A method, device, equipment and medium for screening sampling objects

By obtaining and analyzing the audit method information of the audited objects and selecting the corresponding objects for random inspection, the problem of incomplete random inspections in the existing technology is solved, and the comprehensive verification of preset audit rules is achieved, which improves the representativeness and accuracy of random inspections is improved. sex.

CN113935748BActive Publication Date: 2024-11-01ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111126042.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-09-24
Publication Date
2024-11-01
Estimated Expiration
2041-09-24

AI Technical Summary

Technical Problem

The existing random inspection methods cannot fully cover the audit objects, resulting in the random inspection results being unrepresentative and the accuracy of the preset audit rules cannot be effectively verified.

Method used

By obtaining the audit method information of the audited objects, extracting objects using the same audit method from the audit object collection, ensuring that the sampling objects cover all audit methods and achieving comprehensive verification of preset audit rules.

Benefits of technology

It improves the representativeness and accuracy of random inspections, so that the random inspection results can more comprehensively verify the preset audit rules, and enhances the reliability of the audit results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113935748B_ABST
    Figure CN113935748B_ABST
Patent Text Reader

Abstract

The embodiments of this specification disclose a method, device, equipment and medium for selecting inspection objects. The scheme includes: obtaining an audit object set including several audited objects; the audited objects are audited according to preset audit rules; the preset audit rules include several audit methods; determining the audit method information of each audited object; the audit method information is used to indicate the audit method used by the audited object during the audit process; according to the audit method information of each audited object, extracting the audited objects corresponding to each audit method from the audit object set.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, equipment and medium for screening sampling objects. Background Art

[0002] With the development of computer technology, more and more online businesses have emerged, and the business volume has also increased. In order to determine whether the business activities of enterprises, merchants and other entities providing online services comply with national laws, regulations and industry rules, it is necessary to review the business conducted by enterprises, merchants and other users through the Internet. For example, whether there are any illegal texts in the images, videos, audios, texts and other advertisements provided by merchants. For example, if a user wants to use a third-party payment platform to make payments, the third-party payment platform needs to review whether the user is a real-name registered account.

[0003] At present, the audit is usually conducted by machine audit (abbreviated as machine audit) first, and then by manual review. However, since the audited business data is usually very large, it is usually only possible to sample the audit results of the machine audit and conduct manual review by random inspection. The accuracy of the audit is determined based on the random inspection results. It can be seen that the object of random inspection has a certain influence on the judgment of the audit results.

[0004] Therefore, how to make the objects of random inspection more representative and conduct random inspection and verification more comprehensive is a technical problem that needs to be solved urgently. Summary of the invention

[0005] The embodiments of this specification provide a method, device, equipment and medium for screening sampling objects to solve the problem of incomplete sampling in existing sampling methods.

[0006] To solve the above technical problems, the embodiments of this specification are implemented as follows:

[0007] The present invention provides a method for screening a sample object, including:

[0008] Acquire an audit object set including a plurality of audited objects; the audited objects are audited according to preset audit rules; the preset audit rules include a plurality of audit methods;

[0009] Determine the audit method information of each audited object; the audit method information is used to indicate the audit method used by the audited object during the audit process;

[0010] According to the audit method information of each audited object, the audited objects corresponding to each audit method are extracted from the audit object set.

[0011] The present invention provides a screening device for sampling objects, including:

[0012] The object acquisition module is used to acquire an audit object set including a number of audited objects; the audited objects are audited according to preset audit rules; the preset audit rules include a number of audit methods;

[0013] An information determination module, used to determine the audit method information of each audited object; the audit method information is used to indicate the audit method used by the audited object during the audit process;

[0014] The object extraction module is used to extract the audited objects corresponding to each audit method from the audit object set according to the audit method information of each audited object.

[0015] The present invention provides a screening device for sampling objects, including:

[0016] at least one processor; and,

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0019] Acquire an audit object set including a plurality of audited objects; the audited objects are audited according to preset audit rules; the preset audit rules include a plurality of audit methods;

[0020] Determine the audit method information of each audited object; the audit method information is used to indicate the audit method used by the audited object during the audit process;

[0021] According to the audit method information of each audited object, the audited objects corresponding to each audit method are extracted from the audit object set.

[0022] An embodiment of the present specification provides a computer-readable medium on which computer-readable instructions are stored. The computer-readable instructions can be executed by a processor to implement a method for screening sampling objects.

