Data audit method, device, computer equipment and storage medium thereof

Abstract

This application relates to the field of artificial intelligence technology, and more particularly to a data audit method, apparatus, computer device, and storage medium thereof. The method comprises: determining an audit level for received interactive data; determining an audit process corresponding to the interactive data based on the audit level; and performing audit processing on the interactive data based on the audit process. This application enables rapid auditing of interactive data, reduces the difficulty of auditing interactive data, improves the efficiency of auditing interactive data, reduces unnecessary audit processes during the audit of interactive data, and ensures the timeliness of interactive data.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a data audit method, apparatus, computer equipment, and storage medium thereof. Background Art

[0002] With the rapid development of network technology, promoting information through applications such as live video streaming has become a widely used interactive promotional method across various industries. As the number of people participating in and watching live video streaming increases, the amount of interactive data related to live video streaming (such as comments, messages, and comments) is also increasing. As the amount of interactive data continues to increase and the content of this interactive data continues to enrich, the review of this interactive data becomes increasingly important.

[0003] In the existing technology, when a user sends interactive data for a live video broadcast, it is necessary to perform keyword matching on the interactive data based on a pre-set illegal keyword library to determine whether the characters in the interactive data are the same as those in the keyword library. If the interactive data does not contain the same characters as those in the illegal keyword library, the interactive data will be publicly displayed.

[0004] Since the existing audit method has low audit efficiency, it takes a lot of time when the amount of interactive data that needs to be audited is large. Since during the live video broadcast, the interactive data will only be publicly displayed after passing the audit, the existing audit method will make it difficult to ensure the real-time display of the interactive data. Summary of the Invention

[0005] Based on this, it is necessary to provide a data audit method, device, computer equipment and storage medium thereof that can realize rapid audit of interactive data in response to the above technical problems.

[0006] In a first aspect, the present application provides a data audit method. The method comprises:

[0007] Determine the audit level for the received interaction data;

[0008] Determine the audit process corresponding to the interactive data based on the audit level;

[0009] Based on the audit process, the interaction data is audited and processed.

[0010] In one embodiment, determining an audit level for received interaction data includes:

[0011] Determining a grading rule corresponding to the interaction scenario based on the interaction scenario of the received interaction data;

[0012] Based on the grading rules, the review level corresponding to the interaction data is determined.

[0013] In one embodiment, determining the review level corresponding to the interaction data based on the classification rules includes:

[0014] Determining character information corresponding to the interaction data, where the character information includes the type of characters included in the interaction data and / or the total length of characters corresponding to the interaction data;

[0015] Based on the classification rules, the complexity of the character information corresponding to the interaction data is detected;

[0016] Determine the audit level corresponding to the interaction data based on the complexity detection results.

[0017] In one embodiment, based on the audit process, the interactive data is audited and processed, including:

[0018] Perform word segmentation on the interactive data and determine the word segmentation results;

[0019] Based on the review process, the word segmentation results are reviewed and processed.

[0020] In one embodiment, if the audit process includes at least two audit steps, the word segmentation results are audited based on the audit process, including:

[0021] Based on each review step, the word segmentation results are reviewed and processed, and the number of review steps for which the word segmentation results fail the review is determined;

[0022] Determine the audit results of the interaction data based on the quantity value.

[0023] In one embodiment, after the interaction data is audited and processed, the following steps are included:

[0024] If the audit result is passed, the interaction data is output.

[0025] In a second aspect, the present application also provides a data audit device. The device includes:

[0026] A first determination module is used to determine an audit level for the received interaction data;

[0027] The second determination module is used to determine the review process corresponding to the interaction data according to the review level;

[0028] The audit module is used to audit and process the interaction data based on the audit process.

[0029] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the data audit method according to any one of the embodiments of the first aspect is implemented.

[0030] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the data audit method according to any one of the embodiments of the first aspect.

[0031] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, implements the data audit method according to any embodiment of the first aspect.

