CN113947392A

CN113947392A - Abnormity determining method and device in traffic data auditing task

Info

Publication number: CN113947392A
Application number: CN202111575923.6A
Authority: CN
Inventors: 卢朝晖; 吴狄豹; 王仁毅; 张建鑫; 周檑胜; 徐百超
Original assignee: Zhejiang Lijia Electronic Technology Co ltd
Current assignee: Zhejiang Lijia Electronic Technology Co ltd
Priority date: 2021-12-22
Filing date: 2021-12-22
Publication date: 2022-01-18
Anticipated expiration: 2041-12-22
Also published as: CN113947392B

Abstract

The embodiment of the application provides a method and a device for determining abnormity in a traffic data auditing task, wherein the method comprises the following steps: clustering each monitoring site according to the geographical position information to obtain a plurality of monitoring site clusters; acquiring the auditing time period weight and the historical access weight of the auditor; respectively determining auditing tasks which need to be processed by the auditors in the plurality of monitoring site clusters; and respectively inputting the audit data and the input data corresponding to each audit task processed by the auditor into the distribution statistical model corresponding to the audit task to obtain an abnormal determination result corresponding to the auditor. The technical scheme provided by the embodiment of the invention realizes the distribution of audit data with certain data and business discreteness for auditors, avoids the illegal transaction situation in the audit work, realizes the directional and accurate determination of the abnormity of the audit task, and is further beneficial to improving the accuracy of the data input in a traffic violation data platform.

Description

Abnormity determining method and device in traffic data auditing task

Technical Field

The invention relates to the technical field of computers, in particular to a method and a device for determining abnormity in a traffic data auditing task.

Background

In traffic management, traffic police departments rely more and more on traffic technology monitoring facilities to automatically capture and identify traffic violations such as red light running, overspeed, driving without safety belts, making calls, lane changing, pressing lines and the like, but because the monitoring facilities have the influences of equipment factors (such as lens damage, low resolution and the like) and environmental factors (such as rainy days, foggy days, light rays and the like), the identification of the traffic violations has larger errors. In order to ensure the reliability of the evidence of traffic violation, an auditor is required to audit the traffic picture captured by the monitoring facility, and after the audit, the picture of the illegal action is input into an illegal data input platform, and the picture is used as a certificate of the traffic violation.

However, the audit work of the auditors causes quality problems and abnormal situations of the input data, which are caused by the audit quality of the auditors, on one hand, erroneous judgment and missing judgment of the audit data, and on the other hand, the illegal transaction situation occurs in the audit work, so that it is urgently needed to effectively monitor the abnormal situation in the traffic data audit task in the audit system. In the prior art, the abnormity monitoring method for the auditing platform cannot distinguish different abnormal situations such as auditing quality and illegal transactions, and further the accuracy of traffic data auditing is difficult to improve.

Disclosure of Invention

In view of this, the present invention provides a method and a device for determining an abnormality in a traffic data audit task, which effectively reduce the number of illegal transactions in the traffic data audit task, and directionally supervise the audit quality of auditors, thereby improving the accuracy of traffic data audit.

In a first aspect, an embodiment of the present invention provides a method for determining an anomaly in a traffic data audit task, where the method is applied to a server, the server is in communication connection with an illegal data entry platform and monitoring sites, the server prestores a distribution statistical model corresponding to each monitoring site, and the distribution statistical model is used to characterize a normal entry rate probability interval corresponding to the monitoring site, and the method includes:

acquiring geographical position information corresponding to each monitoring site, and clustering each monitoring site according to the geographical position information to obtain a plurality of monitoring site clusters;

acquiring the auditing time period weight of an auditor and the historical access weight of each monitoring station corresponding to the auditor from the historical auditing information of the auditor;

according to the auditing time period weight and the historical access weight, respectively determining auditing tasks needing to be processed by auditors in the multiple monitoring site clusters to obtain a total auditing task corresponding to the auditors; each audit task in the total audit tasks corresponds to audit data of a specific time period in a monitoring station;

and respectively inputting the audit data and the input data corresponding to each audit task processed by the auditor into the distribution statistical model corresponding to the audit task to obtain an abnormal determination result corresponding to the auditor.

With reference to the first aspect, an embodiment of the present invention provides a first possible implementation manner of the first aspect, where the determining, according to the review time period weight and the historical access weight, the review tasks that the reviewer needs to process in the multiple monitoring site clusters respectively to obtain a total review task corresponding to the reviewer specifically includes:

for each monitoring site cluster, establishing a weight matrix which is constructed by the weight of the auditing time period and the historical access weight and corresponds to the auditor, and searching a first number of target elements in the weight matrix; the first number is determined by the total audit tasks corresponding to the auditors and the number of the monitoring site clusters;

determining the auditing data represented by the monitoring sites and the auditing time periods corresponding to the preset number of target elements as the auditing tasks of the auditors;

and obtaining a total audit task corresponding to the auditor based on the audit tasks respectively determined by the plurality of monitoring station clusters.

With reference to a possible implementation manner of the first aspect, an embodiment of the present invention provides a second possible implementation manner of the first aspect, where the determining, as an audit task of an auditor, audit data represented by monitoring stations and audit time periods corresponding to the preset number of target elements specifically includes:

inquiring a monitoring site and an auditing time period corresponding to a target element in the weight matrix;

acquiring monitoring data acquired by the monitoring station in the auditing time period;

and generating an auditing task of the auditor corresponding to the monitoring site according to the collected monitoring data.

With reference to the first aspect, an embodiment of the present invention provides a third possible implementation manner of the first aspect, where the obtaining of the audit time period weight of the auditor from the historical audit information of the auditor and the historical access weight of the auditor corresponding to each monitoring station specifically includes:

counting the auditing quantity of the historical auditing information of the auditors in each auditing time period;

determining the weight of the auditing time period of the auditors according to the auditing quantity in each auditing time period;

counting the historical audit quantity of each monitoring station in the historical audit information of the auditors;

and determining the historical access weight of the auditor corresponding to each monitoring site according to the historical auditing quantity of each monitoring site.

With reference to the first aspect, an embodiment of the present invention provides a fourth possible implementation manner of the first aspect, where the audit data and entry data corresponding to each audit task processed by the auditor are obtained through the following steps:

extracting the audit data and the site identification information of the monitoring site corresponding to the audit task corresponding to the input data;

classifying the audit data and the input data based on the site identification information to obtain an audit data group and an input data group under the monitoring site corresponding to each site identification information.

