CN116416199A

CN116416199A - Security check graph quality detection method, device, equipment, medium and program product

Info

Publication number: CN116416199A
Application number: CN202111680675.1A
Authority: CN
Inventors: 陈志强; 彭华; 党杰; 宁洪志; 李玮; 王涛; 田龙; 张洋
Original assignee: Nuctech Co Ltd
Current assignee: Nuctech Co Ltd
Priority date: 2021-12-31
Filing date: 2021-12-31
Publication date: 2023-07-11

Abstract

The disclosure provides a quality detection method, device, equipment, medium and program product for a security inspection judgment chart, and belongs to the technical field of security inspection. The security check graph quality detection method comprises the following steps: obtaining judgment chart data to be evaluated according to the associated security inspection detection image and eye movement data; and comparing the judgment chart data to be evaluated with the standard judgment chart data to determine a first judgment chart quality detection result.

Description

Security check graph quality detection method, device, equipment, medium and program product

Technical Field

The disclosure relates to the technical field of security inspection, in particular to a security inspection judgment chart quality detection method, a device, equipment, a medium and a program product.

Background

In recent years, the efficiency and quality of security checks in places such as airports have also presented a great challenge as the peak of passenger flow is continuously being climbed. How to quickly and efficiently realize high-quality security inspection in a safe and controllable range has become a problem to be solved.

The security inspection graph refers to the process that security inspection graph personnel interpret detection images such as X-rays of luggage and goods, and the quality detection of the current security inspection graph is mainly based on video monitoring, and only coarse-grained behaviors such as whether the security inspection graph personnel is on duty, chatting and the like can be monitored, so that the quality detection efficiency of the security inspection graph is low.

Disclosure of Invention

In view of the foregoing, an object of the present disclosure is to provide a security check chart quality detection method, apparatus, device, medium and program product with higher efficiency.

According to an aspect of the present disclosure, there is provided a quality detection method for a security check graph, including: obtaining judgment chart data to be evaluated according to the associated security inspection detection image and eye movement data; and comparing the judgment chart data to be evaluated with the standard judgment chart data to determine a first judgment chart quality detection result.

According to an embodiment of the present disclosure, comparing the to-be-evaluated graph judgment data with the standard graph judgment data, determining the first graph judgment quality detection result includes: processing the graph judgment data to be evaluated according to the graph judgment index to obtain graph judgment index data to be evaluated; respectively comparing the to-be-evaluated graph judging index data with the same graph judging index attribute with the standard graph judging index data to obtain a graph judging quality index result; and determining a first judgment chart quality detection result according to the judgment chart quality index result.

According to an embodiment of the present disclosure, the decision graph data to be evaluated includes a gaze point, which represents: aiming at a specific security inspection image, a user focuses on the gazing position point of the security inspection image; the graph judging index at least comprises one of the following: judgment chart attention degree, the judgment chart attention degree represents: the user averages the total duration of the fixation time of the fixation point per unit time in a specific time period, wherein the fixation point represents the fixation point in the security inspection image; graph judging operation liveness, the graph judging operation liveness represents: the user averages the frequency of graph judging operation per unit time period in a specific time period; first completion rate, first completion rate represents: aiming at a specific security inspection image, the proportion of time spent by a user to watch a first attention point for the first time to the total duration of the judging graph; review rate, review rate represents: for a specific attention point, the proportion of the times that the user looks back at the specific attention point to the times that the user looks at the specific attention point; alternatively, the review rate represents: for each concern point of the specific security inspection image, the number of the concern points which are reviewed by the user accounts for the proportion of the total number of each concern point of the specific security inspection image; a time length of interest distribution, the time length of interest distribution representing: for a specific security inspection image, the gazing time length of a user for each region of interest, wherein the region of interest represents the region comprising at least one point of interest; a degree of interest distribution, the degree of interest distribution representing: the user averages the total number of the judgment pictures and the attention degree of the judgment pictures in each unit time period in a specific time period; search accuracy distribution, search accuracy distribution representation: for a specific security inspection image, the area of the concerned region accounts for the proportion of the area of the specific security inspection image; graph judging proficiency, the graph judging proficiency represents: the total time length of judging the graph of the user in a specific time period; graph judging track, which represents: the image is detected for a particular security check, a trajectory formed by the user's gaze point over time.