[0032] According to the technical solution of the present application, by determining the audit level corresponding to the interactive data, it is ensured that the corresponding audit process can be selected according to the audit level corresponding to the interactive data in the future, thereby reducing the difficulty of auditing the interactive data and improving the efficiency of the subsequent audit of the interactive data; by determining the audit process corresponding to the interactive data and auditing the interactive data, the accuracy of the audit when auditing the interactive data is guaranteed, the rapid audit of the interactive data is realized, the difficulty of auditing the interactive data is reduced, the efficiency of auditing the interactive data is improved, unnecessary audit processes in the audit process of the interactive data are reduced, and the timeliness of the interactive data is guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A diagram showing an application environment of a data audit method in one embodiment;

[0034] Figure 2 A flowchart of a data audit method provided in an embodiment of the present application;

[0035] Figure 3 A flowchart of the steps for determining the audit level provided in an embodiment of the present application;

[0036] Figure 4 A flowchart of the steps for determining the audit result provided in an embodiment of the present application;

[0037] Figure 5 A flowchart of another data audit method provided in an embodiment of the present application;

[0038] Figure 6 A structural block diagram of a data audit device provided in an embodiment of the present application;

[0039] Figure 7 A structural block diagram of another data audit device provided in an embodiment of the present application;

[0040] Figure 8 A structural block diagram of another data audit device provided in an embodiment of the present application;

[0041] Figure 9 A structural block diagram of another data audit device provided in an embodiment of the present application;

[0042] Figure 10 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0044] It should be understood that the specific embodiments described herein are merely used to explain the present application and are not intended to limit the present application. In the description of the present application, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they contradict each other.

[0045] With the rapid development of network technology, applications such as live video broadcasting have become a widely used interactive promotion method across various industries. As live video broadcasting becomes increasingly widespread, the number of people watching live video broadcasts continues to grow, and the amount of interactive data for live video broadcasting (such as comments, messages, or barrages, etc.) is also increasing. However, the interactive data of live video broadcasting is uncontrollable and requires real-time performance. How to prevent the emergence and spread of illegal interactive data while ensuring the real-time performance of interactive data has always been a major problem in the field of interactive data review. The current mainstream method is the keyword library method. The keyword library method has fixed conditions and is prone to misjudgment and misblocking. It is not adaptable to changes in new illegal interactive data. In addition, it requires a long processing time when reviewing interactive data, which reduces the real-time performance of interactive data.

[0046] The data audit method provided in the embodiment of the present application can be applied to Figure 1 In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in FIG. Figure 1As shown. The computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store acquired data for data auditing. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a data auditing method is implemented.

[0047] The present application discloses a data audit method, apparatus, computer equipment and storage medium thereof. A staff member's computer equipment determines the audit level corresponding to the interactive data, and according to the audit level, determines the audit process corresponding to the interactive data, and audits the interactive data according to the audit process.

[0048] Figure 2 A flowchart of a data audit method provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the data audit method may include the following steps:

[0049] Step 201: Determine the review level for the received interaction data.

[0050] It should be noted that the review level refers to a level set based on the complexity of the interaction data, wherein the complexity of the interaction data is used to reflect the types of characters contained in the interaction data and / or the total length of characters corresponding to the interaction data; it should be further explained that if the review level of the interaction data is higher, it means that the complexity corresponding to the interaction data is greater, that is, the interaction data contains more types of characters and / or the interaction data contains a longer total length of characters.

[0051] As an example, if the interaction data A contains 3 types of characters and the interaction data B contains 4 types of characters, and the total length of the characters corresponding to the interaction data A is the same as the total length of the characters corresponding to the interaction data B, it can be determined that the review level of the interaction data B is greater than the review level of the interaction data A.

[0052] As another example, if the total length of characters contained in interaction data C is 10, the total length of characters contained in interaction data D is 12, and the types of characters contained in interaction data C are the same as the types of characters contained in interaction data D, then it can be determined that the review level of interaction data D is greater than the review level of interaction data C.

[0053] As another example, if it is pre-specified that if the character types of the interaction data are less than 5 and the total length of the characters is less than 10, the review level of the interaction data is level 1; if the character types of the interaction data are not less than 5 or the total length of the characters is not less than 10, the review level of the interaction data is level 2; if the interaction data E contains 3 character types and the total length of the characters is 11, the review level of the interaction data E is determined to be level 2; if the interaction data F contains 2 character types and the total length of the characters is 9, the review level of the interaction data F is determined to be level 1.

[0054] It should be noted that the grading rules corresponding to the interaction data can be determined in advance, so that the review level corresponding to the interaction data can be determined according to the grading rules. The grading rules can record the review levels corresponding to different numbers of character types in the interaction data, and the number of character types corresponding to different review levels is different. Specifically, when it is necessary to determine the review level corresponding to the interaction data, the number of character types contained in the interaction data can be determined, and the review level corresponding to the number of character types contained in the interaction data can be found from the grading rules to obtain the review level corresponding to the interaction data.