[0023] An embodiment of this specification can achieve the following beneficial effects:

[0024] In an embodiment of the present specification, from an audit object set that includes several audited objects, audited objects corresponding to each audit method can be extracted according to the audit method used by the audited objects when auditing using preset audit rules, so that the audited objects sampled can cover various audit methods, thereby more comprehensively verifying the preset audit rules and improving the actual effect of the random inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of this specification or the technical solutions in 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 described below are only some embodiments recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0026] Figure 1 This is a schematic diagram of an application scenario of a method for screening sampling objects in an embodiment of this specification;

[0027] Figure 2 A flowchart of a method for screening sampling objects provided in an embodiment of this specification;

[0028] Figure 3 A schematic diagram of a directed acyclic graph of audit rules provided in an embodiment of this specification;

[0029] Figure 4 A swimming lane diagram of a method for screening a sample object provided in an embodiment of this specification;

[0030] Figure 5 A schematic diagram of the structure of a screening device for sampling objects provided in an embodiment of this specification;

[0031] Figure 6 A schematic diagram of the structure of a screening device for sampling objects provided in an embodiment of this specification. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solutions and advantages of one or more embodiments of this specification clearer, the technical solutions of one or more embodiments of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this description, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of one or more embodiments of this specification.

[0033] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0034] In the prior art, when conducting manual review, a certain number of objects are usually randomly selected from the objects that have completed the review as the objects for spot check, and the objects that have been spot checked are manually reviewed to verify the accuracy of the review. In actual applications, the audit rules contained in the audit platform or system for machine audit may be composed of multiple atomic algorithms. When auditing an audit object, not all atomic algorithms may be actually triggered for use. For example, the audit rules contain an atomic algorithm for image recognition, but when the audit object does not contain an image, although the execution steps containing the atomic algorithm will be run according to the execution procedure of the audit rules, the atomic algorithm will not be triggered for use. Different audit objects may trigger different atomic algorithms. The objects extracted by random sampling cannot guarantee coverage of all audit object situations, and comprehensive spot checks and verifications are not performed.

[0035] In order to solve the defects in the prior art, this solution provides the following embodiments:

[0036] Figure 1 Schematic diagram of an application scenario of a method for screening sampling objects in an embodiment of this specification. Figure 1 As shown, the scenario may include an audit object set 1 including several audited objects, a sampling platform 2, and a sampled inspection object 3. Among them, the audited objects in the audit object set 1 may be objects audited by preset audit rules. In the implementation application, the audit platform or system including preset audit rules may audit the audited objects. The sampling platform 2 may be a platform for executing the screening method of the inspection object provided in the embodiment of this specification, and the platform may randomly select the inspection object 3 from the audit object set. The inspection object 3 may be at least one audited object in the audit object set. In the embodiment of this specification, the sampling platform 2 may obtain the audit object set 1 including several audited objects, determine the audit method information of each audited object, and then extract the audited objects corresponding to each audit method from the audit object set as the inspection objects. In this way, the inspection objects may include audited objects audited by various audit methods, and the preset audit rules may be verified more comprehensively.

[0037] Next, a method for screening sampling objects provided in an embodiment of the specification will be specifically described with reference to the accompanying drawings:

[0038] Figure 2 A schematic diagram of a method for selecting a sampling object provided in an embodiment of the present specification. From a program perspective, the execution subject of the process can be a program installed on an application server or an application client.

[0039] like Figure 2 As shown, the process may include the following steps:

[0040] Step 202: Acquire an audit object set including a number of audited objects; the audited objects are audited according to preset audit rules; the preset audit rules include a number of audit methods.

[0041] Among them, the preset audit rules may include multiple atomic algorithms, the audit method may be a combination of different atomic algorithms, and different audit methods may include different atomic algorithms. The audit object may include audit materials, which may represent the audit content to be audited; the atomic algorithm may represent an atomic single-function algorithm, which may include an artificial intelligence algorithm. In the embodiments of this specification, the atomic algorithm may be a single-function artificial intelligence algorithm without business semantics that is relied on in the audit rules.

[0042] Step 204: Determine the audit method information of each audited object; the audit method information is used to indicate the audit method used by the audited object during the audit process.

[0043] In actual applications, when different audit objects are audited using preset audit rules, different audit objects may be audited using different audit methods in the preset audit rules. In the embodiments of this specification, the audit methods used by each audited object can be counted to determine the audit method information of each audited object.

