CN113128390B

CN113128390B - Sampling inspection method, sampling inspection device, electronic equipment and storage medium

Info

Publication number: CN113128390B
Application number: CN202110404201.8A
Authority: CN
Inventors: 黄真
Original assignee: Beijing QIYI Century Science and Technology Co Ltd
Current assignee: Beijing QIYI Century Science and Technology Co Ltd
Priority date: 2021-04-14
Filing date: 2021-04-14
Publication date: 2023-06-30
Anticipated expiration: 2041-04-14
Also published as: CN113128390A

Abstract

The embodiment of the invention relates to a sampling inspection method, a sampling inspection device, electronic equipment and a storage medium, which comprise the following steps: when determining that sampling rechecking is carried out on a plurality of inspected objects corresponding to at least one target initial inspection party, determining initial inspection effect index values of all the target initial inspection parties; determining a target sampling rate corresponding to each target primary inspection party according to the primary inspection effect index value of each target primary inspection party, the number of primary inspected objects corresponding to each target primary inspection party and the preconfigured total rechecking capacity; sampling the primary inspected objects corresponding to the target primary inspection parties according to the target sampling rate corresponding to the target primary inspection parties so as to carry out rechecking on sampling results by rechecking parties. Therefore, the final false detection rate can be reduced and the accuracy of the final detection result can be improved while the duplicate detection party resources are reasonably allocated.

Description

Sampling inspection method, sampling inspection device, electronic equipment and storage medium

Technical Field

The embodiment of the invention relates to the technical field of data processing, in particular to a sampling inspection method, a sampling inspection device, electronic equipment and a storage medium.

Background

The content auditing work of the video website mainly has two purposes, namely compliance and copyright, wherein the compliance problem relates to a wide range, and a large amount of auditing work is needed. In order to ensure that the video content released by the video website is free of risk, after the primary inspection of the video, a rechecking party with more experience is usually arranged to recheck the primary inspected video.

Currently, when a video that has been subjected to primary inspection is subjected to secondary inspection, a full-scale secondary inspection or sampling secondary inspection at a fixed sampling rate is generally adopted. However, the full-quantity reinspection clearly occupies a large amount of reinspection resources, and when the reinspection resources are insufficient, the large reinspection pressure is faced; the sampling and rechecking mode according to the fixed sampling rate can lead to random probability of rechecking objects which are in charge of the initial inspection by different initial inspection parties, has unfairness and obviously has insufficient rechecking coverage on risk objects.

Disclosure of Invention

In view of the above, in order to solve the technical problems that the total re-inspection is likely to face insufficient re-inspection resources, resulting in larger re-inspection pressure, and the sampling re-inspection according to the fixed sampling rate results in random probability of re-inspection of objects in charge of primary inspection of different primary inspection parties, unfairness exists, and the re-inspection coverage of risk objects is obviously insufficient, the embodiment of the invention provides a sampling inspection method, a device, electronic equipment and a storage medium.

In a first aspect, an embodiment of the present invention provides a sampling inspection method, including:

when determining that sampling rechecking is carried out on a plurality of inspected objects corresponding to at least one target initial inspection party, determining initial inspection effect index values of all the target initial inspection parties;

determining a target sampling rate corresponding to each target primary inspection party according to the primary inspection effect index value of each target primary inspection party, the number of primary inspected objects corresponding to each target primary inspection party and the preconfigured total rechecking capacity;

Sampling the primary inspected objects corresponding to the target primary inspection parties according to the target sampling rate corresponding to the target primary inspection parties so as to carry out rechecking on sampling results by rechecking parties.

In one possible implementation manner, the determining to sample and recheck the plurality of primary inspected objects corresponding to the at least one target primary inspector includes:

comparing the total number of the plurality of primary inspected objects corresponding to the at least one target primary inspected party with the preconfigured total capacity of the re-inspection;

and if the total number is larger than the total recheck capacity, determining to sample and recheck a plurality of initial inspected objects corresponding to at least one target initial inspection party.

In one possible implementation manner, the determining the target sampling rate corresponding to each target primary party according to the primary-detection effect index value of each target primary party, the number of primary-detected objects corresponding to each target primary party, and the preconfigured total recheck capacity includes:

determining initial sampling rate corresponding to each target primary detection party according to the primary detection effect index value of each target primary detection party;

determining whether the initial sampling rate corresponding to each target primary detection party meets a first setting condition according to the number of primary detection objects corresponding to each target primary detection party and the preset total recheck capacity;

If yes, determining the initial sampling rate corresponding to each target primary detection party as the target sampling rate corresponding to each target primary detection party;

if the initial sampling rate is not met, carrying out iterative adjustment on the initial sampling rate corresponding to each target primary detection party according to a set iterative adjustment mode, stopping iteration until the first set condition is met, and determining the target sampling rate corresponding to each target primary detection party according to the initial sampling rate currently corresponding to each target primary detection party after the iteration is finished.

In one possible embodiment, the preliminary examination effect index value includes a first preliminary examination effect index value, and the determining an initial sampling rate corresponding to each target preliminary examination party according to the preliminary examination effect index value of each preliminary examination party includes:

for each target primary inspection party, searching a sampling rate corresponding to a first primary inspection effect index value of the target primary inspection party from a preset first sampling rate configuration table, wherein the first sampling rate configuration table comprises a corresponding relation between the first primary inspection effect index value and the sampling rate;

and determining the initial sampling rate corresponding to the target primary detection party according to the sampling rate corresponding to the first primary detection effect index value of the target primary detection party.

In one possible implementation manner, the primary detection effect index value further includes a second primary detection effect index value, and the determining, according to the found sampling rate corresponding to the first primary detection effect index value of the target primary detection party, the initial sampling rate corresponding to the target primary detection party includes:

if the second primary detection effect index value of the target primary detection party meets a second set condition, determining the found sampling rate corresponding to the first primary detection effect index value of the target primary detection party as the initial sampling rate corresponding to the target primary detection party;

and if the second primary detection effect index value of the target primary detection party meets a third set condition, determining the initial sampling rate corresponding to the target primary detection party according to a preset sampling rate calculation formula and the searched sampling rate corresponding to the first primary detection effect index value of the target primary detection party.