[0055] In one embodiment of the present application, the grading rules may also record the review levels corresponding to different total lengths of characters in the interaction data, and the total lengths of characters corresponding to different review levels are different; specifically, when it is necessary to determine the review level corresponding to the interaction data, the total length of characters corresponding to the interaction data may be determined, and the review level corresponding to the total length of characters in the interaction data may be searched from the grading rules to obtain the review level corresponding to the interaction data.

[0056] In one embodiment of the present application, the grading rules may also record the review levels corresponding to different numbers of character types and different total lengths of characters in the interaction data. Specifically, when it is necessary to determine the review level corresponding to the interaction data, the different numbers of character types and total lengths of characters in the interaction data may be determined, and the review level corresponding to the interaction data may be searched from the grading rules to obtain the review level corresponding to the interaction data.

[0057] It should be noted that the audit grading model can be used to determine the audit level of interactive data. When the audit level corresponding to the interactive data needs to be determined, the interactive data is input into the audit grading model, which then assesses the level of the interactive data to obtain the audit level determined by the interactive data. Furthermore, when the audit grading model needs to be trained, training data pre-labeled with audit levels can be used as input into the audit grading model, thereby training the audit grading model and ensuring the accuracy of the audit grading model in determining the audit level of the interactive data.

[0058] Step 202: Determine the audit process corresponding to the interaction data according to the audit level.

[0059] It should be noted that when determining the audit process corresponding to the interaction data, at least two audit steps corresponding to the audit level can be selected from a pre-set audit step library based on the audit level, and the at least two audit steps can be combined to determine the audit process. The audit step library contains audit steps corresponding to several different audit levels.

[0060] The audit steps may include matching with blacklisted Chinese characters, matching with blacklisted Chinese and English characters, matching with sensitive risk characters, etc. When the audit process needs to be determined, at least two audit steps corresponding to the audit levels may be sorted and processed. The at least two audit steps after sorting are the audit process. Further, when the interactive data needs to be audited according to the audit process, the interactive data is audited and processed in the order of the audit steps in the audit process.

[0061] In one embodiment of the present application, when it is necessary to determine the audit process based on the audit steps, at least two audit steps corresponding to the audit level are selected from the audit step library, and the priorities corresponding to the at least two audit steps are obtained. The at least two audit steps are sorted based on the priorities of the at least two audit steps to obtain the audit process, wherein, if the priority of the audit step is high, it means that the audit step will be in a front position in the audit process. It can be understood that the audit step with a high priority will first audit the interaction data, and the audit step with a high priority is relatively important. If the audit step fails the audit, there is no need to audit the interaction data based on subsequent audit steps.

[0062] There are many ways to determine the priority of review steps, such as based on pre-set priority judgment rules, the importance of the review step, or the experience of the staff. The setting of the priority of the review step is not limited here.

[0063] Step 203: Based on the review process, the interaction data is reviewed and processed.

[0064] In one embodiment of the present application, if the audit process includes at least two audit steps, when the interactive data needs to be audited, the interactive data is audited based on the audit steps, and based on a pre-set qualified threshold, the relationship between the number of audit steps that fail the audit of the interactive data and the qualified threshold is judged to determine the result of the audit of the interactive data; specifically, if the number of audit steps that fail the audit of the interactive data is greater than or equal to the qualified threshold, the result of the audit of the interactive data is unqualified; if the number of audit steps that fail the audit of the interactive data is less than the qualified threshold, the result of the audit of the interactive data is qualified.

[0065] In another embodiment of the present application, if the audit process includes at least two audit steps, the key audit steps and non-key audit steps of the audit steps are determined, and the interaction data is first audited and processed based on the key audit steps. If there is a key audit step that fails to pass the audit during the audit of the interaction data by the key audit steps, the audit result of the interaction data is determined to be unqualified; if there is no key audit step that fails to pass the audit during the audit of the interaction data by the key audit steps, the interaction data is audited and processed based on the non-key audit steps, and based on a pre-set pass threshold, the relationship between the number of non-key audit steps that fail to pass the audit of the interaction data and the pass threshold is judged to determine the result of the audit processing of the interaction data; specifically, if the number of non-key audit steps that fail to pass the audit of the interaction data is greater than or equal to the pass threshold, the result of the audit processing of the interaction data is unqualified; if the number of non-key audit steps that fail to pass the audit of the interaction data is less than the pass threshold, the result of the audit processing of the interaction data is qualified.

