Service content digital management system and operation method based on data processing

Abstract

The present application provides a service content digital management system and operation method based on data processing, which relates to the field of data processing technology. The method includes: consuming messages to receive service content feedback data, executing pre-recall classification, and sending review tasks; consuming messages to receive review tasks and generating review results; performing callback management according to the review results, extracting source information of service content feedback data according to the callback results, and functionally identifying the source information; monitoring service content feedback data according to the functional identification results, and generating a quick management plan. This application can solve the technical problem in the prior art that the poor perfection of the review link of service content feedback data leads to increased content risks and further affects the stability of the system, and achieves the technical goal of improving the perfection of the review link, and achieves the technical effect of reducing content risks.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a service content digital management system and an operation method based on data processing. Background Art

[0002] The service content can be used to support users to customize and generate content, display content to the public by uploading service content, and then process the content generated by platform users, combat risks of illegal content generated by users, solve various content security issues, ensure the security of online content, and promptly discover and resolve risks.

[0003] At present, the existing review chain of service content feedback data is poorly developed and cannot effectively identify and handle risky content, resulting in the release of inappropriate, illegal or even illegal content, bringing legal risks and possibly damaging the interests of users.

[0004] In summary, the prior art has a technical problem in which the review link for service content feedback data is poorly completed, which increases content risks and further affects system stability. Summary of the invention

[0005] The purpose of this application is to provide a service content digital management system and operation method based on data processing, so as to solve the technical problem in the prior art that the review link of service content feedback data is poorly perfected, resulting in increased content risks and further affecting system stability.

[0006] In view of the above problems, the present application provides a service content digital management system and operation method based on data processing.

[0007] In the first aspect, the present application provides a service content digital management system based on data processing, wherein the system includes: a message management module, the message management module is used to consume messages to receive service content feedback data, perform pre-recall classification, and send review tasks; an review module, the review module is used to consume messages to receive the review tasks, and generate review results; a callback management module, the callback management module is used to perform callback management according to the review results, extract source information of the service content feedback data according to the callback results, and functionally identify the source information; a monitoring module, the monitoring module is used to monitor the service content feedback data according to the functional identification results, and generate a quick management plan.

[0008] On the second aspect, the present application provides a service content digital management operation method based on data processing, which is implemented through a service content digital management system based on data processing, wherein the method includes: consuming messages to receive service content feedback data, executing pre-recall classification, and sending review tasks; consuming messages to receive the review tasks and generating review results; performing callback management based on the review results, extracting source information of the service content feedback data based on the callback results, and functionally identifying the source information; monitoring the service content feedback data based on the functional identification results and generating a quick management plan.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] Receive service content feedback data through consumption messages, perform pre-recall classification, and send review tasks; receive the review tasks through consumption messages and generate review results; perform callback management based on the review results, extract source information of the service content feedback data based on the callback results, and perform functional identification on the source information; monitor the service content feedback data based on the functional identification results, generate a rapid management plan, achieve the technical goal of improving the perfection of the review link, and achieve the technical effect of reducing content risks.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 This is a schematic diagram of the structure of the service content digital management system based on data processing for this application;

[0014] Figure 2 This is a flowchart of the service content digital management operation method based on data processing in this application.

[0015] Description of reference numerals:

[0016] Message management module 11, audit module 12, callback management module 13, monitoring module 14. DETAILED DESCRIPTION

[0017] This application solves the technical problem in the prior art that the review link of service content feedback data is poorly perfected, which leads to increased content risk and further affects the stability of the system by providing a service content digital management system and operation method based on data processing. It achieves the technical goal of improving the perfection of the review link and achieves the technical effect of reducing content risk.