In one possible implementation manner, the determining whether the initial sampling rate corresponding to each target primary party meets the first setting condition according to the number of the primary inspected objects corresponding to each target primary party and the preconfigured total recheck capacity includes:

determining a first estimated total amount of all the target primary inspection parties according to the initial sampling rate corresponding to each target primary inspection party and the number of the corresponding primary inspected objects;

Comparing the first estimated total recheck amount with a first value and a second value, wherein the first value is the difference value between the total recheck amount and a set value, and the second value is the sum value of the total recheck amount and the set value;

if the first estimated total amount is larger than or equal to the first value and smaller than or equal to the second value, determining that the initial sampling rate corresponding to each target primary detection party meets a first setting condition;

if the first estimated total review is smaller than the first value or larger than the second value, determining that the initial sampling rate corresponding to each target primary party does not meet a first setting condition.

In one possible implementation manner, the iteratively adjusting the initial sampling rate corresponding to each target primary detection party according to the set iterative adjustment manner until the first set condition is met, includes:

determining an adjusting coefficient in the iterative process according to the total recheck capacity and the total current first estimated recheck amount of all the target primary check parties;

multiplying the initial sampling rate corresponding to the target primary detection party currently by the adjustment coefficient aiming at each target primary detection party to obtain the initial sampling rate corresponding to the target primary detection party in the iterative process;

Determining a first estimated total amount of rechecks corresponding to all the target primary inspection parties in the current iteration process according to the number of the primary inspected objects corresponding to each target primary inspection party and the initial sampling rate corresponding to the current iteration process;

comparing the first estimated total recheck amount corresponding to all the target primary inspection parties in the iterative process with the first value and the second value;

if the first estimated total amount of the first rechecks corresponding to all the target initial detection parties in the iterative process is larger than or equal to the first value and smaller than or equal to the second value, determining that the initial sampling rate currently corresponding to each target initial detection party meets a first setting condition, and stopping iteration;

and if the comparison shows that the total amount of the first estimated rechecks corresponding to all the target initial inspection parties in the current iteration process is smaller than the first value or larger than the second value, returning to execute the step of determining the adjustment coefficient in the current iteration process according to the total recheck capacity and the total amount of the first estimated rechecks corresponding to all the target initial inspection parties so as to enter the next iteration process.

In one possible implementation manner, when the comparison shows that the total amount of the first estimated review corresponding to all the target primary checkpoints in the current iteration process is greater than the second value, the determining the adjustment coefficient in the current iteration process according to the total review capacity and the total current first estimated review of all the target primary checkpoints includes:

Dividing the total recheck capacity by the total current first estimated recheck capacity of all the target primary check parties to obtain an adjustment coefficient in the iterative process.

In one possible implementation manner, when the comparison shows that the total amount of first estimated review corresponding to all the target primary checkpoints in the current iteration process is smaller than the first value, the determining the adjustment coefficient in the current iteration process according to the total review capacity and the total current first estimated review of all the target primary checkpoints includes:

determining the target primary detection party with the current corresponding initial sampling rate of 1 as a first primary detection party;

determining second estimated total amounts of all the first primary inspection parties according to the number of the primary inspected objects corresponding to the first primary inspection parties and the initial sampling rate corresponding to the current primary inspection parties;

subtracting the second estimated total re-detection capacity from the total re-detection capacity to obtain a first difference value; subtracting the second estimated total amount from the first estimated total amount to obtain a second difference;

and dividing the first difference value by the second difference value to obtain an adjustment coefficient in the iterative process.

In one possible embodiment, before the method, the method further comprises:

Determining a plurality of primary check parties triggering primary check operation in a set historical time period;

and determining the primary detection party of which the primary detection party information exists in a preconfigured detection group as the target primary detection party, wherein the detection group comprises a plurality of primary detection party information, the primary detection parties in the same detection group are responsible for carrying out primary detection on the same type of object, the primary detection parties in different detection groups are responsible for carrying out primary detection on different types of object, and the total re-detection capacity corresponding to different detection groups is different.

In a second aspect, an embodiment of the present invention provides a sampling test apparatus, including:

the index value determining module is used for determining the primary detection effect index value of each target primary detection party when determining that sampling re-detection is carried out on a plurality of primary detection objects corresponding to at least one target primary detection party;

the sampling rate determining module is used for determining the target sampling rate corresponding to each target primary party according to the primary detection effect index value of each target primary party, the number of primary detection objects corresponding to each target primary party and the preconfigured total recheck capacity;

and the sampling detection module is used for sampling the primary detection objects corresponding to the target primary detection parties according to the target sampling detection rate corresponding to the target primary detection parties so as to carry out rechecking on sampling results by a rechecking party.

In one possible embodiment, the apparatus further comprises:

the first comparison module is used for comparing the total number of the plurality of primary detection objects corresponding to at least one target primary detection party with the preconfigured total capacity of the repeated detection;

and the sampling determining module is used for determining sampling and rechecking a plurality of primary detection objects corresponding to at least one target primary detection party if the total number is larger than the total rechecking capacity.

In one possible embodiment, the spot check rate determination module includes:

the first determining submodule is used for determining initial sampling rate corresponding to each target primary party according to the primary detection effect index value of each target primary party;

the second determining submodule is used for determining whether the initial sampling rate corresponding to each target primary party meets a first setting condition according to the number of the primary inspected objects corresponding to each target primary party and the preset total rechecking capacity;

the third determining sub-module is used for determining the initial sampling rate corresponding to each target primary detection party as the target sampling rate corresponding to each target primary detection party if the initial sampling rate corresponding to each target primary detection party meets a first setting condition;

The iteration sub-module is used for carrying out iteration adjustment on the initial sampling rate corresponding to each target primary party according to a set iteration adjustment mode if the initial sampling rate corresponding to each target primary party does not meet a first set condition, and stopping iteration until the first set condition is met;

and the fourth determination submodule is used for determining the target sampling rate corresponding to each target primary party according to the initial sampling rate currently corresponding to each target primary party after iteration is finished.

In a possible implementation manner, the preliminary examination effect index value includes a first preliminary examination effect index value, and the first determination submodule is specifically configured to:

for each target primary inspection party, searching a sampling rate corresponding to a first primary inspection effect index value of the target primary inspection party from a preset first sampling rate configuration table, wherein the first sampling rate configuration table comprises a corresponding relation between the first primary inspection effect index value and the sampling rate; and determining the initial sampling rate corresponding to the target primary detection party according to the sampling rate corresponding to the first primary detection effect index value of the target primary detection party.