[0066] It should be noted that the audit processing model can be used to audit and process the interaction data according to the audit process and determine the audit results corresponding to the interaction data; when the interaction data needs to be audited and processed, the interaction data and the audit process are input into the audit processing model to determine the audit results corresponding to the interaction data.

[0067] According to the data audit method of the present application, by determining the audit level corresponding to the interactive data, it is ensured that the corresponding audit process can be selected according to the audit level corresponding to the interactive data, thereby reducing the difficulty of auditing the interactive data and improving the efficiency of subsequent auditing of the interactive data; by determining the audit process corresponding to the interactive data and auditing the interactive data, the audit accuracy of the interactive data is ensured, the rapid audit of the interactive data is achieved, the difficulty of auditing the interactive data is reduced, the audit efficiency of the interactive data is improved, unnecessary audit processes in the audit process of the interactive data are reduced, and the timeliness of the interactive data is ensured.

[0068] It should be noted that the review level corresponding to the interactive data can be determined according to the grading rules corresponding to the interactive data; optionally, Figure 3 As shown, Figure 3 A flowchart of steps for determining an audit level is provided in an embodiment of the present application. Specifically, determining the audit level corresponding to the interaction data may include the following steps:

[0069] Step 301: Determine a grading rule corresponding to the interaction scenario according to the interaction scenario of the received interaction data.

[0070] The interactive scene refers to the type of live video broadcast corresponding to the interactive data, and the interactive scene may include but is not limited to: outdoor live broadcast, game live broadcast, and food live broadcast, etc. The classification rules are explained and defined in the following step 302 and are not explained here.

[0071] It should be noted that due to the different interaction scenarios, there are also differences in the interaction data pages for different interaction scenarios. Therefore, a unified audit level determination method cannot make differentiated judgments based on the differences in interaction data. In order to ensure the accuracy of the judgment of the audit level corresponding to the interaction data, different grading rules need to be selected for different interaction scenarios.

[0072] Further explanation: There are many ways to determine different grading rules corresponding to different interaction scenarios: for example, it can be determined based on the experience of staff, or based on historical interaction data. The grading rules corresponding to different interaction scenarios are not limited here.

[0073] For example, if the interactive scenario of the interactive data is outdoor live broadcast, the review level can be divided into four levels, namely review level one, review level two, review level three and review level four; pure Chinese characters and simple symbols (simple symbols are common punctuation marks, such as commas, periods, exclamation marks and question marks) with a length of less than 10 are review level one, pure Chinese characters and simple characters with a length of more than 10 are review level two, letters and various symbols and emoticons with a length of less than 10 are review level three, and letters and various symbols and emoticons with a length of more than 10 are review level four. If the interactive scenario of the interactive data is game live streaming, the review level of game live streaming can be divided into four levels, namely review level one, review level two, review level three and review level four; pure Chinese characters and simple symbols (simple symbols are common punctuation marks, such as commas, periods, exclamation marks and question marks) with a length of less than 8 are review level one, pure Chinese characters and simple characters with a length of more than 8 are review level two, letters and various symbols and emoticons with a length of less than 8 are review level three, letters and various symbols and emoticons with a length of more than 8 are review level four.

[0074] Step 302: Determine the review level corresponding to the interaction data based on the classification rules.

[0075] In one embodiment of the present application, character information corresponding to the interaction data is determined; based on a grading rule, complexity detection is performed on the character information corresponding to the interaction data; and based on the complexity detection result, the review level corresponding to the interaction data is determined.

[0076] The character information includes the character types included in the interaction data and / or the total length of characters corresponding to the interaction data.

[0077] It should be noted that the classification rules record the complexity corresponding to different character information and / or the audit levels corresponding to different complexity levels. It can be understood that different character types and / or total character lengths correspond to different audit levels in the classification rules. When it is necessary to determine the audit level, the character type and / or total character length of the interaction data are substituted into the classification rules to determine the complexity corresponding to the character type and / or total character length. According to the classification rules, the audit level corresponding to the complexity level is determined, thereby determining the audit level corresponding to the interaction data. The specific implementation method can refer to the method for determining the audit level corresponding to the interaction data described in the above embodiment.