[0044] Step 206: According to the audit method information of each audited object, extract audited objects of each audit method from the audit object set.

[0045] In an embodiment of the present specification, from an audit object set that includes several audited objects, audited objects corresponding to each audit method can be extracted according to the audit method used by the audited objects when auditing using preset audit rules. This allows the audited objects sampled to cover various audit methods and various types of audit objects, thereby enabling a more comprehensive verification of the preset audit rules and also improving the actual effect of the random inspection.

[0046] It should be understood that the order of some steps in the methods described in one or more embodiments of this specification can be interchanged according to actual needs, or some steps can be omitted or deleted.

[0047] The embodiments of this specification do not limit the content of the specific preset audit rules, and the preset audit rules can be existing audit rules. For example, in actual applications, when auditing the object to be audited, the audit can be conducted according to certain audit rules. Assuming that the object to be audited is an advertisement for a certain product, it is necessary to review whether the pictures, texts, display specifications, etc. contained in the advertisement meet the corresponding regulations, and the audit can be conducted by setting audit rules.

[0048] The preset review rules may be composed of multiple atomic algorithms. For example, assuming that when reviewing the above-mentioned advertisement, the atomic algorithms that may be included include an algorithm for identifying images in the advertisement to determine whether the images contain any illegal content; an algorithm for identifying text to determine whether the text contains any illegal content; an algorithm for identifying display specifications to determine whether the display specifications of the advertisement meet the display requirements, and so on.

[0049] The audit methods in the embodiments of this specification may correspond to different atomic algorithms. For example, audit method a may include an algorithm for recognizing images, and audit method b may include algorithms for text extraction and text recognition.

[0050] based on Figure 2 The method, the examples of this specification also provide some specific implementation plans of the method, which are described below.

[0051] The preset audit rules in the embodiments of this specification may include multiple atomic algorithms; the audit method may include at least one of the atomic algorithms.

[0052] The information of the audit method for each audited object may specifically include:

[0053] Determine the atomic algorithms used by each audited object during the audit process.

[0054] Among them, for each audited object among the audited objects, it can be determined that each atomic algorithm is used in the audit process of each audited object.

[0055] In actual applications, the preset audit rules can be executed by a computer in the form of a program, where the audit can be performed according to the set steps. Each audit step can be understood as a respective audit sub-rule, and each audit sub-rule can contain an atomic algorithm for the audit. Each atomic algorithm can also be understood as the algorithm used in each audit step.

[0056] In actual applications, during the audit of the audit object, the preset audit rules can be executed according to the preset execution steps. To ensure the integrity of the audit, each step in the preset audit rules will usually be executed on the audit object. However, due to the characteristics of the audit object itself, it may not trigger the use of all atomic algorithms in the preset audit rules. For example, when the preset audit rules include an atomic algorithm for text recognition, if the audit object does not contain text, although the execution steps of the atomic algorithm including text recognition will be executed during the audit of the audit object, the atomic algorithm will not be actually triggered. In the embodiment of this specification, the atomic algorithm used in the audit process of the audited object can be the atomic algorithm that is triggered during the audit process. The audited object contains content that can be recognized and calculated by the atomic algorithm, and the corresponding audit result can be obtained through the atomic algorithm.

[0057] In actual applications, during the audit of the audit object, the atomic algorithms used by the audit object can also be marked. The audit procedure corresponding to the preset audit rules can include instructions for marking the atomic algorithms used by the audit object. When the audit object uses a certain atomic algorithm, a corresponding identifier can be generated to indicate that the audit object uses the atomic algorithm. In actual applications, it can be determined based on the audit results of the audit object whether the audit object uses each atomic algorithm in the preset audit rules, wherein the audit results can include the results of identifying the audit object using each atomic algorithm. When the audit results do not include the identification results corresponding to certain atomic algorithms in each atomic algorithm, it can be determined that these atomic algorithms are not used in the audit object.

[0058] The determination of each atomic algorithm used by each audited object in the audit process described in the embodiments of this specification may specifically include:

[0059] Obtaining the rule triggering identifier corresponding to each audited object; the rule triggering identifier is used to indicate that the atomic algorithm corresponding to the rule triggering identifier in the preset audit rule is used in the process of auditing each audited object;

[0060] Based on the rule triggering identifier, it is determined that each of the audited objects uses each of the atomic algorithms during the audit process.