In one possible embodiment, the preliminary examination effect index value further includes a second preliminary examination effect index value, and the first determination submodule is further configured to:

In one possible embodiment, the second determining submodule is specifically configured to:

determining a first estimated total amount of all the target primary inspection parties according to the initial sampling rate corresponding to each target primary inspection party and the number of the corresponding primary inspected objects; comparing the first estimated total recheck amount with a first value and a second value, wherein the first value is the difference value between the total recheck amount and a set value, and the second value is the sum value of the total recheck amount and the set value; if the first estimated total amount is larger than or equal to the first value and smaller than or equal to the second value, determining that the initial sampling rate corresponding to each target primary detection party meets a first setting condition; if the first estimated total review is smaller than the first value or larger than the second value, determining that the initial sampling rate corresponding to each target primary party does not meet a first setting condition.

In one possible implementation, the iteration sub-module is specifically configured to:

determining an adjusting coefficient in the iterative process according to the total recheck capacity and the total current first estimated recheck amount of all the target primary check parties; multiplying the initial sampling rate corresponding to the target primary detection party currently by the adjustment coefficient aiming at each target primary detection party to obtain the initial sampling rate corresponding to the target primary detection party in the iterative process; determining a first estimated total amount of rechecks corresponding to all the target primary inspection parties in the current iteration process according to the number of the primary inspected objects corresponding to each target primary inspection party and the initial sampling rate corresponding to the current iteration process; comparing the first estimated total recheck amount corresponding to all the target primary inspection parties in the iterative process with the first value and the second value; if the first estimated total amount of the first rechecks corresponding to all the target initial detection parties in the iterative process is larger than or equal to the first value and smaller than or equal to the second value, determining that the initial sampling rate currently corresponding to each target initial detection party meets a first setting condition, and stopping iteration; and if the comparison shows that the total amount of the first estimated rechecks corresponding to all the target initial inspection parties in the current iteration process is smaller than the first value or larger than the second value, returning to execute the step of determining the adjustment coefficient in the current iteration process according to the total recheck capacity and the total amount of the first estimated rechecks corresponding to all the target initial inspection parties so as to enter the next iteration process.

In one possible implementation manner, in a case that the total amount of the first estimated review corresponding to the target primary detection party in the current iteration process is greater than the second value, the iteration sub-module is further configured to:

In one possible implementation manner, in a case that the total amount of first estimated review corresponding to all the target primary checkpoints in the current iteration process is compared to be smaller than the first value, the iteration sub-module is further configured to:

determining the target primary detection party with the current corresponding initial sampling rate of 1 as a first primary detection party; determining second estimated total amounts of all the first primary inspection parties according to the number of the primary inspected objects corresponding to the first primary inspection parties and the initial sampling rate corresponding to the current primary inspection parties; subtracting the second estimated total re-detection capacity from the total re-detection capacity to obtain a first difference value; subtracting the second estimated total amount from the first estimated total amount to obtain a second difference; and dividing the first difference value by the second difference value to obtain an adjustment coefficient in the iterative process.

In one possible embodiment, the apparatus further comprises:

the primary detection party determining module is used for determining a plurality of primary detection parties triggering primary detection operation in a set history time period;

the target determining module is used for determining the primary detection party with the primary detection party information existing in the preconfigured detection group as the target primary detection party, wherein the detection group comprises a plurality of primary detection party information, the primary detection party in the same detection group is responsible for carrying out primary detection on the same type of object, the primary detection party in different detection groups is responsible for carrying out primary detection on different types of object, and the total re-detection capacity corresponding to different detection groups is different.

In a third aspect, an embodiment of the present invention provides an electronic device, including: the system comprises a processor and a memory, wherein the processor is used for executing a sampling inspection program stored in the memory so as to realize the sampling inspection method of any one of the first aspect.

In a fourth aspect, an embodiment of the present invention provides a storage medium storing one or more programs executable by one or more processors to implement the spot check method of any one of the first aspects.

According to the technical scheme provided by the embodiment of the invention, when the sampling and re-inspection are carried out on a plurality of primary inspected objects corresponding to at least one target primary inspection party, the primary inspection effect index value of each target primary inspection party is determined, the target sampling rate corresponding to each target primary inspection party is determined according to the primary inspection effect index value of each target primary inspection party, the number of primary inspected objects corresponding to each target primary inspection party and the pre-configured total re-inspection capacity, the primary inspected objects corresponding to each target primary inspection party are sampled according to the target sampling rate corresponding to each target primary inspection party, so that the re-inspection is carried out on the sampling result by the re-inspection party, and the target sampling rate corresponding to each target primary inspection party is intelligently determined according to the primary inspection effect index value of each target primary inspection party, the number of primary inspected objects corresponding to each target primary inspection party and the pre-configured total re-inspection capacity. Because the target spot check rate is related to the initial check effect index value and the total re-check capacity of the target initial check party, the re-check coverage rate of each target initial check party is reasonably determined according to the initial check quality of the target initial check party while reasonably allocating the re-check party resources, so that the target initial check party can not only fairly sample the re-check, but also set a lower spot check rate for the target initial check party with higher initial check quality, and set a higher spot check rate for the target initial check party with lower initial check quality, thereby effectively ensuring the re-check coverage rate of a risk object, further reducing the final false check rate and improving the accuracy of a final check result.

Drawings

FIG. 1 is a flowchart of an embodiment of a sampling inspection method according to an embodiment of the present invention;

FIG. 2 is a flowchart of another embodiment of a sampling inspection method according to an embodiment of the present invention;

FIG. 3 is a flowchart of an embodiment of a method for spot check according to an embodiment of the present invention;

FIG. 4 is a flowchart of an embodiment of a method for spot check according to an embodiment of the present invention;

FIG. 5 is a block diagram of an embodiment of a sampling test device according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

In order to facilitate understanding of the embodiments of the present invention, an exemplary description is first made below of an application scenario of the sampling inspection method provided by the embodiments of the present invention.

In an exemplary application scenario, to ensure compliance and copyrights of video content published by a video website, the video on the video website may be audited. Further, to ensure that the video content published by the video website is risk-free, after the primary inspection of the video, a review party with more experience is usually arranged to review the primary inspected video. Here, the primary party may be a user or a machine learning model, and similarly, the review party may also be a user or a machine learning model.

In another exemplary application scenario, to ensure compliance and quality of service for customer service, the customer service process, such as call recording, chat recording, etc., may be audited. Similarly, after the primary inspection of the customer service process, the primary inspection party usually arranges a recheck party with more experience to recheck the call record, chat record, etc. that have been subjected to the primary inspection.

Currently, in the above exemplary application scenario, when the primary inspected object (for example, video, call recording, chat recording, etc.) is subjected to review, a full-scale review or sampling review at a fixed sampling rate is generally adopted.