According to an embodiment of the present disclosure, determining a first graph quality detection result according to a graph quality index result includes: and determining a weighted sum of the quality index results of each judgment chart according to the weight of each judgment chart index to obtain a first judgment chart quality detection result.

According to an embodiment of the present disclosure, comparing the to-be-evaluated graph judgment data with the standard graph judgment data, determining the first graph judgment quality detection result includes: comparing the judgment chart data to be evaluated with the standard judgment chart data, and determining judgment chart deviation data of the judgment chart data to be evaluated relative to the standard judgment chart data; and comparing the judgment chart deviation data with a standard threshold value, and determining a first judgment chart quality detection result.

According to an embodiment of the disclosure, the security check judgment chart quality detection method further includes: and determining standard judgment chart data according to the attribute of the security inspection detection image.

According to an embodiment of the disclosure, the security check judgment chart quality detection method further includes: determining user state data according to the facial image of the user; and determining a second judgment chart quality detection result according to the user state data.

According to an embodiment of the present disclosure, determining the second decision quality detection result according to the user status data includes: the facial image of the user is identified and user status data with status tags is determined.

According to an embodiment of the disclosure, the security check judgment chart quality detection method further includes: and determining a target judgment chart quality detection result according to the first judgment chart quality detection result and the second judgment chart quality detection result.

According to an embodiment of the disclosure, the first quality detection result of the judgment chart, the second quality detection result of the judgment chart, and the target quality detection result of the judgment chart respectively include pass and fail, and the security inspection quality detection method further includes: and sending a prompt signal to the security check graph judging end in response to at least one of the first graph judging quality detection result, the second graph judging quality detection result and the target graph judging quality detection result being unqualified.

According to another aspect of the present disclosure, there is provided a security check graph quality detection apparatus, including: the judging graph data acquisition module to be evaluated is used for acquiring judging graph data to be evaluated according to the associated security inspection image and eye movement data; the first judgment chart quality detection result determining module is used for comparing the judgment chart data to be evaluated with the standard judgment chart data to determine a first judgment chart quality detection result.

According to still another aspect of the present disclosure, there is provided an electronic apparatus including: one or more processors; and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the quality detection method of the security check graph of the embodiments of the present disclosure.

According to yet another aspect of the present disclosure, there is also provided a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the security check graph quality detection method of the embodiments of the present disclosure.

Drawings

FIG. 1 schematically illustrates a system architecture of a security decision quality detection method according to an embodiment of the disclosure;

FIG. 2 schematically illustrates a flow chart of a security decision quality detection method in accordance with an embodiment of the present disclosure;

fig. 3 schematically illustrates a flowchart of operation S220 according to an embodiment of the present disclosure;

fig. 4 schematically illustrates a flowchart of operation S23 according to an embodiment of the present disclosure;

fig. 5 schematically illustrates a flowchart of operation S220 according to another embodiment of the present disclosure;

FIG. 6 schematically illustrates a flow chart of a security decision quality detection method in accordance with another embodiment of the present disclosure;

FIG. 7 schematically illustrates a flow chart of a security decision quality detection method in accordance with yet another embodiment of the present disclosure;

FIG. 8 schematically illustrates a flowchart of operation S420 of an embodiment of the present disclosure;

FIG. 9 schematically illustrates a flow chart of a security decision quality detection method in accordance with yet another embodiment of the present disclosure;

FIG. 10 schematically illustrates a flow chart of a security decision quality detection method in accordance with yet another embodiment of the present disclosure;

FIG. 11 schematically illustrates a schematic diagram of a security decision quality detection device in accordance with an embodiment of the disclosure;

fig. 12 schematically illustrates a schematic diagram of an electronic device in which a security decision quality detection method of an embodiment of the present disclosure may be implemented.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is only exemplary and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and/or the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the terms used herein should be construed to have meanings consistent with the context of the present specification and should not be construed in an idealized or overly formal manner.

Where expressions like at least one of "A, B and C, etc. are used, the expressions should generally be interpreted in accordance with the meaning as commonly understood by those skilled in the art (e.g.," a system having at least one of A, B and C "shall include, but not be limited to, a system having a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the related personal information of the user all conform to the regulations of related laws and regulations, necessary security measures are taken, and the public order harmony is not violated.