[0061] In actual applications, a record table can be generated to record the audit method information of each audited object. The record table can include the object identifier of each audited object and the atomic algorithm rule trigger identifier used by each audited object. Specifically, one of the row fields and column fields in the record table can represent each atomic algorithm, and the other field can represent the audit method adopted by each audited object.

[0062] Assume that the preset audit rules include 4 atomic algorithms and 20 audit objects are audited. Table 1 is a schematic diagram of a record table for recording the audit methods of each audited object provided in an embodiment of this specification.

[0063]

[0064] Table 1

[0065] As shown in Table 1, the row field in the record table may contain identifiers representing various atomic algorithms: Atom 1, Atom 2, Atom 4 and Atom 4; the column field may contain identifiers representing various audited objects: Object 1, Object 2...Object 20; the intersection of rows and columns may indicate whether the audited object corresponding to the row uses the atomic algorithm corresponding to the column. Among them, a specific character may be used to indicate whether the audited object uses an atomic algorithm. For example, "1" may be used to indicate that the audited object uses a certain atomic algorithm, or that the audit result of the audited object includes the audit result corresponding to the atomic algorithm; "0" may be used to indicate that the audited object does not use a certain atomic algorithm, or that the audited object does not obtain the audit result corresponding to the atomic algorithm. For example, the data of object 1 in Table 1 above may indicate that the audited object 1 uses an audit method including atomic algorithm 1 and atomic algorithm 2; the data of object 2 may indicate that the audited object 2 uses an audit method including atomic algorithm 1 and atomic algorithm 3, and so on.

[0066] In practical applications, the column fields may also be used to represent the various atomic algorithms, and the row fields may be used to represent the audit methods adopted by the various audited objects. It can be understood that the above Table 1 is only an exemplary representation. In practical applications, the form of recording the audit methods adopted by the various audited objects may be selected according to actual needs, and is not limited to the form of table statistics. The specific recording form is not limited in the embodiments of this specification, as long as it can represent the audit methods adopted by the various audited objects.

[0067] In the embodiments of this specification, based on the audit method information of each audited object, at least some audit objects can be extracted from the audited objects using the same audit method, so that the corresponding audited objects can be extracted for each audit method as sampling objects. Specifically, the extraction of audited objects corresponding to each audit method from the audit object set in the embodiments of this specification can specifically include:

[0068] According to the audit method information of each audited object, count the audited objects corresponding to each audit method to obtain a first audited object set corresponding to each audit method;

[0069] A second set of audited objects corresponding to each audit method is extracted from the first set of audited objects corresponding to each audit method; the second set of audited objects is a subset of the first set of audited objects.

[0070] The first audited object set may include audited objects audited using the same audit method; for each audit method, the first audited object set corresponding to the audit method can be obtained. The second audited object set may include at least some of the audited objects in the first audited object set; for each audit method, the second audited object set corresponding to the audit method can be obtained; when there are multiple audit methods, multiple second audited object sets can be obtained, and the final sampling objects may include audited objects in each second audited object set.

[0071] Continuing with Table 1 above, assuming that when objects 5, 8 and 10 were audited, atoms 1, 2 and 3 in the atomic algorithm were used, it can be determined that the same audit method was used for objects 5, 8 and 10. The set consisting of objects 5, 8 and 10 can be used as the first audited object set, and then at least part of them can be selected as sampling objects. Assuming that one sampling object needs to be selected for this audit method, one can be selected from objects 5, 8 and 10. Assume that object 8 is selected as the sampling object.

[0072] In the embodiment of the present specification, a preset number of sampling objects may be selected as needed. Specifically, in the embodiment of the present specification, the second audited object set may include a preset number of audited objects.

[0073] In order to make the sampled objects better reflect the performance of the preset audit rules, in the embodiment of this specification, the preset number can be positively correlated with the number of atomic algorithms included in the audit method corresponding to the second audited object set.

[0074] When the audit method contains more atomic algorithms, the complexity of the audit object is higher, and more audited objects that use this audit method can be extracted as sampling inspection objects. For example, if the audit method 1 in the preset audit rule uses 3 atomic algorithms, 5 audited objects can be extracted from the audited objects that use audit method 1 as sampling inspection objects; if the audit method 2 in the preset audit rule uses 4 atomic algorithms, 8 audited objects can be extracted from the audited objects that use audit method 2 as sampling inspection objects.

[0075] In actual applications, the preset audit rules may include multiple atomic algorithms. According to the situations in which different atomic algorithms are used, multiple audit methods can be determined. In the embodiments of this specification, the various audit methods that the preset audit rules may correspond to can be determined based on the various atomic algorithms included in the preset audit rules, and then the audited objects corresponding to each audit method can be extracted from the audited objects as sampling objects.