[0018] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0019] Embodiment 1

[0020] This application provides a service content digital management system based on data processing, which has the same inventive concept as the service content digital management operation method based on data processing, please refer to the attached Figure 1 , the system comprising:

[0021] A message management module 11, which is used to consume message reception service content feedback data, perform pre-recall classification, and send review tasks;

[0022] An audit module 12, the audit module 12 is used to consume the message to receive the audit task and generate an audit result;

[0023] A callback management module 13, the callback management module 13 is used to perform callback management according to the review result, extract source information of the service content feedback data according to the callback result, and perform function identification on the source information;

[0024] The monitoring module 14 is used to monitor the service content feedback data according to the function identification result and generate a quick management solution.

[0025] Further, the message management module 11 in the system is also used for:

[0026] Build a pre-recall classification model, train it based on sample service content feedback data, and obtain sample pre-recall classification results, including sample black tasks, sample white tasks, and sample gray tasks;

[0027] Input the pre-recall classification model into the service content feedback data for analysis to obtain a pre-recall classification result;

[0028] Among them, based on the previous recall classification results, black tasks are extracted for punishment and management, white tasks are extracted for release, and gray tasks are extracted for task review.

[0029] Further, the message management module 11 in the system is also used for:

[0030] Generate an audit queue based on the gray task, determine whether there is a task drop, and determine the task volume based on the drop determination result;

[0031] Adjust the message consumption priority based on the task volume and configure message consumption limit;

[0032] The queue interruption processing is performed based on the drop judgment result.

[0033] Further, the message management module 11 in the system is also used for:

[0034] Slicing the service content feedback data to generate picture frame data and audio slice data;

[0035] Message consumption is performed on the picture frame data and the audio slice data, triggering a review instruction;

[0036] Perform scene management according to the review instructions and generate feedback scene information, including new scene registration, scene information modification, and scene screening;

[0037] The audit task is generated by combining the picture frame data and the audio slice data with the feedback scene information, and the audit module is connected to transmit the audit task.

[0038] Furthermore, the audit module 12 in the system is also used for:

[0039] Extract feedback types based on sample service content feedback data, generate sample feedback type indicators and sample feedback type indicator responses, and construct a sample feedback type form;

[0040] A matching degree is calculated based on the sample feedback type form and the service content feedback data, matching feedback type indicators and matching feedback type indicator responses that meet a matching degree threshold are extracted, and the review result is generated.

[0041] Furthermore, the audit module 12 in the system is also used for:

[0042] Pre-building a dual-channel network based on a convolutional neural network, including a first channel and a second channel, wherein the first channel and the second channel respectively have word embedding models;

[0043] Extracting stems from the service content feedback data, inputting the stems into the first channel, converting the input stems into word vector sequences according to the word embedding model in the first channel, and generating a vector representation of the service content feedback data;

[0044] Call the sample feedback type form to input the second channel, convert the word embedding model in the second channel into a word vector sequence, and generate a sample feedback type vector representation;

[0045] Based on the matching network connected by the dual-channel network, the service content feedback data vector representation and the sample feedback type vector representation are input into the matching network for matching measurement to obtain a cosine similarity value;

[0046] A matching degree threshold is extracted, and a satisfaction judgment is performed based on the cosine similarity value and the matching degree threshold, so as to obtain the satisfied matching feedback type indicator and the matching feedback type indicator response.

[0047] Furthermore, the callback management module 13 in the system is also used for:

[0048] If the review result meets the risk service threshold, execute the service callback and cache the risk service result;

[0049] Service content risk identification and service content feedback data shielding are performed based on the risk service result.

[0050] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The service content digital management operation method based on data processing and the specific examples in the embodiment are also applicable to the service content digital management system based on data processing in this embodiment. Through the detailed description of the service content digital management operation method based on data processing, those skilled in the art can clearly understand the service content digital management system based on data processing in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0051] Embodiment 2

[0052] Please refer to the attached Figure 1 The present application provides a service content digital management operation method based on data processing, wherein the method is applied to a service content digital management system based on data processing, and the method specifically comprises the following steps:

[0053] Step 1: Consume messages to receive service content feedback data, perform pre-recall classification, and send review tasks.