However, the full-quantity reinspection clearly occupies a large amount of reinspection resources, and when the reinspection resources are insufficient, the large reinspection pressure is faced; the sampling and rechecking mode according to the fixed sampling rate can lead to random probability of rechecking objects which are in charge of the initial inspection by different initial inspection parties, has unfairness and obviously has insufficient rechecking coverage on risk objects.

Based on the above, the embodiment of the invention provides a sampling inspection method. The method provided by the embodiments of the present invention will be further explained with reference to the drawings, and the embodiments do not limit the embodiments of the present invention.

Referring to fig. 1, a flowchart of an embodiment of a sampling inspection method is provided in an embodiment of the present invention. As one example, the method may be applied to a review system, where the review system may include one or more electronic devices, as the invention is not limited in this regard. As shown in fig. 1, the method may include the steps of:

step 101, determining a primary detection effect index value of each target primary detection party when determining to sample and re-detect a plurality of primary detection objects corresponding to at least one target primary detection party.

In the embodiment of the invention, the primary inspected object corresponding to the primary inspection party refers to an object subjected to primary inspection operation by the primary inspection party. Here, the object may be, for example, video, call recording, chat recording, or the like.

In application, after the primary inspection is completed, the primary inspected object or related information of the primary inspected object, such as an object identifier, may be submitted to the review system, so that the review system can detect multiple primary inspection parties that trigger the primary inspection operation within a set historical time period (e.g., within 1 day).

In the embodiment of the invention, after detecting a plurality of primary detection parties triggering primary detection operation in a set historical time period, the rechecking system can determine at least one target primary detection party from the plurality of primary detection parties, and then recheck a plurality of primary detected objects corresponding to the at least one target primary detection party.

As one embodiment, the review system determines each of the plurality of primary checkpoints as a target primary checkpoint.

As another embodiment, taking a video auditing scenario as an example, the video can be divided into two types of long video and short video in the time dimension, and the video can be divided into multiple types of child animation, military video, action video, animal video and the like in the content dimension. Further, in application, in order to improve efficiency and accuracy of video auditing, different primary inspection groups and review groups (hereinafter referred to as inspection groups) are generally configured for different types of videos, and personnel in the same inspection group are specially responsible for auditing the same type of video, and personnel in different inspection groups are responsible for inspecting different types of videos.

In this case, in a case where a review of an object of a certain type is specified, among the above-described plurality of primary inspection parties, a primary inspection party belonging to a test group corresponding to the specified type (hereinafter referred to as a specified type) is specified as a target primary inspection party, and subsequently, a review of a plurality of primary inspected objects corresponding to the target primary inspection party corresponds to a review of a primary inspected object of the specified type.

In the embodiment of the invention, after the target primary detection party is determined, whether full-quantity re-detection or sampling re-detection is carried out on the primary detection object corresponding to the target primary detection party can be determined first. Specifically, the rechecking system may determine the total number of the plurality of primary inspected objects (denoted as C for convenience of description) corresponding to all the target primary inspected parties, and then compare the total number with a preconfigured total rechecking capacity (denoted as Q for convenience of description), where the total rechecking capacity refers to: the total review amount that can be borne by all the review parties in the set time, for example, the total review capacity is 1000, means that all the review parties can review at most 1000 primary objects in the set time. The review party may be a user or a machine learning model.

Further, as an embodiment, in the case of configuring different test groups for different types of objects, because the retests in the different test groups are different, the total retests that different test groups can afford in the same time is different, for example, the total retests that one test group can afford in a specified time is 800, and the total retests that another test group can afford in the same specified time is 1000. That is, different test groups may correspond to different total retests, and thus, the total retests compared with the total number of the plurality of primary test objects described above refers to the total retests corresponding to the test group to which the target primary test party belongs.

If C is less than or equal to Q, the resources of the recheck party are sufficient, and the recheck of all the primary inspected objects can be satisfied, so that when C is less than or equal to Q, the total recheck of a plurality of primary inspected objects corresponding to all the target primary inspected parties can be determined, that is, the sampling rate corresponding to each target primary inspected party is determined to be 1.

Conversely, if C > Q is compared, this means that the recheck-side resource is insufficient to recheck all the primary inspected objects, and therefore, if C > Q is compared, it is possible to determine to sample and recheck a plurality of primary inspected objects corresponding to at least one target primary inspected side.

In the embodiment of the invention, when sampling and rechecking is determined for a plurality of inspected objects corresponding to at least one target primary inspection party, the primary inspection effect index value of each target primary inspection party is determined. Here, the preliminary examination effect index value includes, but is not limited to: false detection rate, first-order false detection rate, etc. The false detection rate refers to the proportion of objects that are considered to be legal (or that are considered to contain no forbidden information) by mistake to all objects that are not legal (contain forbidden information). The first-level false detection rate refers to the proportion of objects that are mistaken for compliance (or mistaken for not containing forbidden information) to all objects that are severely non-compliance (or contain severely forbidden information).

As one example, the re-inspection system may determine a preliminary inspection effect index value for each target primary inspection party based on the primary inspection operation of each target primary inspection party over a recent period of time, such as the last 7 days. By this processing, the primary inspection effect index value determined in this step 101 can be made to truly reflect the current primary inspection quality of the target primary inspection party.

Step 102, determining the target sampling rate corresponding to each target primary inspection party according to the primary inspection effect index value of each target primary inspection party, the number of primary inspected objects corresponding to each target primary inspection party and the preconfigured total capacity of the secondary inspection.

As can be seen from the description in step 102, in the embodiment of the present invention, instead of regarding all primary inspection parties as a whole to use one sampling rate, the target sampling rate corresponding to each target primary inspection party is intelligently determined according to the primary inspection effect index value of each target primary inspection party, the number of primary inspected objects corresponding to each target primary inspection party, and the preconfigured total review capacity. Through the processing, the lower sampling rate can be set for the target primary detection party with higher primary detection quality, and the higher sampling rate can be set for the target primary detection party with lower primary detection quality, so that the final false detection rate is reduced and the accuracy of the final detection result is improved while the resources of the secondary detection party are reasonably allocated.

How to determine the target sampling rate corresponding to each target primary according to the primary detection effect index value of each target primary, the number of primary detected objects corresponding to each target primary, and the preconfigured total capacity of the secondary detection is described below by the embodiments shown in fig. 2 and 3, and is not described in detail herein.