[0076] As an implementation manner, extracting audited objects corresponding to each audit method from the audit object set may specifically include:

[0077] Determine each audit method included in the preset audit rules;

[0078] According to the audit method information of each audited object, count the audited objects corresponding to each audit method included in the preset audit rule to obtain a third audited object set corresponding to each audit method;

[0079] A fourth set of audited objects corresponding to each audit method is extracted from the third set of audited objects corresponding to each audit method; the fourth set of audited objects is a subset of the third set of audited objects.

[0080] If there is no audited object using a certain audit method among the acquired audited objects, the third audited object set corresponding to the audit method may be determined as an empty set.

[0081] In the embodiment of this specification, the fourth audited object set may include a preset number of audited objects. In actual application, a preset number of audited objects may be selected from the third audited object set as audited objects in the fourth audited object set. In actual application, the audited objects in the fourth audited object set may be used as sampling objects.

[0082] In practical applications, a rule file representing the preset audit rules can be generated based on each atomic algorithm contained in the preset audit rules, and the audit method contained in the preset audit rules can be expressed in the form of a file. Specifically:

[0083] In the embodiment of the present specification, the rule file carrying the preset audit rule is a file containing a table; one of the row field and the column field in the table represents the atomic algorithm included in the preset audit rule, and the other field represents the audit method included in the preset audit rule;

[0084] The determining of each audit method included in the preset audit rule may specifically include:

[0085] Based on the rule file, various audit methods included in the preset audit rules are determined.

[0086] Among them, when the row field represents the atomic algorithm included in the preset audit rule, and the column field represents the audit method included in the preset audit rule, each group of row fields can represent the atomic algorithm included in the audit method in the column field corresponding to the row, and the preset characters can be used at the intersection of the row and the column to indicate whether the audit method corresponding to the row includes the atomic algorithm corresponding to the column. For example, "1" can be used to indicate that the audit method corresponding to the row includes the atomic algorithm corresponding to the column, and "0" can be used to indicate that the audit method corresponding to the row does not include the atomic algorithm corresponding to the column. Table 2 is a schematic diagram of a record table of an audit method provided in an embodiment of the present specification.

[0087]

[0088] Table 2

[0089] Assume that the preset audit rules contain n atomic algorithms. For n atomic algorithms, m audit methods can be combined. Each audit method contains different atomic algorithms. The preset audit rules can contain at most 2 n There are multiple audit methods. In practical applications, m can be less than or equal to 2. n .

[0090] For each audit method included in the preset audit rules, for each audit method, sampling objects can be selected from the audited objects that adopt each audit method. In actual applications, the audit method may not include atomic algorithms, and the audit method that does not adopt atomic algorithms can be used as an audit method. To further ensure the comprehensiveness of the sampling inspection, if the audit object set contains audited objects that do not adopt various atomic algorithms, the audited objects can also be selected as sampling objects.

[0091] In practical applications, the atomic algorithms included in the preset audit rules can also be represented by column fields, and the audit methods included in the preset audit rules can be represented by row fields. Each group of column fields can represent the atomic algorithms included in the audit methods in the row fields corresponding to the column. It can be understood that the above Table 2 is only an exemplary representation. In practical applications, the form of representing each audit method can be selected according to actual needs, not limited to the form of table statistics. The specific form is not limited in the embodiments of this specification, as long as it can represent each audit method of the preset audit rules.

[0092] In actual applications, the form of the audit methods of each audited object in the audit object set can be the same as the form of each audit method included in the preset audit rules, so that sampling objects corresponding to each audit method included in the preset audit rules can be extracted from the audit object set according to the matching method.

[0093] In practical applications, the preset audit rules can be arranged and set in the form of a directed acyclic graph (DAG). The method provided in the embodiment of this specification can also include:

[0094] Obtain a directed acyclic graph corresponding to the preset audit rule; the nodes in the directed acyclic graph represent the atomic algorithms in the preset audit rule; the lines in the directed acyclic graph represent the execution order of two adjacent atomic algorithms in the preset audit rule;

[0095] Based on the directed acyclic graph, each atomic algorithm included in the preset audit rule is determined.