[0054] Specifically, service content feedback data is received and processed based on the message queue. Service type feedback data refers to data generated by user feedback on service content. For example, service content feedback data includes feedback data generated in the form of text messages, such as comments, complaints, suggestions, etc. According to preset rules or machine learning models, the received feedback data is preliminarily classified, such as data to be punished, released, task reviewed, etc. The service content feedback data to be reviewed is sent for task review.

[0055] Step 2: Consume the message to receive the review task and generate the review result.

[0056] Specifically, based on the audit tasks stored in the message queue, the corresponding service content feedback data is obtained, the service content feedback data is audited according to the preset audit rules or algorithms, and the audit results are generated.

[0057] Step three: performing callback management according to the review result, extracting source information of the service content feedback data according to the callback result, and performing function identification on the source information.

[0058] Specifically, when the review results are generated, callback management is performed based on the review results, multiple services are called, and further feedback or instructions are obtained. Based on the callback results, source information is extracted from the service content feedback data. The source information may include the source channel of the data, the uploading user, the timestamp, etc. The service content feedback data is parsed, the required source information is extracted, and it is associated with the review results. The extracted source information is functionally identified. The functional identification may include the type of data, importance, processing priority, etc.

[0059] Step 4: Monitor the service content feedback data according to the function identification results and generate a quick management plan.

[0060] Specifically, the service content feedback data is monitored according to the function identification results. This may include real-time monitoring, periodic scanning, anomaly detection, etc. According to the priority and processing requirements in the function identification, the service content feedback data is monitored and managed at different levels. For high-risk or important data, real-time tracking and processing may be required. Based on the monitoring results and business needs, a quick management plan is generated.

[0061] The service content digital management operation method based on data processing is applied to the service content digital management system based on data processing, which can achieve the technical goal of improving the perfection of the review link and achieve the technical effect of reducing content risks.

[0062] Furthermore, the present application also includes:

[0063] Construct a pre-recall classification model, train it based on sample service content feedback data, and obtain sample pre-recall classification results, including sample black tasks, sample white tasks, and sample gray tasks; input the pre-recall classification model based on the service content feedback data for analysis to obtain pre-recall classification results; wherein, based on the pre-recall classification results, extract black tasks for punishment and management, extract white tasks for release and approval, and extract gray tasks for task review.

[0064] Specifically, collect service content feedback data from historical time periods as training samples to ensure that the sample data is sufficiently diverse and representative. Label the sample data to clarify the classification of each sample into sample black tasks, sample white tasks, and sample gray tasks. Select learning models such as logistic regression, random forest, support vector machine, and neural network according to the characteristics of the task and the characteristics of the data to build a pre-recall classification model. Use the labeled sample data to train the model, and optimize the performance of the pre-recall classification model by adjusting the parameters and hyperparameters of the pre-recall classification model.

[0065] Then, the received service content feedback data is input into the pre-recall classification model, and the service content feedback data is analyzed to determine the specific classification of the service content feedback data among black tasks, white tasks, and gray tasks, so as to obtain the pre-recall classification result.

[0066] Furthermore, for output data classified as black tasks, punishment management is carried out, such as banning accounts, restricting functions, etc. For output data classified as white tasks, it is directly released without further review. For output data classified as gray tasks, task review is performed to conduct detailed review and judgment of samples through manual or automatic methods.

[0067] By building a pre-recall classification model, the accuracy of classified service content feedback data can be improved, and the efficiency of processing service type feedback data can be improved.

[0068] Furthermore, the present application also includes:

[0069] Generate an audit queue based on the gray task, determine whether there is a task drop, and determine the task volume based on the drop determination result; adjust the message consumption priority based on the task volume, and configure message consumption flow control; and execute queue interruption processing based on the drop determination result.

[0070] Specifically, when the service content feedback data is judged as a gray task by the pre-recall classification model, it will be added to the review queue and await further review processing. Task drop usually refers to the task waiting in the queue for too long, exceeding the preset threshold, or the task being accidentally discarded due to system errors, service crashes, etc. Monitor the status of the review queue in real time, including queue length, task waiting time, etc. When the waiting time of a task exceeds the preset threshold or it is detected that a task is accidentally discarded, it is judged as a task drop. Task volume refers to the number of gray tasks currently awaiting review and possible growth trends. If task drops occur frequently and the length of the review queue continues to grow, it means that the current task volume is too large, and it may be necessary to increase review resources or adjust the review strategy.