And 103, sampling the primary inspected objects corresponding to the target primary inspection parties according to the target sampling rate corresponding to the target primary inspection parties so as to carry out rechecking on the sampling results by the rechecking parties.

As an embodiment, the rechecking system may extract, for each target primary, the identifier of the primary inspected object corresponding to the target primary according to the target sampling rate corresponding to the target primary, temporarily store the extracted identifier in the local memory space, and after completing the sampling operation for each target primary, obtain, in batch, the primary inspected object according to the identifier of the primary inspected object stored in the local memory space, so that the rechecking party rechecks the sampling result, that is, the obtained primary inspected object.

Referring to fig. 2, a flowchart of an embodiment of another sampling inspection method according to an embodiment of the present invention is provided. The flow shown in fig. 2 describes how to determine the target sampling rate corresponding to each target primary inspection party according to the primary inspection effect index value of each target primary inspection party, the number of primary inspected objects corresponding to each target primary inspection party, and the preconfigured total capacity of the secondary inspection, based on the flow shown in fig. 1. As shown in fig. 2, the process may include the steps of:

step 201, determining initial sampling rate corresponding to each target primary inspection party according to the primary inspection effect index value of each target primary inspection party.

As an embodiment, the first sampling rate configuration table may be configured in advance by the user, where the first sampling rate configuration table includes a correspondence between the first initial detection effect index value and the sampling rate. Here, the first preliminary detection effect index value may be, for example, a false detection rate, and the first preliminary detection effect index value and the sampling rate are in positive correlation, that is, the higher the false detection rate of the preliminary detection party is, the higher the sampling rate corresponding thereto is. Through the arrangement, the false detection rate of the primary detection party is higher, namely, the primary detection quality is poor, the re-detection force of the object responsible for the primary detection of the primary detection party is increased, the accuracy of the final detection result is ensured, and the false detection rate is reduced.

Accordingly, in this step 201, for each target primary inspection party, the sampling rate corresponding to the first primary inspection effect index value in the primary inspection effect index values of the target primary inspection party may be searched for from the preset first sampling rate configuration table, and the searched sampling rate corresponding to the first primary inspection effect index value of the target primary inspection party may be determined as the initial sampling rate corresponding to the target primary inspection party.

As another embodiment, in addition to the above embodiment, the preliminary examination effect index value further includes a second preliminary examination effect index value. Here, the second preliminary detection effect index value may be, for example, a first-level false detection rate, and it is understood that the higher the first-level false detection rate is, the more times the serious false detection event occurs to the preliminary detection party, and the worse the preliminary detection quality is. Accordingly, in this embodiment, the initial sampling rate obtained by the table look-up method may be further selectively adjusted according to the second primary-detection-effect index value of the target primary-detection party.

Specifically, if the second primary-inspection-effect index value of the target primary-inspection party satisfies the second setting condition, the found sampling rate corresponding to the first primary-inspection-effect index value of the target primary-inspection party may be determined as the initial sampling rate corresponding to the target primary-inspection party. Here, the second setting condition may be, for example, that the second preliminary detection effect index value is 0, or that the second preliminary detection effect index value is lower than a preset threshold value.

If the second primary detection effect index value of the target primary detection party meets the third setting condition, determining the initial sampling rate corresponding to the target primary detection party according to a preset sampling rate calculation formula and the searched sampling rate corresponding to the first primary detection effect index value of the target primary detection party. Here, the third setting condition may be, for example, that the second preliminary detection effect index value is greater than 0, or that the second preliminary detection effect index value is higher than a preset threshold value. Wherein, the calculation formula of the sampling rate is as follows:

P ₀ ＝P ₁ +N*α

in the above formula, P ₀ Represents the initial sampling rate, P ₁ The above-mentioned found sampling rate corresponding to the first primary-inspection effect index value of the target primary-inspection party is represented, N represents the second primary-inspection effect index value, and α is a number greater than 0, for example, 0.3.

The sampling rate calculation formula can be realized: when the second primary detection effect index value of the target primary detection party meets the third set condition, namely the number of times of serious false detection events of the target primary detection party is more, and the primary detection quality is poor, the initial sampling rate corresponding to the target primary detection party is properly increased, so that the re-detection force of the object responsible for primary detection of the target primary detection party can be increased, the accuracy of a final detection result is ensured, and the false detection rate is reduced.

Note that if the initial sampling rate calculated by the sampling rate calculation formula is greater than 1, 1 is determined as the initial sampling rate.

It should also be noted that the foregoing embodiment is merely an alternative implementation manner of determining the initial sampling rate, and in practical application, the initial sampling rate corresponding to the target primary party may also be determined by other manners. For example, as an embodiment, the user may configure a corresponding sampling rate for each primary party in advance according to the primary-inspection effect index of each primary party, so as to form a second sampling rate configuration table (including the correspondence between the primary-inspection party information and the sampling rate). Accordingly, in step 201, for each target primary inspection party, the sampling rate corresponding to the target primary inspection party may be searched from the preset second sampling rate configuration table, and the sampling rate corresponding to the target primary inspection party may be determined as the initial sampling rate corresponding to the target primary inspection party.

As another embodiment, in step 201, for each target primary party, the sampling rate corresponding to the target primary party may be searched from a preset second sampling rate configuration table, and if the sampling rate corresponding to the target primary party is searched, the searched sampling rate corresponding to the target primary party is determined as the initial sampling rate corresponding to the target primary party; if the sampling rate corresponding to the target primary inspection party is not found, searching the sampling rate corresponding to the first primary inspection effect index value from a preset first sampling rate configuration table according to the first primary inspection effect index value corresponding to the target primary inspection party, and determining the initial sampling rate corresponding to the target primary inspection party according to the searching result.

Step 202, determining whether an initial sampling rate corresponding to each target primary detection party meets a first setting condition according to the number of primary detection objects corresponding to each target primary detection party and a preset total re-detection capacity; if yes, go to step 203, if not, go to step 204.

In step 202, first, the first estimated total amount of the first target primary inspection is determined according to the initial sampling rate corresponding to each target primary inspection and the number of the first inspected objects corresponding to each target primary inspection, specifically, the first estimated total amount of the first target primary inspection is determined according to the following formula:

in the above formula, A represents a first estimated total amount, a _i Representing the number of primary inspected objects corresponding to the i-th target primary inspected party, P _{0_i} And the initial sampling rate corresponding to the ith target primary inspection party is represented.

