the scheduling index corresponding to the to-be-audited information is calculated by using the index weight corresponding to the to-be-audited information.

[0258] In some embodiments of the present application, the real-time feedback data includes information rejection quantity, information publishing quantity, and click quantity. ​

[0259] The index determination module 2552 is further configured to obtain an information source rejection rate corresponding to the to-be-audited information by comparing the information rejection amount with the information publishing amount, wherein the information rejection amount represents a number of information of the information source corresponding to the to-be-audited information that is taken down, and the information publishing amount represents a total number of information published by the information source; and the index weight corresponding to the to-be-audited information is obtained by performing logarithmic operation on the information source rejection rate and the click volume according to the scheduling index calculation rule, wherein the click volume represents a number of times that the to-be-audited information is displayed.

[0260] In some embodiments of the present application, the real-time feedback data includes an information rejection amount, an information publishing amount, a click volume, and a click volume growth rate.

[0261] The index determination module 2552 is further configured to obtain an information source rejection rate corresponding to the to-be-audited information by comparing the information rejection amount with the information publishing amount; to obtain an adjusted information source rejection rate by performing weight adjustment on the information source rejection rate; and to obtain the index weight corresponding to the to-be-audited information by performing logarithmic operation on the adjusted information source rejection rate, the click volume, and the click volume growth rate according to the scheduling index calculation rule, wherein the click volume growth rate represents a growth rate of the click volume of the to-be-audited information.

[0262] In some embodiments of the present application, the index determination module 2552 is further configured to calculate a first index component by using the click volume and a preset weight construction parameter; to calculate a second index component by using the click volume growth rate and the preset weight construction parameter; to obtain an intermediate multiplication result corresponding to the to-be-audited information by multiplying the first index component, the second index component, and the adjusted information source rejection rate; and to obtain the index weight corresponding to the to-be-audited information by performing logarithmic operation on the intermediate multiplication result.

[0263] In some embodiments of the present application, the index determination module 2552 is further configured to perform weight reduction on the index weight corresponding to the to-be-audited information to obtain a weight-reduced index weight; and to calculate the scheduling index corresponding to the to-be-audited information by using the weight-reduced index weight.

[0264] In some embodiments of the present application, the data extraction module 2551 is further configured to select the real-time feedback data from real-time behavior data according to a comparison result of the real-time behavior data and a real-time data threshold, wherein the real-time behavior data is real-time data returned by a user for the push information, and the real-time behavior data includes at least one of a real-time click volume and a real-time comment volume; and to select the corresponding to-be-audited information from the push information by using the real-time feedback data.

[0265] In some embodiments of the present application, the data extraction module 2551 is further configured to compare the obtained historical behavior data corresponding to the push information with a historical data threshold to obtain a historical data comparison result, wherein the historical behavior data comprises at least one of a historical click volume, a historical negative feedback volume, a historical click growth rate, and a historical browsing time length; and filter out to-be-audited information from the push information according to the historical data comparison result; and filter out real-time feedback data corresponding to the to-be-audited information from the real-time behavior data.

[0266] In some embodiments of the present application, the sequence determination module 2553 is further configured to determine an index determination sequence of the to-be-audited information according to the obtained publishing time of the to-be-audited information, wherein the index determination sequence indicates an order of determining a scheduling index corresponding to the to-be-audited information.

[0267] Correspondingly, the index determination module 2552 is further configured to determine the scheduling index corresponding to the to-be-audited information by using the real-time feedback data according to the index determination sequence.

[0268] In some embodiments of the present application, the information scheduling apparatus 255 further comprises a rule selection module 2555.

[0269] In some embodiments of the present application, the data extraction module 2551 is further configured to obtain at least one test to-be-audited information and at least one test feedback data corresponding to the at least one test to-be-audited information, and divide the at least one test to-be-audited information into at least two test information sets.

[0270] The index determination module 2552 is further configured to calculate a test index weight corresponding to test to-be-audited information in each test information set according to test feedback data corresponding to the test to-be-audited information in the test information set and a temporary index calculation rule corresponding to the test information set, and construct a test scheduling index corresponding to the test to-be-audited information in each test information set by using the test index weight.

[0271] The audit scheduling module 2554 is further configured to perform audit scheduling on the test to-be-audited information in each test information set according to a sequence of the test scheduling index.

[0272] The rule selection module 2555 is further configured to collect scheduling effect data of the test audit information in each test information set, wherein the scheduling effect data describes the scheduling situation of the test audit information in each test information set; and select the scheduling index calculation rule with the best effect from the temporary index calculation rules corresponding to each test information set according to the scheduling effect data.

[0273] In some embodiments of the present application, the rule selection module 2555 is further configured to determine the scheduling effect corresponding to each test information set according to the scheduling effect data; and select the temporary index calculation rule corresponding to the test information set with the best scheduling effect as the scheduling index calculation rule.