[0078] According to the data audit method of the present application, by determining the interaction scenarios corresponding to the interaction data and determining the grading rules, the accuracy of determining the audit level of the interaction data is guaranteed, which provides a judgment basis for the subsequent determination of the audit level of the interaction data and ensures the accuracy of the subsequent audit processing of the interaction data; by determining the audit level, the audit efficiency of the interaction data is improved, which provides a data basis for the subsequent determination of the audit process, reduces the process required for the subsequent audit of the interaction data, and ensures the timeliness of the interaction data.

[0079] It should be noted that the audit process can be performed based on the segmentation results of the interactive data to determine the audit results; optionally, Figure 4 As shown, Figure 4 A flowchart of the steps for determining the audit result provided in an embodiment of the present application. Specifically, determining the audit result may include the following steps:

[0080] Step 401: perform word segmentation processing on the interactive data to determine the word segmentation result.

[0081] It should be noted that there are many methods for word segmentation of interactive data, such as: word segmentation based on a dictionary segmentation algorithm to determine the word segmentation result; or word segmentation based on a statistical segmentation algorithm to determine the word segmentation result. Further explanation: when word segmentation is performed on interactive data based on a dictionary segmentation algorithm, the interactive data can be segmented according to a pre-set dictionary library to determine the word segmentation result; when word segmentation is performed on interactive data based on a statistical segmentation algorithm, the word segmentation result can be determined by annotating the interactive data. The following will explain the word segmentation process in detail based on the above two word segmentation methods:

[0082] As an implementation method, when the interactive data is segmented based on a dictionary segmentation algorithm, the interactive data is matched with a pre-set dictionary library. If a character at a certain position in the interactive data successfully matches a known word in the dictionary library, the character is determined to be the segmentation result. When there is no character in the interactive data that matches a known word in the dictionary library, it indicates that the segmentation processing is completed.

[0083] As an implementation method, when the interactive data is segmented based on a statistical word segmentation algorithm, the interactive data is segmented and annotated based on pre-set annotation rules, wherein the annotation rules are: when the character is the first character of a word, it is marked as B; when the character is the last character of a word, it is marked as E; when the character is the middle character of a word, it is marked as M (it can be multiple); when the character is a word that can independently represent a word, it is marked as S. For example, "XX application is the most important product of XX company's business unit", and the annotated result is "BMMESBMMEBMMMESBMEBE". The interactive data is annotated according to standard rules, and the word segmentation result is determined based on the annotation results corresponding to the interactive data.

[0084] Step 402: Based on the review process, the word segmentation results are reviewed and processed.

[0085] It should be noted that when the audit result needs to be determined, the word segmentation result is audited based on each audit step to determine the number of audit steps that fail the word segmentation result audit; based on the number value, the audit result of the interaction data is determined.

[0086] In one embodiment of the present application, if there is an audit step that fails the audit among at least two audit steps that are pre-specified, it means that the audit result is failed. It can be understood that when the quantity value is greater than or equal to 1, the audit result is unqualified, and if the quantity value is equal to 0, the audit result is qualified.

[0087] For example, at least two audit steps are determined: matching blacklisted Chinese characters, matching with blacklisted Chinese characters in English, and matching with sensitive risk characters. The word segmentation results are audited based on these three audit steps. The audit step "matching blacklisted Chinese characters" is determined to have failed. The remaining two audit steps are both passed, and the quantity value is determined to be 1. Since the quantity value is greater than or equal to 1, the audit result of the interactive data is determined to be unqualified.

[0088] It should be noted that if the review result is approved, the interaction data is output, thereby enabling public display of the interaction data. For example, comment interaction data can be displayed on a pop-up page during a live video broadcast. If the review result is rejected, the interaction data is deleted. Further, after the review result of the interaction data is determined, new interaction data is received and the step of "determining the review level for the received interaction data" is executed until no new interaction data is received.

[0089] According to the data audit method of the present application, by performing word segmentation processing on the interactive data, it is ensured that the interactive data can be fully audited and processed, ensuring the smooth progress of the subsequent audit process, improving the accuracy of the subsequent audit processing, and preventing audit errors or omissions; by determining the audit results by determining the quantitative value, it is achieved that the interactive data is quickly audited, the difficulty of auditing the interactive data is reduced, the efficiency of auditing the interactive data is improved, unnecessary audit processes in the audit process of the interactive data are reduced, and the timeliness of the interactive data is guaranteed.

[0090] In one embodiment of the present application, Figure 5 As shown, Figure 5 This is a flowchart of another data audit method provided in an embodiment of the present application. Optionally, when it is necessary to audit the interactive data:

[0091] Step 501: Determine a grading rule corresponding to the interaction scenario according to the interaction scenario of the received interaction data.