With reference to the first aspect, an embodiment of the present invention provides a fifth possible implementation manner of the first aspect, where the respectively inputting audit data and entry data corresponding to each audit task processed by an auditor into a distribution statistical model corresponding to the audit task to obtain an abnormality determination result corresponding to the auditor specifically includes:

counting audit data corresponding to each audit task to obtain a first data volume, and counting entry data corresponding to each audit task to obtain a second data volume;

calculating a data logging rate based on the first data volume and the second data volume;

searching a recording rate probability value corresponding to the data recording rate from a preset recording rate probability table; the recording rate probability table stores a corresponding relation between a data recording rate and a recording rate probability value;

and determining an abnormal determination result corresponding to the auditor according to whether the recording rate probability value falls into the normal recording rate probability interval.

With reference to the fifth possible implementation manner of the first aspect, an embodiment of the present invention provides a sixth possible implementation manner of the first aspect, where the method further includes:

calculating the review abnormal rate corresponding to the specified time period according to the counted number of the abnormal monitoring sites and the total number of the monitoring sites corresponding to the total review task;

obtaining the auditing abnormal rate corresponding to a plurality of appointed time periods of the auditor, and calculating a first mean abnormal rate based on the auditing abnormal rate corresponding to the appointed time periods;

and determining an abnormality determination result corresponding to the auditor according to the first mean value abnormality rate.

In a second aspect, an embodiment of the present invention further provides an anomaly determination apparatus in a traffic data auditing task, where the apparatus is applied to a server, the server is in communication connection with an illegal data entry platform and monitoring sites, a distribution statistical model corresponding to each monitoring site is prestored in the server, and the distribution statistical model is used to represent a normal recording rate probability interval corresponding to the monitoring site, and the apparatus includes:

the site clustering module is used for acquiring geographical position information corresponding to each monitoring site and clustering each monitoring site according to the geographical position information to obtain a plurality of monitoring site clusters;

the weight determining module is used for acquiring the auditing time period weight of an auditor from historical auditing information of the auditor and the historical access weight of each monitoring station corresponding to the auditor;

a task determining module, configured to determine, according to the review time period weight and the historical access weight, the review tasks that the reviewer needs to process in the multiple monitoring site clusters, respectively, to obtain a total review task corresponding to the reviewer; each audit task in the total audit tasks corresponds to audit data of a specific time period in a monitoring station;

and the abnormity determining module is used for respectively inputting the auditing data and the input data corresponding to each auditing task processed by the auditor into the distribution statistical model corresponding to the auditing task to obtain an abnormity determining result corresponding to the auditor.

In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the anomaly determination method in the traffic data auditing task of the first aspect.

In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, where the storage medium stores a computer program, and the computer program is executable by a processor to complete the abnormality determination method in the traffic data auditing task according to the first aspect.

The embodiment of the invention has the following beneficial effects: first of all

The embodiment of the application provides a method and a device for determining abnormity in a traffic data auditing task, wherein factors of main sources of illegal transaction data generated in three traffic data auditing tasks, such as auditing data geographic position repeatability, auditing data time period repeatability, auditing data monitoring station repeatability and the like, are considered at first, auditing data with certain data and service discreteness are distributed for auditors, and illegal transaction situations in auditing work are avoided; and then acquiring entry data corresponding to each audit task in the total audit tasks processed by the auditor, and inputting the audit data group and the entry data group of the same monitoring station into a distribution statistical model corresponding to the same monitoring station to obtain an abnormal determination result of the same monitoring station, which is output by the distribution statistical model based on a normal recording rate probability interval corresponding to the same monitoring station. The technical scheme provided by the embodiment of the invention effectively removes the traffic data auditing quality problem from various abnormal situations, realizes the purpose of directionally and accurately determining the abnormity of the auditing task, and is further beneficial to improving the accuracy of data input in a traffic violation data platform.

Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.

In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1 is a schematic structural diagram of a monitoring system for auditing behaviors according to an embodiment of the present invention;

fig. 2 is a flowchart of an abnormality determination method in a traffic data audit task according to an embodiment of the present invention;

FIG. 3 is a flowchart of another method for determining an anomaly in a traffic data review task according to an embodiment of the present invention;

FIG. 4 is a flowchart of another method for determining an anomaly in a traffic data review task according to an embodiment of the present invention;

FIG. 5 is a flowchart of another method for determining an anomaly in a traffic data review task according to an embodiment of the present invention;

FIG. 6 is a flow chart of another method for determining an anomaly in a traffic data review task according to an embodiment of the present invention;

fig. 7 is a schematic structural diagram of an abnormality determination device in a traffic data audit task according to an embodiment of the present invention;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In view of the above problem, the following first describes in detail an abnormality determination method in a traffic data audit task according to an embodiment of the present invention. The execution subject is a server, fig. 1 shows a schematic structural diagram of a monitoring system for auditing behaviors, and as shown in fig. 1, the system includes a server 100, and an illegal data entry platform 101 and monitoring sites 102 which are in communication connection with the server 100, the server 100 prestores a distribution statistical model corresponding to each monitoring site 102, and the distribution statistical model is used for representing a normal recording rate probability interval corresponding to the monitoring site.

Generally, there are a plurality of monitoring stations connected to the server 100, and for convenience of illustration, fig. 1 illustrates 4 monitoring stations 102, where a monitoring station may be understood as a monitoring device installed on a traffic road and capable of collecting traffic video, such as a video camera; the illegal data entry platform 101 can be understood as an operable platform capable of uploading traffic violation images or traffic violation information (such as, license plate number, vehicle type, etc.) which can be used as a traffic violation certificate to be subsequently delivered to a traffic police department. In practical application, the number of monitoring sites connected to the server may be in communication connection according to actual needs, and is not limited herein.

Based on the above server, the following first introduces in detail an abnormality determination method in a traffic data audit task provided by an embodiment of the present invention with reference to fig. 2, including the following steps:

and S010, acquiring geographical position information corresponding to each monitoring station, and clustering the monitoring stations according to the geographical position information to obtain a plurality of monitoring station clusters.

The embodiment of the invention aims to solve the problem that the quality problem of the traffic data audit is effectively separated from various abnormal situations, namely the illegal transaction situation of auditors is effectively eliminated from various abnormal situations in the task allocation stage. From the perspective of big data, in the prior art, if an auditor autonomously selects audit data or the audit data which is simply and randomly distributed and is adopted by the system cannot ensure sufficient discrete type, the illegal transaction situation can be characterized in that the same auditor audits the monitoring data of the same region, the same time period or the same monitoring station for multiple times on the data, and further forms the risk of illegal transaction. Particularly, in the application scenario of traffic data auditing, the geographic position information of the monitoring station is an important factor for ensuring the data dispersion of the auditing task.