The first estimated total retest amount is then compared to a first value, which may be the difference between the total retest amount and a set point (denoted as T), and a second value, which may be the sum of the total retest amount and the set point, which is a number greater than 0.

If the comparison shows that the total amount of the first estimated recheck is larger than or equal to the first value and smaller than or equal to the second value, namely Q-T is smaller than or equal to A is smaller than or equal to Q+T, the method means that if the initial inspected objects corresponding to the target primary inspection parties are sampled according to the initial sampling rate corresponding to the current of the target primary inspection parties, recheck party resources can meet rechecking of the sampled initial inspected objects, and accordingly it can be determined that the initial sampling rate corresponding to the current of the target primary inspection parties meets the first setting condition.

If the total amount of the first estimated recheck is smaller than the first value, namely A is smaller than or equal to Q-T, the method means that if the initial inspected objects corresponding to the target primary inspection parties are sampled according to the initial sampling rate corresponding to the current primary inspection parties, recheck party resources can meet the requirement of rechecking the initial inspected objects obtained by sampling, but recheck party resources cannot be fully utilized, and at the moment, it can be determined that the initial sampling rate corresponding to the current primary inspection parties does not meet the first setting condition.

If the total amount of the first estimated review is larger than the second value, namely A is larger than or equal to Q+T, the method means that if the initial inspected objects corresponding to the target primary inspection parties are sampled according to the initial sampling rate corresponding to the current primary inspection parties, the review party resources are insufficient, so that the review is subjected to larger pressure, and at the moment, the fact that the initial sampling rate corresponding to the current primary inspection parties does not meet the first setting condition can be determined.

And 203, determining the initial sampling rate corresponding to each target primary inspection party as the target sampling rate corresponding to each target primary inspection party.

In the embodiment of the invention, when the initial sampling rate corresponding to the current of each target primary inspection party is determined to meet the first setting condition, the initial sampling rate corresponding to the current of each target primary inspection party can be directly determined as the target sampling rate corresponding to each target primary inspection party based on the description.

And 204, performing iterative adjustment on the initial sampling rate corresponding to each target primary detection party according to a set iterative adjustment mode, and stopping iteration until a first set condition is met.

In the embodiment of the invention, when the initial sampling rate corresponding to each target primary inspection party currently does not meet the first setting condition, the initial sampling rate corresponding to each target primary inspection party currently can be adjusted based on the description so as to obtain the target sampling rate.

As an embodiment, when the current corresponding initial sampling rate of each target primary inspection party is adjusted, an iterative adjustment mode may be adopted, that is, each time the adjustment is performed, it is determined whether the current initial sampling rate meets the first set condition, if yes, iteration is stopped, if not, another adjustment is performed, and after the adjustment, it is determined whether the current initial sampling rate meets the first set condition, so that the iteration is performed until the initial sampling rate meets the first set condition.

When the first estimated total amount is smaller than the first value and the initial sampling rate corresponding to the current of each target primary inspection party is determined to not meet the first setting condition, the initial sampling rate corresponding to the current of each target primary inspection party can be increased, so that the resources of the secondary inspection party can be fully utilized. When the first estimated total amount is larger than the second value and the initial sampling rate corresponding to the current of each target primary inspection party is determined to not meet the first setting condition, the initial sampling rate corresponding to the current of each target primary inspection party can be reduced, so that the re-inspection pressure is reduced.

And 205, after the iteration is finished, determining the target sampling rate corresponding to each target primary party according to the initial sampling rate corresponding to each target primary party currently.

After iteration is finished, if the initial sampling rate corresponding to the current target primary detection party is greater than 1, determining 1 as the target sampling rate corresponding to the target primary detection party; if the initial sampling rate corresponding to the current of the target primary inspection party is less than or equal to 1, determining the initial sampling rate corresponding to the current of the target primary inspection party as the target sampling rate corresponding to the target primary inspection party.

Through the flow shown in fig. 2, the target sampling rate corresponding to each target primary inspection party is determined according to the primary inspection effect index value of each target primary inspection party, the number of primary inspection objects corresponding to each target primary inspection party and the preconfigured total secondary inspection capacity, so that the target sampling rate of each target primary inspection party is respectively determined according to the primary inspection quality of each target primary inspection party, the secondary inspection coverage of a risk object is effectively ensured, and meanwhile, the secondary inspection party resources can be reasonably allocated, so that the secondary inspection party resources are effectively utilized.

Referring to fig. 3, a flowchart of an embodiment of a sampling inspection method according to another embodiment of the present invention is provided. The flow shown in fig. 3 describes how to iteratively adjust the initial sampling rate corresponding to each target primary inspection party according to the set iterative adjustment mode on the basis of the flow shown in fig. 2, until the first set condition is satisfied, and the iteration is stopped. As shown in fig. 3, the process may include the steps of:

Step 301, determining an adjustment coefficient in the current iteration process according to the total recheck capacity and the total current first estimated recheck amount of all target primary checkpoints.

Step 302, for each target primary inspection party, multiplying the initial sampling rate corresponding to the current target primary inspection party by an adjustment coefficient to obtain the initial sampling rate corresponding to the target primary inspection party in the current iteration process.

In the first iteration process, the initial sampling rate corresponding to the current target primary inspection party refers to the initial sampling rate obtained in the step 201, and the current first estimated total amount of the target primary inspection party refers to the first estimated total amount of the target primary inspection party obtained in the step 202; in the non-first iteration process, the initial sampling rate currently corresponding to the target primary side refers to the initial sampling rate obtained after the last iteration is finished, and the first estimated total amount currently corresponding to the target primary side refers to the first estimated total amount obtained by using the initial sampling rate obtained after the last iteration is finished.

As can be seen from the above description, when the total first estimated review count is smaller than the first value, the current corresponding initial sampling rate of each target primary inspection party can be increased, so that the resources of the review party can be fully utilized, and therefore, when the total first estimated review count of all target primary inspection parties is smaller than the first value, the adjustment coefficient (S) determined in step 301 is greater than 1, and thus, the current corresponding initial sampling rate of each target primary inspection party can be increased by executing step 302.