[0092] Step 502: Determine character information corresponding to the interaction data. The character information includes the type of characters included in the interaction data and / or the total length of characters corresponding to the interaction data.

[0093] Step 503: Based on the classification rules, complexity detection is performed on the character information corresponding to the interaction data.

[0094] Step 504: Determine the review level corresponding to the interaction data based on the complexity detection result.

[0095] Step 505: Determine the audit process corresponding to the interaction data according to the audit level.

[0096] Step 506: perform word segmentation processing on the interactive data to determine the word segmentation result.

[0097] Step 507: The review process includes at least two review steps. Based on each review step, the word segmentation result is reviewed and processed to determine the number of review steps in which the word segmentation result fails the review.

[0098] Step 508: Determine the audit result based on the quantity value.

[0099] It should be noted that if the audit result is passed, the interaction data will be output and publicly displayed.

[0100] According to the data audit method of the present application, by determining the audit level corresponding to the interactive data, it is ensured that the corresponding audit process can be selected according to the audit level corresponding to the interactive data, thereby reducing the difficulty of auditing the interactive data and improving the efficiency of subsequent auditing of the interactive data; by determining the audit process corresponding to the interactive data and auditing the interactive data, the audit accuracy of the interactive data is ensured, the rapid audit of the interactive data is achieved, the difficulty of auditing the interactive data is reduced, the audit efficiency of the interactive data is improved, unnecessary audit processes in the audit process of the interactive data are reduced, and the timeliness of the interactive data is ensured.

[0101] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0102] Based on the same inventive concept, the present application also provides a data audit device for implementing the aforementioned data audit method. The implementation solution provided by the device is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations of one or more data audit device embodiments provided below can be found in the above-mentioned limitations of the data audit method and will not be repeated here.

[0103] In one embodiment, Figure 6 As shown, Figure 6 This is a structural block diagram of a data audit device provided in an embodiment of the present application, which provides a data audit device including: a first determination module 100, a second determination module 200 and an audit module 300, wherein:

[0104] The first determination module 100 is configured to determine an audit level for received interaction data.

[0105] The second determining module 200 is used to determine the review process corresponding to the interaction data according to the review level.

[0106] The audit module 300 is used to perform audit processing on the interaction data based on the audit process.

[0107] According to the data audit device of the present application, by determining the audit level corresponding to the interactive data, it is ensured that the corresponding audit process can be selected according to the audit level corresponding to the interactive data, thereby reducing the difficulty of auditing the interactive data and improving the efficiency of subsequent auditing of the interactive data; by determining the audit process corresponding to the interactive data and auditing the interactive data, the accuracy of the audit when auditing the interactive data is ensured, the rapid audit of the interactive data is achieved, the difficulty of auditing the interactive data is reduced, the efficiency of auditing the interactive data is improved, unnecessary audit processes in the audit process of the interactive data are reduced, and the timeliness of the interactive data is ensured.

[0108] In one embodiment, Figure 7 As shown, Figure 7 This is a structural block diagram of another data audit device provided in an embodiment of the present application. A data audit device is provided. The first determination module 100 in the data audit device includes: a first determination unit 110 and a second determination unit 120, wherein:

[0109] The first determining unit 110 is configured to determine a grading rule corresponding to an interaction scenario according to the interaction scenario of the received interaction data.

[0110] The second determining unit 120 is configured to determine the review level corresponding to the interaction data based on a grading rule.

[0111] According to the data audit device of the present application, by determining the interaction scenario corresponding to the interaction data and determining the grading rules, the accuracy of determining the audit level of the interaction data is guaranteed, a judgment basis is provided for the subsequent determination of the audit level of the interaction data, and the accuracy of the subsequent audit processing of the interaction data is guaranteed; by determining the audit level, the audit efficiency of the interaction data is improved, a data basis is provided for the subsequent determination of the audit process, the process required for the subsequent audit of the interaction data is reduced, and the timeliness of the interaction data is guaranteed.

[0112] In one embodiment, Figure 8 As shown, Figure 8 This is a structural block diagram of another data audit device provided in an embodiment of the present application. A data audit device is provided. The second determination unit 120 in the data audit device includes: a first determination subunit 121, an audit subunit 122, and a second determination subunit 123, wherein:

[0113] The first determining subunit 121 is configured to determine character information corresponding to the interaction data, where the character information includes the type of characters included in the interaction data and / or the total length of characters corresponding to the interaction data.