[0071] Then, the message consumption priority determines the order in which the messages are processed in the consumption queue. Messages with high priority will be processed first, and vice versa. When the task volume is large, the consumption priority of gray tasks can be increased to ensure that important or urgent tasks can be processed first, or the consumption priority of other types of tasks can be lowered to free up more resources to process gray tasks. Message consumption flow limiting is to control the consumption speed of messages to prevent system overload or crash due to excessive message consumption. Set a reasonable message consumption rate limit based on the system's processing capacity and the current task volume. When the task volume is large, the consumption rate limit can be appropriately lowered to ensure the stable operation of the system.

[0072] Next, queue-jumping processing is to take a specific task out of the normal review queue and directly insert it to the front of the queue so that it can be processed first. When a task is detected to be dropped, the reason for the drop can be analyzed. If it is because a specific task such as a high-priority task or an urgent task has been waiting for a long time without being processed, queue-jumping processing can be performed to ensure that the queue-jumping task can be processed first.

[0073] By achieving effective management of gray tasks, important or urgent tasks can be given priority while avoiding system overload or crash.

[0074] Furthermore, the present application also includes:

[0075] The service content feedback data is sliced ​​to generate picture frame data and audio slice data; the picture frame data and audio slice data are consumed as messages to trigger a review instruction; scene management is performed according to the review instruction to generate feedback scene information, including new scene registration, scene information modification, and scene screening; the review task is generated by combining the picture frame data and audio slice data with the feedback scene information, and the review module is connected to transmit the review task.

[0076] Specifically, for service content feedback data containing video, a video processing tool or library is used to extract frames and key frames as image data. For service content feedback data containing audio, an audio processing tool or library is used to slice and extract audio segments.

[0077] Then, the picture frame data and the audio slice data are input into the message queue as messages. The message queue is monitored, and once new picture frame data or audio slice data is received, a review instruction is triggered.

[0078] Next, when a new feedback scenario is identified, the new scenario information is registered in the scenario management system, including the scenario name, description, related rules, etc. The existing scenario information is modified to adapt to business changes or rule updates. According to business needs or audit policies, the feedback scenarios that need to be processed are screened.

[0079] Next, combine the image frame data, audio slice data and the filtered feedback scene information to generate a specific audit task. Send the generated audit task to the audit module. Ensure that the audit task can be reliably transmitted to the audit module, and perform retries or error handling when necessary.

[0080] By generating audit tasks, the efficiency of audit service content feedback data can be improved.

[0081] Furthermore, the present application also includes:

[0082] Feedback type extraction is performed based on sample service content feedback data, sample feedback type indicators and sample feedback type indicator responses are generated, and a sample feedback type form is constructed; a matching degree calculation is performed based on the sample feedback type form and the service content feedback data, matching feedback type indicators and matching feedback type indicator responses that meet a matching degree threshold are extracted, and the review result is generated.

[0083] Specifically, historical service content feedback data is collected as sample service content feedback data. Text analysis or classification processing is performed on the sample data to extract different feedback types, such as positive feedback, negative feedback, function suggestions, fault reports, etc., as sample feedback type indicators. According to the sample feedback type indicators, indicator data is extracted from the sample service content feedback data as sample feedback type indicator responses. Based on the extracted sample feedback type indicators and sample feedback type indicator responses, a sample feedback type form is constructed.

[0084] Then, design a machine learning classification and other matching algorithms to calculate the matching between the sample feedback type form and the service content feedback data. Set the matching threshold based on business needs or experience. Based on the matching calculation results, extract the feedback type indicators and feedback type indicator responses that meet the matching threshold from the service content feedback data as matching feedback type indicators and matching feedback type responses. Integrate the extracted matching feedback type indicators and matching feedback type indicators into the review results.