Specifically, in this step, the monitoring sites are clustered according to the geographical location information corresponding to each monitoring site, so as to obtain a plurality of monitoring site clusters. The geographical location information of the monitoring site is a monitoring site attribute which can be called and stored in the server, and can be longitude and latitude coordinates of the monitoring site, and can also be administrative region identification of a city to which the monitoring site belongs.

Taking longitude and latitude coordinates of the monitoring sites as an example, the embodiment of the invention can adopt a two-dimensional clustering algorithm based on methods such as Kmeans, KNN, Birch and the like, and take longitude and latitude of the monitoring sites as two-dimensional coordinate values to cluster all the monitoring sites in a city according to the longitude and latitude coordinates to obtain a plurality of monitoring site clusters. It can be understood that each cluster of monitoring sites represents a group of monitoring sites with similar geographic location information and belonging to the same area on different scales. If the monitoring site data audited by the auditor are concentrated in the same monitoring site cluster, the discreteness of the audited data is difficult to guarantee, and potential illegal transaction risks can be caused. Therefore, the reason for clustering the monitoring sites in this step is to distribute tasks distributed by one auditor among a plurality of monitoring site clusters when further task distribution is performed subsequently.

Specifically, the method for clustering the monitoring sites by using the longitude and latitude coordinates of the monitoring sites may include the following steps. The operation of primary clustering is as follows: selecting a plurality of monitoring sites from all monitoring sites in a city as clustering centers, calculating the distance between each monitoring site and each clustering center, and attributing each monitoring site to the monitoring site cluster where the clustering center closest to the monitoring site cluster is located. And then, re-determining the monitoring sites serving as the clustering centers in each monitoring site cluster according to the longitude and latitude coordinates of the monitoring sites in each monitoring site cluster, and performing clustering operation again. After the clustering operation is repeatedly performed for a plurality of times in the process, the clustering result of the monitoring site cluster does not change any more, and the final clustering result of the monitoring site cluster is obtained.

The number of monitoring sites initially selected as cluster centers in the above method determines the number of clusters of monitoring sites. The user can determine the number of the monitoring site clusters according to requirements in an actual application scene. Generally, the number of monitoring site clusters can be between 10 and 20 according to the number and density of monitoring sites in a city. If the obtained clustering result is not ideal, the user can readjust the selection of the initial clustering center. Although the whole clustering process is large in calculation amount, the number and the positions of the monitoring sites in the city are relatively fixed, and the clustering process does not need to be repeated for many times.

And taking the geographical location information of the monitoring sites as the administrative region identifier of the city to which the monitoring sites belong as an example, when clustering the monitoring sites in the scene, only the monitoring sites with the same administrative region representation need to be attributed to one monitoring site cluster. The administrative mark may be a mark of an administrative district, a mark of a street, or the like. It should be noted that the result of clustering according to the geographical location information depends on the distribution of monitoring sites in different cities and whether parameter selection in a clustering algorithm is appropriate, so that sufficient dispersion of the audit data in the geographical location cannot be completely guaranteed, and the assignment of the audit task needs to be further determined subsequently in a more specific screening manner based on the monitoring sites, thereby further guaranteeing sufficient dispersion of the audit data in the geographical location.

Step S020, acquiring the auditing time period weight of an auditor and the historical access weight of each monitoring station corresponding to the auditor from the historical auditing information of the auditor.

After the plurality of monitoring site clusters are obtained, the distributed audit tasks need to be further determined based on the plurality of monitoring site clusters through factors such as audit time period weight, historical access weight and the like corresponding to auditors in the step.

The auditing time period weight of the auditor in the embodiment of the invention refers to the auditing frequency of the auditor for tasks in different time periods indicated by traffic data which are accumulatively audited by the auditor for different time periods in different time periods of each day. The related attributes of each audit data of the historical audit of the auditors are recorded in the server, such as monitoring sites, time periods, audit data, logging data and the like. The server divides the traffic data generated within 24 hours of a day into a plurality of time periods, for example, 24 time periods. Actually calculating the auditing historical data of the auditor, statistically determining that 1000 auditing data of the auditor audited at 17:00-18:00 are the time period with the most history, and determining the weight of the auditing time period of the auditor at 17:00-18:00 as 1. The auditing time period weight of other time periods of the auditor can be respectively determined according to the proportion of the number of the audited data to 1000. Other methods may also be adopted to calculate the weights of the auditors in the auditing time periods in different time periods, which is not specifically limited in the embodiment of the present invention, and generally, the value of the weight pair in the auditing time period may be between 0 and 1.

Similarly, the historical access weight of the auditor corresponding to each monitoring station in the embodiment of the invention refers to the auditing frequency of the auditor for different monitoring stations, which is indicated by the accumulated audited traffic data of the auditor for each monitoring station in the city. Also illustratively, the system may statistically determine that 500 audit data have been audited by an auditor for a monitoring site representing ZJ0000001, and the historical access weight of the auditor for the monitoring site representing ZJ0000001 may be set to 1 for the monitoring site with the most history. The historical access weight of the auditor to other monitoring sites can be determined by the ratio of the number of audited data to 500. Other methods may also be used to calculate the historical access weight of the auditor corresponding to each monitoring site, and the embodiment of the present invention is not limited specifically, and generally, the value of the historical access weight may be between 0 and 1.

It can be seen that the values of the audit period weight and the historical access weight are dynamically changed for the auditor. As audit data accumulates, the server may periodically recalculate audit period weights for auditors, as well as historical access weights for the auditors corresponding to each monitoring site. The calculated time period may be set to one day, one week, or one month.

Step S030, according to the auditing time period weight and the historical access weight, respectively determining auditing tasks which need to be processed by the auditor in the plurality of monitoring site clusters, and obtaining a total auditing task corresponding to the auditor; each audit task in the total audit tasks corresponds to audit data of a specific time period in a monitoring station.

The total audit task corresponding to the auditor determined in this step is a set of multiple audit tasks allocated to the auditor at a time, each audit task in the total audit task corresponds to audit data of a specific time period in one monitoring station, and a specific process of step S030 is as follows, as shown in fig. 3.