[0096] Figure 3 A schematic diagram of a directed acyclic graph of audit rules provided in an embodiment of this specification. Figure 3 As shown, assuming that the audit task is to audit that no red envelope related text and prompts appear in the display page, the audit object can be each display page, and the preset audit rule can be an audit rule set to identify the red envelope related text and prompts in the page. Assuming that the preset audit rule includes atomic algorithm 302, atomic algorithm 304 and atomic algorithm 306, as shown in FIG. Figure 3 As shown, the execution order of each atomic algorithm can be represented in the directed acyclic graph. In the embodiment of this specification, three operator algorithms can be executed according to the front-back dependency relationship represented by the directed acyclic graph. Different audit objects may use different atomic algorithms.

[0097] Assume that the atomic algorithm 302 is an algorithm for OCR recognition of cv.common.ocr images; the atomic algorithm 304 is an algorithm for nlp.match.kfc keyword matching; and the atomic algorithm 306 is an algorithm for cv.extract.template image template recognition. When the audit object 300 is a picture, the atomic algorithm 306 can be used to identify the picture, determine whether the audit object contains a picture representing a red envelope, and obtain the audit result 308. The audit method of the audit object can include the atomic algorithm 306; when the audit object 300 is a picture and there is text in the picture, the atomic algorithm 302 can be used to identify the text in the audit object, and then the atomic algorithm 304 can be used to perform keyword comparison to determine whether the audit object contains text information representing a red envelope, and obtain the audit result 308. The audit method of the audit object can include the atomic algorithm 302 and the atomic algorithm 304; when the audit object 300 is text, the atomic algorithm 304 can be used to perform keyword comparison to determine whether the audit object contains text information representing a red envelope, and obtain the audit result 308. The audit method of the audit object can include the atomic algorithm 304.

[0098] Understandably, Figure 3 This is only an exemplary description, and the specific structure of the directed acyclic graph is set according to actual needs and is not specifically limited here.

[0099] In actual applications, the audit object set may include multiple audited objects using the same audit method. In order to make the sample inspection objects more representative and more valuable for random inspection, the embodiments of this specification may select the sample inspection objects based on the audit time of the audited objects.

[0100] As an implementation manner, the first audited object set in the embodiment of this specification includes multiple audited objects;

[0101] The extracting of the second audited object set corresponding to each audit method specifically includes:

[0102] Determine the audit time of each audited object in the first audited object set; the audit time is the time taken to audit the audited object using the preset audit rule;

[0103] sorting the audited objects in the first audited set according to the auditing time;

[0104] Select the audited objects whose sorting positions match the preset sorting positions as the sampling objects.

[0105] In actual applications, more complex audit objects may require a longer audit time, and more complex audit objects can better verify the accuracy of preset audit rules; or, the audit time for some audit objects may be longer due to the preset audit rules themselves and other reasons. The audit objects that take a long time to audit may also reflect the performance of the preset audit rules.

[0106] In the embodiment of the present specification, the audit time of each audited object can be recorded, and the audited objects in the first audited set can be sorted in descending order of audit time, and the audited objects ranked in the first few positions can be selected as the sampling objects.

[0107] Similarly, the audit time can be sorted from short to long, and the audited objects ranked in the last few places can be selected as the objects for random inspection. The specific sorting method is not limited in the embodiments of this specification.

[0108] In actual applications, for audited objects with the same auditing time, they can be further sorted according to the time when they were audited. For example, audited objects that are closer to the current time can be sorted in front of audited objects that are farther away from the current time. Newer audited objects are given priority, which is conducive to verifying the adaptability of preset audit rules.

[0109] It is understandable that the "first", "second", "third" and "fourth" mentioned in the embodiments of this specification are only named for the purpose of clarity and have no special meaning. The method for determining the fourth audited object set can also be similar to the method for determining the second audited object set from the first audited object set. Specifically, in the embodiments of this specification, the third audited object set can include multiple audited objects;

[0110] The extracting of the fourth audited object set corresponding to each audit method may specifically include:

[0111] Determine the audit time of each audited object in the third audited object set; the audit time is the time taken to audit the audited object using the preset audit rule;

[0112] sorting the audited objects in the third audited set according to the auditing time;

[0113] Select the audited objects whose sorting positions match the preset sorting positions as the sampling objects.

[0114] The audit time can be sorted from short to long or from long to short, and a preset number of audited objects ranked later or earlier can be selected as the sampling objects. The preset number can also be positively correlated with the number of atomic algorithms included in the audit method corresponding to the third audited object set.