[0085] By matching sample feedback type forms with service content feedback data, the accuracy of review results can be improved.

[0086] Furthermore, the present application also includes:

[0087] A dual-channel network is pre-built based on a convolutional neural network, including a first channel and a second channel, wherein the first channel and the second channel respectively have a word embedding model; the service content feedback data is subjected to word stem extraction and input into the first channel, and the input word stem is converted into a word vector sequence according to the word embedding model in the first channel to generate a service content feedback data vector representation; the sample feedback type form is called and input into the second channel, and the word vector sequence is converted into a sample feedback type vector representation according to the word embedding model in the second channel; based on a matching network connected by the dual-channel network, the service content feedback data vector representation and the sample feedback type vector representation are input into the matching network for matching measurement to obtain a cosine similarity value; a matching threshold is extracted, and a satisfaction judgment is performed based on the cosine similarity value and the matching threshold to obtain a satisfied matching feedback type indicator and a matching feedback type indicator response.

[0088] Specifically, a dual-channel network is pre-built based on a convolutional neural network, including a first channel and a second channel, wherein the first channel and the second channel respectively have a word embedding model, and the first channel is used to process service content feedback data. The second channel is used to process a sample feedback type form. Both the first channel and the second channel contain a word embedding model for converting text data into a numerical vector.

[0089] Then, the service content feedback data is extracted from the stems. The stems extracted from the service content feedback data are input into the word embedding model of the first channel and converted into a word vector sequence. The word vector sequence output from the first channel is combined into an overall vector representation of the service content feedback data as the vector representation of the service content feedback data.

[0090] Next, a sample feedback type form is obtained. The text in the sample feedback type form is input into the word embedding model of the second channel, and the output is converted into a word vector sequence, which is combined into an overall vector representation of the sample feedback type as the sample feedback type vector representation.

[0091] Next, a matching network is connected based on a dual-channel network to compare the similarity of the two vector representations. The service content feedback data vector representation and the sample feedback type vector representation are input into the matching network to calculate the cosine similarity value between the two.

[0092] Then, a matching threshold is set to obtain the service content feedback data that best matches the sample feedback type indicator. Based on the comparison between the cosine similarity value and the matching threshold, it is determined whether there is a matching feedback type indicator and a matching feedback type indicator response that meet the conditions. If the matching threshold is met, the service content feedback data that meets the conditions is obtained as the matching feedback type indicator and the matching feedback type indicator response.

[0093] Through similarity matching, the processing efficiency of service content feedback data can be improved.

[0094] Furthermore, the present application also includes:

[0095] If the review result meets the risk service threshold, a service callback is executed and the risk service result is cached; based on the risk service result, a service content risk identification and service content feedback data shielding are executed.

[0096] Specifically, service callback is a mechanism that triggers the call to a service when a certain event or condition is met. When the review result meets the risk service threshold, the service callback is triggered. For example, the service callback includes calling a risk processing service or API to notify the relevant system or personnel of the existence of the risk. The result of the service callback, that is, the risk service result, is cached in the database or other storage medium to improve the efficiency of subsequent query and processing, and to facilitate the recording and tracking of risk events.

[0097] Then, based on the cached risk service results, service content such as user feedback, comments, and posts are marked as risky by adding tags next to the service content, changing the display of the content, or moving the content to a specific area. Based on the risk service results, the service content feedback data is shielded. The specific shielding method depends on the nature of the data and the needs of the system. For example, comments containing sensitive information can be deleted, feedback data can be made invisible, or the data can be moved to an isolated area for administrator review to protect user privacy, prevent information leakage, and reduce potential risks.

[0098] By performing risk detection on service content feedback data, the efficiency of processing service content feedback data can be improved.

[0099] In summary, the service content digital management operation method based on data processing provided by this application has the following technical effects:

[0100] Receive service content feedback data through consumption messages, perform pre-recall classification, and send review tasks; receive the review tasks through consumption messages and generate review results; perform callback management based on the review results, extract source information of the service content feedback data based on the callback results, and perform functional identification on the source information; monitor the service content feedback data based on the functional identification results, generate a rapid management plan, achieve the technical goal of improving the perfection of the review link, and achieve the technical effect of reducing content risks.