Step 031, for each monitoring station cluster, establishing a weight matrix constructed by the auditing time period weight and the historical access weight corresponding to the auditor, and searching for a first number of target elements in the weight matrix; the first number is determined by the total audit tasks corresponding to the auditors and the number of the monitoring site clusters.

The total audit task corresponding to the auditor determined in this step is determined in a plurality of monitoring site clusters. In order to ensure the discreteness of the distributed audit data, the audit task data can be evenly distributed in a plurality of monitoring site clusters. Therefore, it is first necessary to determine how many pieces of audit data need to be screened out in each monitoring site cluster. In this step, the first amount of audit data in each monitoring site cluster is determined by the total audit tasks corresponding to the auditors and the amount of the monitoring site clusters. For example, 500 pieces of audit data need to be processed by auditors, and the server clusters the monitoring sites in the city into 20 monitoring site clusters, so that 25 pieces of audit data need to be determined in each monitoring site cluster.

In this step, for a monitoring station cluster, the 25 pieces of audit data are determined by searching in a weight matrix constructed by the audit time period weight and the historical access weight corresponding to the auditor. It is mentioned in the foregoing that the auditing time period weights of the auditor in 24 time periods can be calculated, and the monitoring site cluster has 800 monitoring sites, so that the corresponding auditing time period weight and historical access weight of the auditor for the monitoring site cluster can be represented by a 24 × 80 weight matrix, and each element in the weight matrix can be the sum or product value of the corresponding auditing time period weight and historical access weight.

In this step, the searching for the first number of target elements in the weight matrix may be performed by traversing each element in the matrix to find the first number of target elements with the smallest element value. According to the matrix row and column corresponding to each target element, the monitoring station and the auditing time period corresponding to the target element can be determined.

Step S032, determining the monitoring sites corresponding to the first number of target elements and the auditing data represented by the auditing time period as the auditing task of the auditor.

After the monitoring sites and the auditing time periods corresponding to the first number of target elements are determined, the auditing data represented by the monitoring sites and the auditing time periods corresponding to the target elements can be determined as the auditing tasks of the auditors. Inquiring a monitoring site and an auditing time period corresponding to a target element in the weight matrix; acquiring monitoring data acquired by the monitoring station in the auditing time period; and generating an auditing task of the auditor corresponding to the monitoring site according to the collected monitoring data.

It is mentioned above that the result of clustering according to the geographic location information cannot completely guarantee that the audit data is sufficiently discrete in the geographic location, and it is necessary to subsequently determine the assignment of the audit task further by a screening manner based on the monitoring site. In addition, the auditing time period is also an important factor for ensuring the data discrete degree, and if auditing tasks of fixed time periods, such as traffic peak time periods or other specific time periods with high incidence of illegal events between 8:00 and 9:00, are intensively audited by auditors in the prior art, illegal transactions in the process of auditing illegal data by specific groups of potential specific people can be caused to exist in individual auditors. In the step, the data of the auditing tasks allocated to the auditors are ensured to be sufficiently discrete based on the factors such as the repeatability of the data auditing time period, the repeatability of the data auditing monitoring station and the like.

Step 033, obtaining a total audit task corresponding to the auditor based on the audit tasks respectively determined by the plurality of monitoring site clusters.

After the corresponding audit task is determined for each monitoring site cluster, the total audit task corresponding to the auditor can be obtained based on the audit tasks respectively determined for the multiple monitoring site clusters. The total audit task is a collection of audit tasks assigned to one auditor at a time. In the embodiment of the invention, each monitoring station cluster needs to determine that the corresponding audit task forms the total audit task of the auditor, so that the condition that illegal transactions occur in the total audit task is avoided.

And step S040, the audit data and the input data corresponding to each audit task processed by the auditor are respectively input into the distribution statistical model corresponding to the audit task, and the abnormal determination result corresponding to the auditor is obtained.

In this embodiment, after the recording rate probability value is calculated based on the audit data group and the recording data group, the recording rate probability value is compared with the normal recording rate probability interval to obtain a detection result, specifically, the detection result of the same monitoring station may be implemented through steps C1 to C4:

step C1, counting the number of the audit data in the audit data group of the same monitoring station to obtain a first data volume, and recording the number of the recording data in the recording data group to obtain a second data volume;

step C2, calculating the data recording rate based on the first data volume and the second data volume;

and dividing the second data quantity by the first data quantity to obtain the data recording rate of the same monitoring station.

Step C3, searching the recording rate probability value corresponding to the data recording rate from the preset recording rate probability table;

the recording rate probability table stores a corresponding relationship between the data recording rate and the recording rate probability value. In practical use, the correspondence between the data recording rate and the recording rate probability value stored in the recording rate probability table can be obtained based on the probability density function, that is, each data recording rate corresponds to a recording rate probability value.

The example that the probability density function corresponding to the monitoring station conforms to the normal distribution is taken as an example for explanation, so the calculation formula of the probability density function is as follows:

(ii) a Wherein,

and u represents a standard deviation of the data recording rate, u represents a mean value of the data recording rate, and x represents the data recording rate.

The standard deviation and the mean value of the data recording rate can be obtained by calculating the historical data recording rate, specifically, the historical data recording rates of the M monitoring sites are taken, wherein the mean value calculation formula of the data recording rates is as follows:

(ii) a Wherein,

the v-th data recording rate is expressed, and the value range of v is [1, M]M represents the number of historical data recording rates;

the calculation formula of the standard deviation of the data recording rate is as follows:

。

the recording rate probability value corresponding to the data recording rate is obtained by substituting the data recording rate into the probability density function, so that a recording rate probability table with the corresponding relation between the data recording rate and the recording rate probability value can be constructed based on the probability density function, and the recording rate probability value corresponding to the data recording rate can be found by utilizing the table.

And step C4, determining the detection result of the same monitoring station according to whether the recording rate probability value falls into the normal recording rate probability interval.

And if the recording rate probability value falls into the normal recording rate probability interval, determining that the monitoring station is a normal monitoring station, and if the recording rate probability value does not fall into the normal recording rate probability interval, determining that the monitoring station is an abnormal monitoring station.