[0115] To more clearly illustrate a method for screening sampling objects provided in an embodiment of this specification, Figure 4 A swimming lane diagram of a method for screening a sample object provided in an embodiment of this specification. Figure 4 As shown, the scheme may include a data acquisition phase, an extraction phase, and a result processing phase, specifically:

[0116] Step 402: The audited objects may be stored in the data storage unit.

[0117] In practical applications, the data storage unit may be associated with the audit unit and used to store the audit object and audit result of the audit unit. The audit unit may be a functional unit that audits the audit object using preset audit rules.

[0118] Step 404: The sampling unit may obtain an audit object set including a number of audited objects.

[0119] The sampling unit may be a functional unit that extracts sampling objects from the audited objects. In practical applications, the sampling unit may also be a platform or server with a sampling function.

[0120] Step 406: Determine the audit method information of each audited object.

[0121] The data storage unit may also store the situations of each atomic algorithm used by each audited object. For example, the identifier of each atomic algorithm used by each audited object may be recorded, and the sampling unit may determine the audit method used by each audited object based on the identifier.

[0122] Step 408: According to the audit method information of each audited object, count the audited objects corresponding to each audit method to obtain a first audited object set corresponding to each audit method.

[0123] In practical applications, audited objects that use the same audit method can be divided into a set.

[0124] Step 410: extracting a number of audited objects from the first audited object set corresponding to each audit method to obtain a second audited object set corresponding to each audit method.

[0125] Each of the audit methods may correspond to a first audited object set, and different audit methods may correspond to different audited objects in the first audited object set.

[0126] Step 412: Use the audited objects in the second audited object set as sampling objects.

[0127] In practical applications, a preset number of audited objects can be extracted from audited objects using the same audit method as sampling inspection objects, and then a certain number of audited objects can be extracted as sampling inspection objects for each different audit method.

[0128] In actual applications, the sampled inspection objects can be provided to the manual review platform for further verification of the audited objects through manual review, and the accuracy of the preset audit rules can also be verified. When problems are found, the preset audit rules can also be adjusted.

[0129] Based on the same idea, the embodiments of this specification also provide a device corresponding to the above method. Figure 5 This is a schematic diagram of a device for screening a sample object provided in an embodiment of this specification. Figure 5 As shown, the device may include:

[0130] The object acquisition module 502 is used to acquire an audit object set including a plurality of audited objects; the audited objects are audited according to preset audit rules; the preset audit rules include a plurality of audit methods;

[0131] The information determination module 504 is used to determine the audit method information of each audited object; the audit method information is used to indicate the audit method used by the audited object during the audit process;

[0132] The object extraction module 506 is used to extract the audited objects corresponding to each audit method from the audit object set according to the audit method information of each audited object.

[0133] Based on the same idea, the embodiments of this specification also provide a device corresponding to the above method.

[0134] Figure 6 This is a schematic diagram of a screening device for sampling objects provided in an embodiment of this specification. Figure 5 As shown, the device 600 may include:

[0135] at least one processor 610; and,

[0136] A memory 630 is communicatively connected to the at least one processor; wherein,

[0137] The memory 630 stores instructions 620 executable by the at least one processor 610. The instructions are executed by the at least one processor 610 to enable the at least one processor 610 to:

[0138] Acquire an audit object set including a plurality of audited objects; the audited objects are audited according to preset audit rules; the preset audit rules include a plurality of audit methods;

[0139] Determine the audit method information of each audited object; the audit method information is used to indicate the audit method used by the audited object during the audit process;

[0140] According to the audit method information of each audited object, the audited objects corresponding to each audit method are extracted from the audit object set.

[0141] Based on the same idea, the embodiment of this specification also provides a computer-readable medium corresponding to the above method. The computer-readable medium stores computer-readable instructions, and the computer-readable instructions can be executed by a processor to implement a method for screening sampling objects.

[0142] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. Figure 6 As for the device shown, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0143] In the 1990s, it was very clear whether the improvement of a technology was a hardware improvement (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or a software improvement (improvement of the method flow). However, with the development of technology, many improvements in the method flow today can be regarded as direct improvements in the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented with a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming themselves, without having to ask chip manufacturers to design and produce dedicated integrated circuit chips. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0144] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0145] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0146] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0147] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0148] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0149] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0150] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0151] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0152] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0153] Computer readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0154] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity or device including the element.

[0155] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0156] The present application may be described in the general context of computer executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0157] The above description is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present application shall be included in the scope of the claims of the present application.