[0101] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0102] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A digital management system for service content based on data processing, characterized in that: The system comprises: A message management module, which is used to consume message reception service content feedback data, perform pre-recall classification, and send review tasks; An audit module, which is used to consume messages to receive the audit tasks and generate audit results; A callback management module, the callback management module is used to perform callback management according to the review result, extract source information of the service content feedback data according to the callback result, and perform function identification on the source information; A monitoring module, the monitoring module is used to monitor the service content feedback data according to the function identification result and generate a rapid management plan; The review results are generated, including: Extract feedback types based on sample service content feedback data, generate sample feedback type indicators and sample feedback type indicator responses, and construct a sample feedback type form; Calculate the matching degree between the sample feedback type form and the service content feedback data, extract matching feedback type indicators and matching feedback type indicator responses that meet the matching degree threshold, and generate the review result; The matching degree calculation is performed based on the sample feedback type form and the service content feedback data, and the matching feedback type indicator and the matching feedback type indicator response that meet the matching degree threshold are extracted, including: Pre-building a dual-channel network based on a convolutional neural network, including a first channel and a second channel, wherein the first channel and the second channel respectively have word embedding models; Extracting stems from the service content feedback data, inputting the stems into the first channel, converting the input stems into word vector sequences according to the word embedding model in the first channel, and generating a vector representation of the service content feedback data; Call the sample feedback type form to input the second channel, convert the word embedding model in the second channel into a word vector sequence, and generate a sample feedback type vector representation; Based on the matching network connected by the dual-channel network, the service content feedback data vector representation and the sample feedback type vector representation are input into the matching network for matching measurement to obtain a cosine similarity value; A matching degree threshold is extracted, and a satisfaction judgment is performed based on the cosine similarity value and the matching degree threshold, so as to obtain the satisfied matching feedback type indicator and the matching feedback type indicator response.

2. The system according to claim 1, characterized in that Perform pre-recall classification, including: Build a pre-recall classification model, train it based on sample service content feedback data, and obtain sample pre-recall classification results, including sample black tasks, sample white tasks, and sample gray tasks; Input the pre-recall classification model into the service content feedback data for analysis to obtain a pre-recall classification result; Among them, based on the previous recall classification results, black tasks are extracted for punishment and management, white tasks are extracted for release, and gray tasks are extracted for task review.

3. The system according to claim 2, characterized in that The system further comprises: Generate an audit queue based on the gray task, determine whether there is a task drop, and determine the task volume based on the drop determination result; Adjust the message consumption priority based on the task volume and configure message consumption limit; The queue interruption processing is performed based on the drop judgment result.

4. The system according to claim 1, characterized in that Send review tasks, which previously included: Slicing the service content feedback data to generate picture frame data and audio slice data; Message consumption is performed on the picture frame data and the audio slice data, triggering a review instruction; Perform scene management according to the review instructions and generate feedback scene information, including new scene registration, scene information modification, and scene screening; The audit task is generated by combining the picture frame data and the audio slice data with the feedback scene information, and the audit module is connected to transmit the audit task.

5. The system according to claim 1, wherein: Callback management is performed based on the review results, including: If the review result meets the risk service threshold, execute the service callback and cache the risk service result; Service content risk identification and service content feedback data shielding are performed based on the risk service result.

6. A service content digital management operation method based on data processing, characterized in that: The method is implemented by the service content digital management system based on data processing according to any one of claims 1 to 5, and the method comprises: Consumer messages receive service content feedback data, perform pre-recall classification, and send review tasks; Consume the message to receive the audit task and generate the audit result; Perform callback management according to the review result, extract source information of the service content feedback data according to the callback result, and perform function identification on the source information; The service content feedback data is monitored according to the function identification results to generate a quick management plan.

Images