It is worth mentioning that in an application scenario of traffic data auditing, especially in a modern city with a developed monitoring system, due to the fact that the number of monitoring sites and the number of auditors are very large, and in combination with the time period and the data dimensionality of the monitoring site cluster in the embodiment of the present invention, if all data dimensionalities are directly considered, all data are processed in real time through methods such as linear programming and an artificial intelligence model, and at this time, the calculation amount of one-time task allocation cannot be borne by a server. Therefore, the monitoring sites are clustered, and the subsequent task allocation calculation based on factors such as the repeatability of the audit data time period, the repeatability of the audit data monitoring sites and the like is only performed in each monitoring site cluster, so that the calculation amount of the overall task allocation is greatly reduced; secondly, when a weight matrix is constructed, if the auditing time period weight and the historical access weight of the constructed weight matrix are arranged according to the size sequence, the whole weight matrix does not need to be traversed when a first number of target elements are searched in the optimization mode, and higher calculation efficiency can be ensured even if the number of monitoring sites in a monitoring site cluster is larger; thirdly, although the technical scheme of the embodiment of the invention can dynamically adjust the auditing time period weight and the historical access weight of the auditor according to the accumulation of the auditing data, the auditing time period weight and the historical access weight are not changed in the adjustment period, that is to say, the weight matrix corresponding to the auditor is also unchanged, so that a large amount of repeated calculation is avoided.

According to the method for determining the abnormity in the traffic data auditing task, provided by the embodiment of the invention, the factors of main sources generated by illegal transaction data in three traffic data auditing tasks, namely the auditing data geographic position repeatability, the auditing data time period repeatability, the auditing data monitoring station repeatability and the like, are considered at first, auditing data with certain data and service discreteness are distributed for auditors, and the illegal transaction situation in auditing work is avoided; and then acquiring entry data corresponding to each audit task in the total audit tasks processed by the auditor, and inputting the audit data group and the entry data group of the same monitoring station into a distribution statistical model corresponding to the same monitoring station to obtain an abnormal determination result of the same monitoring station, which is output by the distribution statistical model based on a normal recording rate probability interval corresponding to the same monitoring station. The technical scheme provided by the embodiment of the invention effectively removes the traffic data auditing quality problem from various abnormal situations, realizes the purpose of directionally and accurately determining the abnormity of the auditing task, and is further beneficial to improving the accuracy of data input in a traffic violation data platform.

Based on the server, another method for determining an abnormality in a traffic data audit task is provided in an embodiment of the present invention, and fig. 4 shows a flowchart of the method for determining an abnormality in a traffic data audit task, as shown in fig. 4, the method includes the following steps:

step S202, randomly distributing a total audit task to be processed in a designated time period for auditors;

each audit task in the total audit tasks corresponds to one monitoring site, and audit data included in the audit tasks are acquired by the corresponding monitoring sites.

Because the work energy of the auditor is limited, usually, several monitoring sites can be randomly handed to the auditor for data auditing of the monitoring sites in a specified time period.

Since the monitoring station is a monitoring facility for video acquisition, the audit data included in the audit task is a video image of one frame included in the traffic video.

Step S204, acquiring the input data corresponding to each audit task in the total audit tasks processed by the auditor;

the input data are illegal data of an input illegal data input platform determined from the auditing data corresponding to the auditing task.

Only the data entered into the illegal data entry platform is determined to be illegal data, so that in the embodiment, an auditor is required to audit each audit task in the total audit tasks, and the illegal data is found from the audit data included in the audit tasks and entered into the illegal data entry platform to serve as a subsequent traffic violation evidence; the illegal data recorded into the illegal data recording platform may be an illegal video image or image information (e.g., an image frame number) corresponding to the illegal video image.

Step S206, classifying the audit data and the input data according to the monitoring sites corresponding to the audit tasks in the total audit tasks respectively to obtain an audit data set and an input data set belonging to the same monitoring site;

in practical use, each audit task carries unique site identification information of a corresponding monitoring site, for example, the site identification information of the monitoring site may be represented by numbers, characters or letters, which is not limited herein.

Since each audit task carries the site identification information, the audit data and the entered data can be classified at the same site based on the site identification information, and the classification process can be realized through steps a1 to a 2:

step A1, extracting the audit data and the site identification information of the monitoring site corresponding to the audit task corresponding to the input data;

the entry data can be understood as a part of the audit data, and each of the audit data and the entry data carries task identification information of a corresponding audit task when the entry data is actually used, so that the audit task corresponding to the audit data and the entry data can be found through the task identification information, and further, the site identification information of the monitoring site corresponding to the audit task is extracted, so that which monitoring site corresponding to each of the audit data and the entry data is can be determined.

Step A2, classifying the audit data and the input data based on the site identification information to obtain an audit data group and an input data group under the monitoring site corresponding to each site identification information.

And classifying the audit data of the same site identification information to obtain audit data groups under each monitoring site, and classifying the input data of the same site identification information to obtain input data groups under each monitoring site.

For example, the audit data includes 6 audit data, where the site identification information corresponding to audit data 1 is 1, the site identification information corresponding to audit data 2 is 4, the site identification information corresponding to audit data 3 is 2, the site identification information corresponding to audit data 4 is 3, the site identification information corresponding to audit data 5 is 2, the site identification information corresponding to audit data 6 is 1, and each site identification information corresponds to a monitoring site, so there are 4 monitoring sites, where the site identification information of audit data 1 and audit data 6 is the same, so that the audit data 1 and audit data 6 are attributed to the monitoring site whose site identification information is 1 to obtain the audit data group of the monitoring site, and the audit data groups of other monitoring sites are classified together and are not described herein, the classification process of the entered data set is the classification process of the audit data set, and therefore, the description is not repeated.

Step S208, inputting the auditing data group and the recording data group of the same monitoring station into a distribution statistical model corresponding to the same monitoring station to obtain a detection result of the same monitoring station, which is output by the distribution statistical model based on a normal recording rate probability interval corresponding to the same monitoring station;

the distribution statistical model can be understood as a detection model capable of detecting whether a monitoring station is a normal monitoring station or an abnormal monitoring station, where the normal monitoring station refers to that a recording rate probability value of the monitoring station obtained based on an audit data group and an input data group is in a normal recording rate probability interval after an audit data group corresponding to the monitoring station is audited by an auditor, and it is indicated that no abnormal sample occurs when the auditor audits audit data of the monitoring station, and the abnormal monitoring station refers to that the recording rate probability value obtained is not in the normal recording rate probability interval, and it is indicated that the abnormal sample occurs when the auditor audits audit data of the monitoring station.