Claims

1. A method for screening sampling objects, comprising: Get an audit object collection containing several audited objects; The audited object is audited according to preset audit rules; the preset audit rules include several audit methods; the preset audit rules include multiple atomic algorithms; the audit method includes at least one of the atomic algorithms; Determine the audit method information of each audited object; the audit method information is used to indicate the audit method used by the audited object during the audit process; According to the audit method information of each audited object, the audited objects corresponding to each audit method are extracted from the audit object set.

2. According to the method of claim 1, the step of determining the audit method information of each audited object specifically comprises: Determine the atomic algorithms used by each audited object during the audit process.

3. According to the method of claim 2, the step of determining each atomic algorithm used by each audited object during the audit process specifically comprises: Obtain the rule triggering identifier corresponding to each audited object; The rule triggering identifier is used to indicate that the atomic algorithm corresponding to the rule triggering identifier in the preset audit rule is used in the process of auditing each audited object; Based on the rule triggering identifier, it is determined that each of the audited objects uses each of the atomic algorithms during the audit process.

4. The method according to claim 1, wherein extracting audited objects corresponding to each audit method from the audit object set specifically comprises: According to the audit method information of each audited object, count the audited objects corresponding to each audit method to obtain a first audited object set corresponding to each audit method; A second set of audited objects corresponding to each audit method is extracted from the first set of audited objects corresponding to each audit method; the second set of audited objects is a subset of the first set of audited objects.

5. The method according to claim 4, wherein the second audited object set includes a preset number of audited objects.

6. The method according to claim 1, wherein extracting audited objects of each audit method from the audit object set comprises: Determine each audit method included in the preset audit rules; According to the audit method information of each audited object, count the audited objects corresponding to each audit method included in the preset audit rule to obtain a third audited object set corresponding to each audit method; A fourth set of audited objects corresponding to each audit method is extracted from the third set of audited objects corresponding to each audit method; the fourth set of audited objects is a subset of the third set of audited objects.

7. According to the method of claim 6, the rule file carrying the preset audit rule is a file containing a table; one of the row field and the column field in the table represents the atomic algorithm included in the preset audit rule, and the other field represents the audit method included in the preset audit rule; The determination of each audit method included in the preset audit rule specifically includes: Based on the rule file, various audit methods included in the preset audit rules are determined.

8. The method according to claim 1, further comprising: Obtain a directed acyclic graph corresponding to the preset audit rule; the nodes in the directed acyclic graph represent the atomic algorithms in the preset audit rule; the lines in the directed acyclic graph represent the execution order of two adjacent atomic algorithms in the preset audit rule; Based on the directed acyclic graph, each atomic algorithm included in the preset audit rule is determined.

9. The method according to claim 4, wherein the first audited object set includes a plurality of audited objects; The extracting of the second audited object set corresponding to each audit method specifically includes: Determine the audit time of each audited object in the first audited object set; the audit time is the time taken to audit the audited object using the preset audit rule; sorting the audited objects in the first audited set according to the auditing time; Select the audited objects whose sorting positions match the preset sorting positions as the sampling objects.

10. The method according to claim 5, wherein the preset number is positively correlated with the number of atomic algorithms included in the audit method corresponding to the second audited object set.

11. A screening device for sampling objects, comprising: An object acquisition module, used to acquire an audit object set including a number of audited objects; The audited object is audited according to preset audit rules; the preset audit rules include several audit methods; the preset audit rules include multiple atomic algorithms; the audit method includes at least one of the atomic algorithms; An information determination module is used to determine the audit method information of each audited object; The audit method information is used to indicate the audit method used by the audited object during the audit process; The object extraction module is used to extract the audited objects corresponding to each audit method from the audit object set according to the audit method information of each audited object.

12. A screening device for sampling objects, comprising: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: Acquire an audit object set including a plurality of audited objects; the audited objects are audited according to preset audit rules; the preset audit rules include a plurality of audit methods; the preset audit rules include a plurality of atomic algorithms; the audit methods include at least one of the atomic algorithms; Determine the audit method information of each audited object; the audit method information is used to indicate the audit method used by the audited object during the audit process; According to the audit method information of each audited object, the audited objects corresponding to each audit method are extracted from the audit object set.

13. A computer-readable medium having computer-readable instructions stored thereon, wherein the computer-readable instructions can be executed by a processor to implement the method for screening sampling objects according to any one of claims 1 to 10.