[0274] In some embodiments of the present application, the sequence determination module 2553 is further configured to update the real-time scheduling sequence of the to-be-audited information based on the obtained latest feedback data corresponding to the to-be-audited information, to obtain an updated scheduling sequence.

[0275] Correspondingly, the audit scheduling module 2554 is further configured to perform audit scheduling on the to-be-audited information according to the updated scheduling sequence.

[0276] The embodiment of the present application provides a computer program product or a computer program, which comprises computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the information scheduling method provided in the embodiment of the present application.

[0277] The embodiment of the present application provides a computer readable storage medium storing executable instructions, wherein the executable information scheduling instructions are stored. When the executable instructions are executed by a processor, the processor will execute the information scheduling method provided in the embodiment of the present application, for example, the method shown in Figure 3 、 Figure 4 、 Figure 5 、 Figure 8 .

[0278] In some embodiments, the computer readable storage medium can be FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disc, or CD-ROM memory; or various devices comprising one or any combination of the above memories.

[0279] In some embodiments, the executable information scheduling instructions can take the form of a program, software, software modules, scripts, or code, written in any form of programming language, including compiled or interpreted languages, or declarative or procedural languages, and they can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0280] By way of example, the executable information scheduling instructions can, but need not necessarily, correspond to a file in a file system, can be stored in a portion of a file that holds other programs or data, for example, one or more scripts stored in a markup language document, in a single file dedicated to the program in question, or in multiple coordinated files, for example, files that store one or more modules, sub programs, or portions of code.

[0281] By way of example, the executable information scheduling instructions can be deployed to be executed on one computer, or on multiple computers located at one site, or distributed across multiple sites and interconnected by a communication network.

[0282] The above description is only for the embodiments of the present application, and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, and improvement within the spirit and scope of the present application shall be included in the protection scope of the present application.

Claims

1. An information scheduling method characterized by comprising: The method comprises the following steps: When receiving the push information pushed to the user, extracting the to-be-audited information from the push information, and extracting the real-time feedback data corresponding to the to-be-audited information from the real-time behavior data corresponding to the push information; When the form of the scheduling index is an abnormal influence score, in the case that the real-time feedback data comprises information rejection quantity, information publishing quantity and click quantity, comparing the information rejection quantity and the information publishing quantity to obtain an information source rejection rate corresponding to the to-be-audited information; according to a scheduling index calculation rule, performing logarithmic operation on the information source rejection rate and the click quantity to obtain an index weight corresponding to the to-be-audited information; or, In the case that the real-time feedback data comprises the information rejection quantity, the information publishing quantity, the click quantity and click quantity growth rate, comparing the information rejection quantity and the information publishing quantity to obtain the information source rejection rate; performing weight adjustment on the information source rejection rate to obtain an adjusted information source rejection rate; according to the scheduling index calculation rule, performing logarithmic operation on the adjusted information source rejection rate, the click quantity and the click quantity growth rate to obtain the index weight corresponding to the to-be-audited information; The scheduling index calculation rule is a temporary index calculation rule for timely auditing test auditing information, which is selected from a plurality of temporary index calculation rules according to scheduling effect data, and the scheduling effect data comprises at least one of the following: the click quantity of the test auditing information, and a time length from publishing to auditing of the test auditing information; The index weight corresponding to the to-be-audited information is used to calculate the scheduling index corresponding to the to-be-audited information; the scheduling index represents the abnormal influence degree of the to-be-audited information; The scheduling index corresponding to the to-be-audited information is used to determine a real-time scheduling sequence of the to-be-audited information; The to-be-audited information is audited and scheduled according to the real-time scheduling sequence.

2. The method of claim 1, wherein: The information rejection quantity represents the number of information of the information source corresponding to the to-be-audited information that is taken down, and the information publishing quantity represents the total number of information published by the information source; The click quantity represents the number of times that the to-be-audited information is displayed.

3. The method of claim 1, wherein: The click quantity growth rate represents the growth rate of the click quantity of the to-be-audited information.

4. The method of claim 1, wherein, The logarithmic operation on the adjusted information source rejection rate, the click quantity and the click quantity growth rate to obtain the index weight corresponding to the to-be-audited information comprises: A first index component is calculated by using the click quantity and a preset weight construction parameter; A second index component is calculated by using the click quantity growth rate and the preset weight construction parameter; The first index component, the second index component and the adjusted information source rejection rate are multiplied to obtain an intermediate multiplication result corresponding to the to-be-audited information; The intermediate multiplication result is logarithmically operated to obtain the index weight corresponding to the to-be-audited information.