The recording rate probability value refers to a probability value of a data recording rate, the probability value can be determined through a probability density function, the data recording rate can be understood as a proportion of the data volume of the recorded data group to the data volume of the auditing data group, the data volume of the recorded data group can be divided by the data volume of the auditing data group to obtain the data volume, the normal recording rate probability interval refers to an interval range of the recording rate probability that the monitoring station is normal, generally, the normal recording rate probability interval is closely related to the probability density function corresponding to the monitoring station, and through research, the probability density function of each monitoring station is normally distributed or distributed in a biased normal state, so that the normal recording rate probability interval and the probability density function can be determined based on a mean value and a standard deviation corresponding to the historical data recording rate.

In this embodiment, the probability density function conforming to the normal distribution is taken as an example for explanation, and the data recording rate is shown to be [ u-2 ] through research

，u+2

]The probability of the recording rate is more than 95%, therefore, the probability interval of the normal recording rate can be set as [ u-2 ]

，u+2

]In this embodiment, after the distribution statistical model calculates the recording rate probability value based on the audit data group and the recording data group, the model detects whether the recording rate probability value is within the normal recording rate probability interval, so as to determine the detection result of whether the monitoring station is a normal monitoring station or an abnormal monitoring station.

Step S210, counting the number of monitoring sites with abnormal detection results corresponding to the total audit task;

and step S212, determining the auditing behavior of the auditors according to the counted number of the abnormal monitoring sites.

According to the method for determining the abnormity in the traffic data auditing task, the cheating probability of the auditors can be effectively reduced by randomly distributing the monitoring sites for the auditors, the auditing behavior of the auditors can be accurately monitored according to the auditing data of the auditing task and the number of the abnormal monitoring sites calculated according to the input data of the input platform, the illegal transaction frequency is reduced while the reliability of the illegal data of the input platform is improved, and therefore the strong control on the traffic illegal behavior is improved.

The embodiment provides another method for determining the abnormality in a traffic data auditing task, which is implemented on the basis of the embodiment; this embodiment focuses on a specific implementation of randomly allocating a total audit task. As shown in fig. 5, another flow chart of the abnormality determining method in the traffic data auditing task in this embodiment includes the following steps:

step S302, randomly distributing a plurality of monitoring sites for auditors;

specifically, the process of randomly allocating the monitoring stations may be implemented through steps B1 to B3:

step B1, acquiring auditing information of an auditor;

wherein the audit information comprises at least one of: identity identification information, audit date information and duration information of a specified time period; the audit information may be set according to implementation requirements, and is not limited herein.

Step B2, inquiring the number of the auditing sites corresponding to the auditing information from a preset number inquiry table;

the quantity query table stores the corresponding relation between the quantity of the audit sites and the audit information; it can be understood that the number of review stations corresponding to different pieces of review information is stored in the number lookup table, and the description is given by taking the review information as the duration information of the specified time period as an example, the number of review stations corresponding to 4 hours of duration information of the specified time period is 20, the number of review stations corresponding to 6 hours of duration information of the specified time period is 50, and the number of review stations corresponding to 8 hours of duration information of the specified time period is 70, and the correspondence between the number of review stations and the review information in the table may be set according to actual needs, and is not limited herein.

B3, randomly selecting monitoring sites with the number of auditing sites from a plurality of monitoring sites in communication connection with the server and distributing the monitoring sites to auditors;

in practical use, the number of the auditing sites is less than or equal to the total number of the monitoring sites in communication connection with the server, in the previous example, the total number of the monitoring sites is 100, and 70 monitoring sites are randomly selected from the 100 monitoring sites and allocated to the auditing personnel because the time length information of the specified time period is 70 corresponding to 8 hours.

As another embodiment, in addition to determining the monitoring stations allocated to the auditors in the above manner, the monitoring stations may be allocated according to a principle that audit information carried by the monitoring stations matches audit information of the auditors, specifically, each monitoring station is configured with the audit information in advance, and the monitoring stations matching the audit information of the auditors are allocated to the auditors.

Step S304, acquiring monitoring data acquired by each monitoring station in a corresponding working period; wherein the working period is longer than the specified period;

generally, the monitoring stations all work for 24 hours, so that 00:00-24:00 of each day is used as a working period of the monitoring stations, the working period of the working period is 24 hours, therefore, the obtained monitoring data is 24-hour traffic video, the specified period can be understood as the working period of an auditor, and can be set to 9:00-17:00, and the specified period of the auditor is 8 hours.

Step S306, intercepting the monitoring data corresponding to each monitoring station according to a specified time period, and generating an auditing task corresponding to the monitoring station according to the intercepted monitoring data;

in the previous example, the working period may be intercepted as 3 periods based on the designated period of 8 hours duration of the auditor, which may be understood as intercepting the monitoring data of 24 hours into 3 parts, where each part includes the monitoring data of 8 hours duration, and in this embodiment, the 3 parts of the monitoring data obtained by interception are used as 3 auditing tasks of the monitoring station.

Step S308, randomly combining a total audit task to be processed in a specified time period for auditors; the total audit task comprises audit tasks corresponding to a plurality of monitoring sites distributed for auditors;

if there are multiple audit tasks corresponding to the monitoring sites obtained in step S306, at least one of the audit tasks may be randomly allocated to the auditor, and if there is one audit task corresponding to the monitoring site obtained in step S306, the audit task is allocated to the auditor.

Step S310, acquiring entry data corresponding to each audit task in the audit task total audit tasks processed by auditors; the input data are illegal data of an input illegal data input platform determined from the auditing data corresponding to the auditing task;

step S312, classifying the audit data and the input data according to the monitoring sites corresponding to the audit tasks in the total audit tasks respectively to obtain an audit data set and an input data set belonging to the same monitoring site;

step S314, inputting the auditing data group and the recording data group of the same monitoring station into a distribution statistical model corresponding to the same monitoring station to obtain a detection result of the same monitoring station, which is output by the distribution statistical model based on a normal recording rate probability interval corresponding to the same monitoring station;

(ii) a Wherein,

(ii) a Wherein,

。

Step S316, counting the number of monitoring sites with abnormal detection results corresponding to the total audit task;

and step S318, determining the auditing behavior of the auditors according to the counted number of the abnormal monitoring sites.

According to the method for determining the abnormity in the traffic data auditing task, which is provided by the embodiment of the application, a plurality of monitoring stations can be randomly distributed to auditors, and monitoring data acquired by each monitoring station in a corresponding working period is acquired; intercepting the monitoring data corresponding to each monitoring station according to a specified time period aiming at each monitoring station, and generating an auditing task corresponding to each monitoring station according to the intercepted monitoring data; randomly combining a total audit task to be processed in a specified time period for auditors; the method and the system for distributing the monitoring sites and the audit tasks randomly can ensure the randomness of data distribution, effectively reduce the cheating probability of auditors, and improve the reliability of illegal data of the input platform.