[0114] The review sub-unit 122 is used to perform complexity detection on the character information corresponding to the interactive data based on the classification rules.

[0115] The second determining subunit 123 is configured to determine the review level corresponding to the interaction data according to the complexity detection result.

[0116] According to the data audit device of the present application, by determining the character information corresponding to the interactive data, a data basis is provided for the subsequent determination of the complexity of the interactive information, the accuracy of determining the audit level of the interactive data is ensured, and a judgment basis is provided for the subsequent determination of the audit level of the interactive data; the audit level is determined according to the complexity detection result, which ensures the accuracy of the subsequent audit processing of the interactive data, reduces unnecessary audit processes in the process of auditing the interactive data, and ensures the timeliness of the interactive data.

[0117] In one embodiment, Figure 9 As shown, Figure 9 This is a structural block diagram of another data audit device provided in an embodiment of the present application. A data audit device is provided. If the audit process includes at least two audit steps, the audit module 300 in the data audit device includes: a third determination unit 310 and a fourth determination unit 320, wherein:

[0118] The third determining unit 310 is configured to perform an audit process on the word segmentation result based on each audit step, and determine the number of audit steps for which the word segmentation result fails the audit;

[0119] The fourth determining unit 320 is configured to determine a review result of the interaction data according to the quantity value.

[0120] It should be noted that if the audit result is passed, the interaction data will be output.

[0121] According to the data audit device of the present application, by performing word segmentation processing on the interactive data, it is ensured that the interactive data can be fully audited and processed, the smooth progress of the subsequent audit process is ensured, the accuracy of the subsequent audit processing is improved, and audit errors or omissions are prevented; by determining the audit results by determining the quantitative value, a rapid audit of the interactive data is achieved, the difficulty of auditing the interactive data is reduced, the efficiency of auditing the interactive data is improved, unnecessary audit processes in the audit process of the interactive data are reduced, and the timeliness of the interactive data is ensured.

[0122] Each module in the above-mentioned data audit device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor of the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0123] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 10 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a data audit method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0124] Those skilled in the art will understand that Figure 10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0125] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0126] Determine the audit level for the received interaction data;

[0127] Determine the audit process corresponding to the interactive data based on the audit level;

[0128] Based on the audit process, the interaction data is audited and processed.

[0129] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0130] Determining a grading rule corresponding to the interaction scenario based on the interaction scenario of the received interaction data;

[0131] Based on the grading rules, the review level corresponding to the interaction data is determined.

[0132] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0133] Determining character information corresponding to the interaction data, where the character information includes the type of characters included in the interaction data and / or the total length of characters corresponding to the interaction data;

[0134] Based on the classification rules, the complexity of the character information corresponding to the interaction data is detected;

[0135] Determine the audit level corresponding to the interaction data based on the complexity detection results.

[0136] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0137] Perform word segmentation on the interactive data and determine the word segmentation results;

[0138] Based on the review process, the word segmentation results are reviewed and processed.

[0139] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0140] Based on each review step, the word segmentation results are reviewed and processed, and the number of review steps for which the word segmentation results fail the review is determined;

[0141] Determine the audit results of the interaction data based on the quantity value.

[0142] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0143] If the audit result is passed, the interaction data will be output and publicly displayed.

[0144] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0145] Determine the audit level for the received interaction data;

[0146] Determine the audit process corresponding to the interactive data based on the audit level;

[0147] Based on the audit process, the interaction data is audited and processed.

[0148] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0149] Determining a grading rule corresponding to the interaction scenario based on the interaction scenario of the received interaction data;

[0150] Based on the grading rules, the review level corresponding to the interaction data is determined.

[0151] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0152] Determining character information corresponding to the interaction data, where the character information includes the type of characters included in the interaction data and / or the total length of characters corresponding to the interaction data;

[0153] Based on the classification rules, the complexity of the character information corresponding to the interaction data is detected;

[0154] Determine the audit level corresponding to the interaction data based on the complexity detection results.

[0155] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0156] Perform word segmentation on the interactive data and determine the word segmentation results;

[0157] Based on the review process, the word segmentation results are reviewed and processed.

[0158] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0159] Based on each review step, the word segmentation results are reviewed and processed, and the number of review steps for which the word segmentation results fail the review is determined;

[0160] Determine the audit results of the interaction data based on the quantity value.

[0161] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0162] If the audit result is passed, the interaction data will be output and publicly displayed.