5. The method according to claim 1, characterized in that The method further comprises: The method further comprises: The method further comprises:

6. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: The method further comprises: The method further comprises: The method further comprises:

7. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: The method further comprises: The method further comprises: The method further comprises:

8. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: The method further comprises: The method further comprises: The method further comprises:

9. The method of claim 1, wherein, The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further The test scheduling index corresponding to the test audit information in each test information set is constructed by using the test index weight, and the test audit information in each test information set is audited and scheduled according to the order of the test scheduling index. The scheduling effect data of the test audit information in each test information set is collected, and the scheduling effect data describes the test audit information auditing scheduling in each test information set. The best scheduling index calculation rule is selected from the temporary index calculation rules corresponding to each test information set according to the scheduling effect data.

10. The method of claim 9, wherein, The best scheduling index calculation rule is selected from the temporary index calculation rules corresponding to each test information set according to the scheduling effect data. The scheduling effect of each test information set is determined according to the scheduling effect data. The temporary index calculation rule corresponding to the test information set with the best scheduling effect is selected as the scheduling index calculation rule.

11. The method according to any one of claims 1 to 5, 9 or 10, characterized in that, After the real-time scheduling order of the to-be-audited information is determined by using the scheduling index corresponding to the to-be-audited information, and before the to-be-audited information is audited and scheduled according to the real-time scheduling order, the method further comprises: Based on the obtained latest feedback data corresponding to the to-be-audited information, the real-time scheduling order of the to-be-audited information is updated to obtain an updated scheduling order. Correspondingly, the to-be-audited information is audited and scheduled according to the real-time scheduling order, comprising: The to-be-audited information is audited and scheduled according to the updated scheduling order.

12. An information scheduling apparatus characterized by comprising: Comprise: The data extraction module is used to extract the to-be-audited information from the push information when receiving the push information pushed to the user, and extract the real-time feedback data corresponding to the to-be-audited information from the real-time behavior data corresponding to the push information; When the form of the scheduling index is the abnormal influence score, the information source rejection rate corresponding to the to-be-audited information is obtained by comparing the information rejection amount and the information publishing amount in the case that the real-time feedback data includes the information rejection amount, the information publishing amount and the click amount. According to the scheduling index calculation rule, the information source rejection rate and the click volume are logarithmically operated to obtain the index weight corresponding to the to-be-audited information; or, in the case that the real-time feedback data includes the information rejection volume, the information publishing volume, the click volume and the click volume growth rate, the information rejection volume is compared with the information publishing volume to obtain the information source rejection rate; the information source rejection rate is adjusted in weight to obtain an adjusted information source rejection rate; according to the scheduling index calculation rule, the adjusted information source rejection rate, the click volume and the click volume growth rate are logarithmically operated to obtain the index weight corresponding to the to-be-audited information; wherein the scheduling index calculation rule is a temporary index calculation rule for timely auditing test auditing information, which is selected from a plurality of temporary index calculation rules according to scheduling effect data; the scheduling effect data includes at least one of the following: the click volume of the test auditing information, and the time length from publishing to auditing of the test auditing information; the scheduling index corresponding to the to-be-audited information is calculated by using the index weight corresponding to the to-be-audited information; and the scheduling index represents the abnormal influence degree of the to-be-audited information. The sequence determination module is configured to determine the real-time scheduling sequence of the to-be-audited information by using the scheduling index corresponding to the to-be-audited information. The auditing scheduling module is configured to perform auditing scheduling on the to-be-audited information according to the real-time scheduling sequence.

13. The apparatus of claim 12, wherein: The information rejection volume represents the number of information of the to-be-audited information corresponding to the information source that is delisted, and the information publishing volume represents the total number of information published by the information source. The click volume represents the number of times of display of the to-be-audited information.

14. The apparatus of claim 12, wherein: The click volume growth rate represents the growth speed of the click volume of the to-be-audited information.

15. The apparatus of claim 12, wherein: The index determination module is further configured to calculate a first index component by using the click volume and a preset weight construction parameter, and calculate a second index component by using the click volume growth rate and the preset weight construction parameter. The first index component, the second index component and the adjusted information source rejection rate are multiplied to obtain an intermediate multiplication result corresponding to the to-be-audited information; and the intermediate multiplication result is logarithmically operated to obtain the index weight corresponding to the to-be-audited information.

16. An information scheduling apparatus characterized by comprising: The memory is configured to store executable information scheduling instructions. The processor is configured to execute the executable information scheduling instructions stored in the memory to implement the method in any one of claims 1 to 11. The memory stores executable information scheduling instructions for being executed by the processor to implement the method in any one of claims 1 to 11.

17. A computer-readable storage medium, characterized in that, The computer instructions are executed by the processor to implement the method in any one of claims 1 to 11.

18. A computer program product comprising computer instructions, characterized in that, ​

Images