The embodiment provides another method for determining the abnormality in a traffic data auditing task, which is implemented on the basis of the embodiment; the embodiment focuses on a specific implementation of determining the auditing behavior of the auditor. As shown in fig. 6, another flow chart of the abnormality determining method in the traffic data auditing task in this embodiment includes the following steps:

step S402, randomly distributing a total audit task to be processed in a designated time period for auditors; each audit task in the total audit tasks corresponds to one monitoring site, and audit data included in the audit tasks are acquired by the corresponding monitoring sites;

step S404, acquiring entry data corresponding to each audit task in the audit task total audit tasks processed by auditors; the input data are illegal data of an input illegal data input platform determined from the auditing data corresponding to the auditing task;

step S406, classifying the audit data and the input data according to the monitoring sites corresponding to the audit tasks in the total audit tasks respectively to obtain an audit data set and an input data set belonging to the same monitoring site;

step S408, inputting the auditing data group and the recording data group of the same monitoring station into a distribution statistical model corresponding to the same monitoring station to obtain a detection result of the same monitoring station, which is output by the distribution statistical model based on a normal recording rate probability interval corresponding to the same monitoring station;

step S410, counting the number of monitoring sites with abnormal detection results corresponding to the total audit task;

step S412, calculating the auditing abnormity rate corresponding to the specified time period according to the counted number of the abnormal monitoring sites and the total number of the monitoring sites corresponding to the total auditing tasks;

the review exception rate may be understood as a ratio of the abnormal monitoring sites to the monitoring sites corresponding to the total review task, and in this embodiment, the review exception rate may be calculated by dividing the number of the abnormal monitoring sites by the total number of the monitoring sites corresponding to the total review task.

Step S414, obtaining auditing abnormal rates corresponding to a plurality of appointed time periods of the auditor, and calculating a first average abnormal rate based on the auditing abnormal rates corresponding to the appointed time periods;

in order to avoid the influence of accidental factors, the abnormal auditing rate of one day or several days cannot represent that the auditor has abnormal auditing behaviors, so that the auditing abnormal rates corresponding to a plurality of specified time periods of the auditor can be obtained for one auditor, the first mean value abnormal rate is calculated based on the auditing abnormal rates corresponding to the specified time periods, and whether the auditing behaviors of the auditor are abnormal or not is determined based on the first mean value abnormal rate.

The first average anomaly rate is calculated according to the following formula:

(ii) a Wherein,

showing the auditing abnormal rate of the ith appointed time interval, wherein the value of i is [1, n ]]，

Indicating the number of the plurality of specified periods.

And S416, determining the auditing behavior of the auditors according to the first mean value abnormal rate.

Specifically, the determination of the audit behavior may be achieved through steps D1 through D3:

step D1, judging whether the first average value abnormal rate is in a first preset normal rate interval;

if so, step D2 is performed, and if not, step D3 is performed. The first preset normal rate interval may be set according to actual needs, and is not limited herein.

Step D2, determining that the auditing behavior of the auditor is normal behavior;

and D3, determining the auditing action of the auditor as abnormal action.

Besides determining whether the first mean abnormal rate is in the first preset normal rate interval to determine the auditing behavior of the auditor, the determination of the auditing behavior may be implemented through steps E1 to E3:

step E1, searching the auditing behavior grade corresponding to the first average value abnormal rate from a preset auditing behavior grade table;

the corresponding relation between the first mean value abnormal rate and the grade of the auditing behavior is stored in the auditing behavior grade table; specifically, the audit behavior grade table stores the normal grade of the audit behavior, the normal mean value abnormal rate section corresponding to the normal grade of the audit behavior, the abnormal grade of the audit behavior, and the abnormal mean value abnormal rate section corresponding to the abnormal grade of the audit behavior, and determines the corresponding audit behavior grade according to whether the first mean value abnormal rate falls into the normal mean value abnormal rate section or the abnormal mean value abnormal rate section.

Step E2, if the audit behavior level is the normal audit behavior level, determining that the audit behavior of the auditor is normal;

and E3, if the audit behavior grade is the audit behavior abnormal grade, determining that the audit behavior of the auditor is abnormal.

The normal grade of the audit behavior is used for indicating that the audit behavior of the auditor is normal behavior, and the abnormal grade of the audit behavior indicates that the audit behavior of the auditor is normal behavior and corresponding audit evidence needs to be submitted, and the audit department further supervises the auditor to be supervised to supervise so as to verify whether the audit behavior is a problem of the auditor to be supervised or a fault problem of the data acquisition site.

In practical use, the undetermined grade of the audit behavior and the undetermined mean value abnormal rate interval corresponding to the undetermined grade of the audit behavior are stored in the audit behavior grade table, if the first mean value abnormal rate falls into the undetermined mean value abnormal rate interval, it is not very clear whether the audit behavior of the auditor is abnormal, and other verifiers are required to perform the verification, so the verification process can be realized through steps F1 to F5:

step F1, sending the total audit tasks corresponding to the designated time intervals to other verifiers to calculate a second average abnormal rate;

the process of calculating the second average value abnormal rate by the other verifiers according to the total audit tasks corresponding to the plurality of specified time periods is the same as the process of calculating the first average value abnormal rate by the auditors, and therefore, detailed description is not given here.

Step F2, calculating the absolute difference of the first average value abnormal rate and the second average value abnormal rate to obtain a difference value abnormal rate;

the difference anomaly rate is a non-negative number, so that when the difference anomaly rate is calculated, the difference between the first average anomaly rate and the second average anomaly rate can be calculated, and then the difference is calculated in absolute value to obtain the difference anomaly rate.

Step F3, judging whether the difference abnormal rate is in a second preset normal rate interval;

if so, go to step F4, if not, go to step F5.

Step F4, determining that the auditing behavior of the auditor is normal behavior;

and step F5, determining that the audit behavior of the auditor is abnormal behavior.

Generally, when it is determined that the audit behavior is an abnormal behavior, a supervising department needs to supervise the audit staff, in this embodiment, the supervising mode can adopt a sampling supervising mode, that is, audit data with a high traffic violation rate is extracted from the audit data, then whether input data corresponding to the part of the audit data is input or not is searched in an illegal data input platform, if the input data of the part of the audit data does not exist or the input quantity is lower than a preset value, it can be definitely determined that the audit staff to be supervised has a data audit problem, and the supervising department can adopt corresponding wordings to carry out audit punishment on the audit staff to be supervised, so as to improve the audit atmosphere and improve the monitoring strength, thereby being beneficial to management and control of the traffic violation behavior.