[0163] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0164] Determine the audit level for the received interaction data;

[0165] Determine the audit process corresponding to the interactive data based on the audit level;

[0166] Based on the audit process, the interaction data is audited and processed.

[0167] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0168] Determining a grading rule corresponding to the interaction scenario based on the interaction scenario of the received interaction data;

[0169] Based on the grading rules, the review level corresponding to the interaction data is determined.

[0170] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0171] Determining character information corresponding to the interaction data, where the character information includes the type of characters included in the interaction data and / or the total length of characters corresponding to the interaction data;

[0172] Based on the classification rules, the complexity of the character information corresponding to the interaction data is detected;

[0173] Determine the audit level corresponding to the interaction data based on the complexity detection results.

[0174] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0175] Perform word segmentation on the interactive data and determine the word segmentation results;

[0176] Based on the review process, the word segmentation results are reviewed and processed.

[0177] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0178] Based on each review step, the word segmentation results are reviewed and processed, and the number of review steps for which the word segmentation results fail the review is determined;

[0179] Determine the audit results of the interaction data based on the quantity value.

[0180] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0181] If the audit result is passed, the interaction data will be output and publicly displayed.

[0182] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0183] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0184] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0185] The above embodiments merely illustrate several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A data audit method, characterized in that: The method comprises: Determining, based on an interaction scenario of the received interaction data, a grading rule corresponding to the interaction scenario; wherein the interaction scenario is a type of live video broadcast corresponding to the interaction data, and the live video broadcast types include: outdoor live broadcast, game live broadcast, and food live broadcast; the grading rule records review levels corresponding to different numbers of character types in the interaction data, and review levels corresponding to different total lengths of characters in the interaction data, wherein different review levels correspond to different numbers of character types and different total lengths of characters; Determining character information corresponding to the interaction data, the character information including the type of characters included in the interaction data and / or the total length of characters corresponding to the interaction data; Based on the classification rules and the pre-trained audit classification model, performing complexity detection on the character information corresponding to the interaction data; Determining the review level corresponding to the interaction data according to the complexity detection result; According to the audit level, at least two audit steps are selected from the audit step library, and the priorities corresponding to the audit steps are obtained; the audit steps include: matching with blacklisted Chinese characters and words, matching with blacklisted Chinese and English characters, and matching with sensitive risk characters; sorting the review steps based on the priority to form a review process corresponding to the interaction data; wherein the higher the priority, the earlier the review step is in the review process; Performing word segmentation processing on the interaction data to determine a word segmentation result; Based on each of the review steps included in the review process, the word segmentation result is reviewed and processed, and the number of the review steps for which the word segmentation result fails the review is determined; A review result of the interaction data is determined according to the quantity value.

2. The method according to claim 1, characterized in that After the interactive data is audited, the following steps are included: If the audit result is passed, the interaction data is output.

3. A data audit device, characterized in that: The device comprises: A first determination module is configured to determine, based on an interaction scenario of received interaction data, a grading rule corresponding to the interaction scenario; wherein the interaction scenario is a type of live video broadcast corresponding to the interaction data, and the live video broadcast types include outdoor live broadcast, game live broadcast, and food live broadcast; the grading rule records review levels corresponding to different numbers of character types in the interaction data, and review levels corresponding to different total lengths of characters in the interaction data, wherein different review levels correspond to different numbers of character types and different total lengths of characters; Determining character information corresponding to the interaction data, the character information including the type of characters included in the interaction data and / or the total length of characters corresponding to the interaction data; Based on the classification rules and the pre-trained audit classification model, performing complexity detection on the character information corresponding to the interaction data; Determining the review level corresponding to the interaction data according to the complexity detection result; A second determination module is configured to select at least two audit steps from an audit step library based on the audit level and obtain the priorities corresponding to the audit steps; the audit steps include: matching with blacklisted Chinese characters and words, matching with blacklisted Chinese and English characters, and matching with sensitive risk characters; sorting the review steps based on the priority to form a review process corresponding to the interaction data; wherein the higher the priority, the earlier the review step is in the review process; An audit module is used to perform word segmentation processing on the interaction data and determine the word segmentation result; Based on each of the review steps included in the review process, the word segmentation result is reviewed and processed, and the number of the review steps for which the word segmentation result fails the review is determined; A review result of the interaction data is determined according to the quantity value.

4. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 2 are implemented.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 2 are implemented.

6. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 2 are implemented.

Images