As an optional implementation manner, when comparing that the total current first estimated review amounts of all the target primary checkpoints are smaller than the first value, the adjustment coefficient in the current iteration process may be determined by the following manner: determining a target primary inspection party with the initial sampling rate of 1 corresponding to the current as a first primary inspection party, determining second estimated total re-inspection amount (marked as B) of all the first primary inspection parties according to the number of the primary inspected objects corresponding to each first primary inspection party and the initial sampling rate corresponding to the current, and subtracting the second estimated total re-inspection amount from the total re-inspection amount to obtain a first difference value; subtracting the second estimated total amount from the first estimated total amount to obtain a second difference value, and dividing the first difference value by the second difference value to obtain an adjustment coefficient in the iterative process, wherein the specific formula is as follows:

in the implementation manner, the first difference value is obtained by subtracting the second estimated total amount from the total re-detection capacity, the second estimated total amount is subtracted from the first estimated total amount to obtain the second difference value, and the first difference value is divided by the second difference value to obtain the adjustment coefficient in the iterative process, so that the influence of the number of the initial detection objects responsible for initial detection, namely the initial detection objects with larger risk, on the adjustment coefficient is eliminated, and the initial sampling rate is adjusted more finely.

As another alternative implementation manner, in the case that the current total amount of the first estimated review of all the target primary checkpoints is less than the first value, the adjustment coefficient in the current iteration process may be determined by: dividing the total recheck capacity by the total current first estimated recheck capacity of all target primary inspection parties to obtain an adjustment coefficient in the iterative process, wherein the specific formula is as follows:

as can be seen from the above description, when the total amount of the first estimated review is greater than the second value, the current corresponding initial sampling rate of each target primary inspection party can be reduced to reduce the review pressure, so that the adjustment coefficient determined in step 301 is less than 1 when the total amount of the first estimated review is greater than the second value, and thus the current corresponding initial sampling rate of each target primary inspection party can be reduced by executing step 302.

As an optional implementation manner, when the current total amount of the first estimated review of all the target primary checkpoints is greater than the second value, the adjustment coefficient in the current iteration process may be determined by the following manner: dividing the total recheck capacity by the total current first estimated recheck capacity of all target primary inspection parties to obtain an adjustment coefficient in the iterative process, wherein the specific formula is as follows:

Step 303, determining the first estimated total amount of the first rechecks corresponding to all the target primary inspection parties in the current iteration process according to the number of the primary inspected objects corresponding to each target primary inspection party and the initial sampling rate corresponding to the current iteration process.

Step 304, comparing the total amount of the first estimated recheck corresponding to all the target primary check parties in the iterative process with a first value and a second value; if the total amount of the first estimated review corresponding to the initial target detection party in the current iteration process is greater than or equal to the first value and less than or equal to the second value, step 305 is executed, and if the total amount of the first estimated review corresponding to the initial target detection party in the current iteration process is less than the first value or greater than the second value, step 301 is executed again to enter the next iteration process.

Step 305, determining that the current corresponding initial sampling rate of each target primary inspection party meets the first setting condition, and stopping iteration.

By the flow shown in fig. 3, the iterative adjustment of the initial sampling rate corresponding to each target primary inspection party is realized according to the set iterative adjustment mode, and the total actual re-inspection amount is maximally close to the total re-inspection capacity while the re-inspection coverage of the risk object is effectively ensured, so that the resources of the re-inspection party are effectively utilized.

Referring to fig. 4, a flowchart of an embodiment of a sampling inspection method according to another embodiment of the present invention is provided. The flow shown in fig. 4 generally describes the spot inspection method provided by the embodiment of the present invention on the basis of the flows shown in fig. 1 to 3. As shown in fig. 4, the process may include the steps of:

step 401, determining the total number C of the plurality of primary inspected objects corresponding to all the target primary inspected parties.

Step 402, comparing the total number C with the preconfigured total capacity Q, and if C is less than or equal to Q, executing step 403; if C > Q is compared, step 404 is performed.

Step 403, determining to perform total re-inspection on a plurality of primary inspected objects corresponding to all target primary inspected parties; ending the flow.

And step 404, determining the initial sampling rate corresponding to each target primary inspection party according to the primary inspection effect index value of each target primary inspection party.

Step 405, determining a first estimated total amount a of the first estimated review of all the target primary inspection parties according to the initial sampling rate currently corresponding to each target primary inspection party and the number of the primary inspected objects corresponding to each target primary inspection party.

Step 406, comparing the first estimated total amount with the first value Q-T and the second value Q+T, if Q-T is not less than A and not more than Q+T, executing step 407; if A is less than or equal to Q-T, then step 408 is performed; if A is greater than or equal to Q+T, then step 410 is performed.

Step 407, determining the target spot check rate corresponding to each target primary check party according to the initial spot check rate corresponding to each target primary check party currently; step 412 is performed.

Step 408, determining the target primary inspection party with the initial sampling rate of 1 corresponding to the current as the first primary inspection party, and determining the second estimated total amount B of all the first primary inspection parties according to the number of the primary inspected objects corresponding to each first primary inspection party and the initial sampling rate corresponding to the current.

Step 409, dividing the first difference by the second difference to obtain an adjustment coefficient S in the iterative process, where the first difference is Q-B and the second difference is a-B; step 411 is performed.

Step 410, dividing the total recheck capacity Q by the current first estimated recheck total amount a of the target primary inspection party to obtain an adjustment coefficient S in the current iteration process.

Step 411, for each target primary inspection party, multiplying the initial sampling rate corresponding to the current target primary inspection party by an adjustment coefficient S to obtain the initial sampling rate corresponding to the target primary inspection party in the current iteration process; execution returns to step 405.

And 412, sampling the primary inspected object corresponding to each target primary inspection party according to the target sampling rate corresponding to each target primary inspection party so as to carry out rechecking on the sampling result by a rechecking party.

For a detailed description of the flow shown in fig. 4, reference may be made to the descriptions in the flows shown in fig. 1 to 3, and the detailed description is omitted here.

The invention also provides an embodiment of the spot check device corresponding to the embodiment of the spot check method.

As shown in fig. 5, a block diagram of an embodiment of a sampling inspection device according to an embodiment of the present invention includes: an index value determination module 51, a spot check rate determination module 52, and a spot check module 53.

The index value determining module 51 is configured to determine a primary detection effect index value of each target primary detection party when determining that sampling and re-detection are performed on a plurality of primary detection objects corresponding to at least one target primary detection party;

the sampling rate determining module 52 is configured to determine a target sampling rate corresponding to each target primary party according to a primary detection effect index value of each target primary party, a number of primary detected objects corresponding to each target primary party, and a preconfigured total review capacity;

and the sampling module 53 is configured to sample the inspected object corresponding to each target primary party according to the target sampling rate corresponding to each target primary party, so that the review party can review the sampling result.