Corresponding to the method embodiment, the embodiment of the invention provides an anomaly determination device in a traffic data auditing task, wherein the device is applied to a server, the server is in communication connection with an illegal data entry platform and monitoring sites, a distribution statistical model corresponding to each monitoring site is prestored in the server, and the distribution statistical model is used for representing a normal recording rate probability interval corresponding to the monitoring site; fig. 7 is a schematic structural diagram showing an abnormality determination apparatus in a traffic data audit task, and as shown in fig. 7, the apparatus includes:

the site clustering module 710 is configured to obtain geographic position information corresponding to each monitoring site, and perform clustering processing on each monitoring site according to the geographic position information to obtain a plurality of monitoring site clusters;

a weight determining module 720, configured to obtain, from historical audit information of an auditor, an audit time period weight of the auditor, and a historical access weight of each monitoring station corresponding to the auditor;

a task determining module 730, configured to determine, according to the review time period weight and the historical access weight, the review tasks that the reviewer needs to process in the multiple monitoring site clusters, respectively, to obtain a total review task corresponding to the reviewer; each audit task in the total audit tasks corresponds to audit data of a specific time period in a monitoring station;

and the anomaly determination module 740 is configured to input the audit data and the entered data corresponding to each audit task processed by the auditor into the distribution statistical model corresponding to the audit task, so as to obtain an anomaly determination result corresponding to the auditor.

The embodiment of the application provides an abnormity determining device in a traffic data auditing task, and the method comprises the steps of firstly, considering factors of main sources generated by illegal transaction data in three traffic data auditing tasks, namely auditing data geographic position repeatability, auditing data time period repeatability, auditing data monitoring station repeatability and the like, distributing auditing data with certain data and business discreteness for an auditor, and avoiding illegal transaction situations in auditing work; and then acquiring entry data corresponding to each audit task in the total audit tasks processed by the auditor, and inputting the audit data group and the entry data group of the same monitoring station into a distribution statistical model corresponding to the same monitoring station to obtain an abnormal determination result of the same monitoring station, which is output by the distribution statistical model based on a normal recording rate probability interval corresponding to the same monitoring station. The technical scheme provided by the embodiment of the invention effectively removes the traffic data auditing quality problem from various abnormal situations, realizes the purpose of directionally and accurately determining the abnormity of the auditing task, and is further beneficial to improving the accuracy of data input in a traffic violation data platform.

An electronic device is further provided in the embodiment of the present application, as shown in fig. 8, which is a schematic structural diagram of the electronic device, where the electronic device includes a processor 121 and a memory 120, where the memory 120 stores computer-executable instructions that can be executed by the processor 121, and the processor 121 executes the computer-executable instructions to implement the abnormality determining method in the traffic data auditing task.

In the embodiment shown in fig. 8, the electronic device further comprises a bus 122 and a communication interface 123, wherein the processor 121, the communication interface 123 and the memory 120 are connected by the bus 122.

The Memory 120 may include a high-speed Random Access Memory (RAM) and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 123 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, and the like may be used. The bus 122 may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus 122 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one double-headed arrow is shown in FIG. 8, but that does not indicate only one bus or one type of bus.

The processor 121 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 121. The Processor 121 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component. 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 application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory, and the processor 121 reads the information in the memory, and completes the steps of the abnormality determination method in the traffic data auditing task of the foregoing embodiment in combination with the hardware thereof.

The embodiment of the present application further provides a computer-readable storage medium, where computer-executable instructions are stored, and when the computer-executable instructions are called and executed by a processor, the computer-executable instructions cause the processor to implement the method for determining an anomaly in the traffic data auditing task, where specific implementation may refer to the foregoing method embodiment, and details are not described herein again.

The computer program product of the method and the device for determining an abnormality in a traffic data auditing task provided by the embodiment of the application includes a computer-readable storage medium storing program codes, instructions included in the program codes can be used for executing the method described in the foregoing method embodiment, and specific implementation can refer to the method embodiment, and is not described herein again.

Unless specifically stated otherwise, the relative steps, numerical expressions, and values of the components and steps set forth in these embodiments do not limit the scope of the present application.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present application. Furthermore, the terms "first," "second," and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.

Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope disclosed in the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the exemplary embodiments of the present application, and are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for determining abnormity in a traffic data auditing task is characterized in that the method is applied to a server, the server is in communication connection with an illegal data entry platform and monitoring sites, a distribution statistical model corresponding to each monitoring site is prestored in the server, and the distribution statistical model is used for representing a normal recording rate probability interval corresponding to the monitoring site, and the method comprises the following steps:

2. The method according to claim 1, wherein the determining, according to the review time period weight and the historical access weight, the review tasks that the reviewer needs to process in the plurality of monitoring site clusters respectively to obtain a total review task corresponding to the reviewer includes:

determining the monitoring sites corresponding to the first number of target elements and the auditing data represented by the auditing time period as the auditing tasks of the auditors;

3. The method according to claim 2, wherein the determining audit data represented by the monitoring sites and the audit time periods corresponding to the first number of target elements as the audit task of the auditor specifically includes:

4. The method according to claim 1, wherein the obtaining of the audit time period weight of the auditor from the historical audit information of the auditor and the historical access weight of the auditor corresponding to each monitoring site specifically includes:

5. The method according to claim 1, wherein the audit data and the entry data corresponding to each audit task processed by the auditor are obtained by:

6. The method according to claim 1, wherein the step of inputting the audit data and the entry data corresponding to each audit task processed by the auditor into the distribution statistical model corresponding to the audit task to obtain the anomaly determination result corresponding to the auditor includes:

7. The method of claim 6, further comprising:

8. The utility model provides an unusual confirming device in traffic data audit task, its characterized in that, the device is applied to the server, the server with illegal data entry platform and monitoring website communication connection, the server prestores the distribution statistical model that each monitoring website corresponds, the distribution statistical model is used for the normal recording rate probability interval that this monitoring website corresponds of representation, the device includes:

9. An electronic device, characterized in that the electronic device comprises:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to perform the anomaly determination method in the traffic data review task of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that the storage medium stores a computer program executable by a processor to perform the method of abnormality determination in a traffic data review task according to any one of claims 1 to 7.