In one possible embodiment, the apparatus further comprises (not shown in the figures):

In one possible implementation, the spot check rate determination module 52 includes (not shown):

Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and an electronic device 600 shown in fig. 6 includes: at least one processor 601, memory 602, at least one network interface 604, and other user interfaces 603. The various components in the electronic device 600 are coupled together by a bus system 605. It is understood that the bus system 605 is used to enable connected communications between these components. The bus system 605 includes a power bus, a control bus, and a status signal bus in addition to a data bus. But for clarity of illustration the various buses are labeled as bus system 605 in fig. 6.

The user interface 603 may include, among other things, a display, a keyboard, or a pointing device (e.g., a mouse, a trackball, a touch pad, or a touch screen, etc.).

It is to be appreciated that the memory 602 in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile memory may be a Read-only memory (ROM), a programmable Read-only memory (ProgrammableROM, PROM), an erasable programmable Read-only memory (ErasablePROM, EPROM), an electrically erasable programmable Read-only memory (ElectricallyEPROM, EEPROM), or a flash memory, among others. The volatile memory may be a random access memory (RandomAccessMemory, RAM) that acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic random access memory (DynamicRAM, DRAM), synchronous dynamic random access memory (SynchronousDRAM, SDRAM), double data rate synchronous dynamic random access memory (ddr SDRAM), enhanced Synchronous Dynamic Random Access Memory (ESDRAM), synchronous link dynamic random access memory (SynchlinkDRAM, SLDRAM), and direct memory bus random access memory (DirectRambusRAM, DRRAM). The memory 602 described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

In some implementations, the memory 602 stores the following elements, executable units or data structures, or a subset thereof, or an extended set thereof: an operating system 6021 and application programs 6022.

The operating system 6021 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. The application 6022 includes various application programs such as a media player (MediaPlayer), a Browser (Browser), and the like for realizing various application services. The program for implementing the method of the embodiment of the present invention may be included in the application 6022.

In the embodiment of the present invention, the processor 601 is configured to execute the method steps provided by the method embodiments by calling a program or an instruction stored in the memory 602, specifically, a program or an instruction stored in the application 6022, for example, including:

The method disclosed in the above embodiment of the present invention may be applied to the processor 601 or implemented by the processor 601. The processor 601 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in the processor 601 or instructions in the form of software. The processor 601 may be a general purpose processor, a digital signal processor (DigitalSignalProcessor, DSP), an application specific integrated circuit (application specific IntegratedCircuit, ASIC), an off-the-shelf programmable gate array (FieldProgrammableGateArray, FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software elements in a decoding processor. The software elements may be located in a random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory 602, and the processor 601 reads information in the memory 602 and performs the steps of the above method in combination with its hardware.

It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For a hardware implementation, the processing units may be implemented within one or more application specific integrated circuits (ApplicationSpecificIntegratedCircuits, ASIC), digital signal processors (DigitalSignalProcessing, DSP), digital signal processing devices (dspev), programmable logic devices (ProgrammableLogicDevice, PLD), field programmable gate arrays (Field-ProgrammableGateArray, FPGA), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units configured to perform the functions described herein, or a combination thereof.

For a software implementation, the techniques described herein may be implemented by means of units that perform the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.

The electronic device provided in this embodiment may be an electronic device as shown in fig. 6, and may perform all steps of the spot check method shown in fig. 1 to 3, so as to achieve the technical effects of the spot check method shown in fig. 1 to 3, and the detailed description will be omitted herein for brevity.

The embodiment of the invention also provides a storage medium (computer readable storage medium). The storage medium here stores one or more programs. Wherein the storage medium may comprise volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, hard disk, or solid state disk; the memory may also comprise a combination of the above types of memories.

When the one or more programs in the storage medium are executable by the one or more processors, the method for spot check performed on the electronic device side is implemented.

The processor is used for executing the sampling inspection program stored in the memory to realize the following steps of the sampling inspection method executed on the electronic equipment side:

Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of function in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.

Claims

1. A method of spot inspection, comprising:

sampling the primary inspected objects corresponding to the target primary inspection parties according to the target sampling rate corresponding to the target primary inspection parties so as to carry out rechecking on sampling results by rechecking parties;

wherein the determining the target sampling rate corresponding to each target primary inspection party according to the primary inspection effect index value of each target primary inspection party, the number of primary inspected objects corresponding to each target primary inspection party, and the preconfigured total recheck capacity comprises:

2. The method of claim 1, wherein determining a sample review of a plurality of primary inspected objects corresponding to at least one target primary inspected party comprises:

3. The method of claim 1, wherein the preliminary examination effect index value includes a first preliminary examination effect index value, and wherein the determining the preliminary sampling rate corresponding to each target preliminary examination party based on the preliminary examination effect index value of each preliminary examination party includes:

4. The method of claim 3, wherein the preliminary examination effect index value further includes a second preliminary examination effect index value, and wherein the determining the preliminary sampling rate corresponding to the target preliminary examination party based on the found sampling rate corresponding to the first preliminary examination effect index value of the target preliminary examination party includes:

5. The method of claim 1, wherein determining whether the initial sampling rate corresponding to each target primary party satisfies a first set condition according to the number of primary inspected objects corresponding to each target primary party and a pre-configured total review capacity comprises:

6. The method of claim 5, wherein iteratively adjusting the initial sampling rate corresponding to each of the target primary inspection parties in a set iterative adjustment manner until the first set condition is satisfied, comprises:

7. The method according to claim 6, wherein, in the case that the total amount of the first estimated review corresponding to all the target primary parties in the current iteration process is greater than the second value, the determining the adjustment coefficient in the current iteration process according to the total review capacity and the total current first estimated review of all the target primary parties includes:

8. The method according to claim 6, wherein, in the case that the total amount of the first estimated review corresponding to all the target primary inspection parties in the current iteration process is smaller than the first value, the determining the adjustment coefficient in the current iteration process according to the total review capacity and the total current first estimated review of all the target primary inspection parties includes:

9. The method of claim 1, further comprising, prior to the method:

10. A spot check device, comprising:

the sampling detection module is used for sampling the primary detection objects corresponding to the target primary detection parties according to the target sampling detection rate corresponding to the target primary detection parties so as to carry out rechecking on sampling results by rechecking parties;

The sampling rate determining module is specifically configured to:

11. An electronic device, comprising: a processor and a memory, the processor being configured to execute a sampling test program stored in the memory to implement the sampling test method of any one of claims 1 to 9.

12. A storage medium storing one or more programs executable by one or more processors to implement the spot check method of any one of claims 1-9.