The security inspection judgment chart refers to the process that security inspection judgment chart personnel judges and reads detection images such as X-rays of luggage and goods, and if abnormal behaviors such as unfocused attention, fatigue state, nonstandard judgment chart mode method and the like occur in the process of judging and reading the luggage X-ray images, the accuracy and timeliness of the judgment chart conclusion are seriously affected, and serious potential safety hazards are generated for normal operation of an airport. The quality detection method of the security check and judgment chart is characterized in that video monitoring is carried out on security check and judgment chart personnel through a monitoring camera, generally, only coarse-grained behaviors such as whether the security check and judgment chart personnel are on duty, whether chat and the like can be monitored, then problem recovery is carried out through modes such as post image recovery, video recovery and the like, and the quality detection efficiency of the security check and judgment chart is low.

The embodiment of the disclosure provides a quality detection method for a security check judgment chart, which comprises the following steps: obtaining judgment chart data to be evaluated according to the associated security inspection detection image and eye movement data; and comparing the judgment chart data to be evaluated with the standard judgment chart data to determine a first judgment chart quality detection result.

According to the security check judgment chart quality detection method, the associated security check detection image and eye movement data are used as the to-be-evaluated judgment chart data, so that the to-be-evaluated judgment chart data can be used for security check judgment chart quality detection from the dimension of the point of regard of a user, namely, the security check judgment chart quality can be detected with finer granularity, and the security check judgment chart quality detection efficiency are improved.

Fig. 1 schematically illustrates a system architecture of a security decision quality detection method according to an embodiment of the present disclosure.

As shown in fig. 1, a system architecture 100 according to this embodiment may include a security check graph end 101, a network 102, and a server 103. The network 102 is used to provide a medium for a communication link between the security check graph end 101 and the server 103. Network 102 may include various connection types such as wired, wireless communication links, or fiber optic cables, among others.

A user may interact with server 103 through network 102 using security check graph end 101 to receive or send messages, etc.

The security diagnostic tip 101 may be a variety of electronic devices having a display screen and supporting diagnostic operations, including but not limited to a desktop computer.

The server 103 may be a server providing various services, such as a background management server (merely an example) that provides support for graph judgment operations made by a user using the security check graph judgment terminal 101. The background management server can analyze and process the received data such as the user request and the like, and feed back the processing result (fed back to the security check graph judging end).

It should be noted that, the quality detection method of the security check chart provided in the embodiments of the disclosure may be generally executed by the server 103. Accordingly, the quality detection device for the security check chart provided in the embodiments of the present disclosure may be generally disposed in the server 103. The quality detection method of the security check graph provided by the embodiment of the present disclosure may also be performed by a server or a server cluster that is different from the server 103 and is capable of communicating with the security check graph end 101 and/or the server 103. Accordingly, the quality detection device for the security check graph provided in the embodiments of the present disclosure may also be disposed in a server or a server cluster different from the server 103 and capable of communicating with the security check graph end 101 and/or the server 103.

It should be understood that the number of security check graph ends, networks, and servers in fig. 1 is merely illustrative. Any number of security check graph ends, networks and servers can be provided according to the implementation requirements.

The quality detection method of the security check chart of the disclosed embodiment will be described in detail below by means of fig. 2 to 10 based on the system architecture described in fig. 1.

Fig. 2 schematically illustrates a flow chart of a security decision quality detection method according to an embodiment of the disclosure.

As shown in fig. 2, the quality detection method 200 of the security check chart of the embodiment includes operations S210 to S220.

In operation S210, decision graph data to be evaluated is obtained according to the associated security inspection image and eye movement data.

A security inspection image may be understood as an image generated when a security inspection device performs security inspection, for example an X-ray image may be generated when an X-ray security inspection device performs security inspection. Eye movement data may be understood as gaze point change data caused by eye rotation of a user. The related security inspection image and eye movement data can be understood as the change of the fixation point of the user on the security inspection image, and the related security inspection image and eye movement data are to-be-evaluated picture judgment data of the user, and the to-be-evaluated picture judgment data can be used for evaluating picture judgment quality of the user.

It should be noted that, because the technical solution of the embodiment of the present disclosure relates to quality detection of a security check chart, in the technical solution of the embodiment of the present disclosure, eye movement data refers to eye movement data of a user to be evaluated for quality of the security check chart, and the user may include, for example: and (5) security inspection and graph judgment personnel.

In operation S220, the to-be-evaluated graph judgment data is compared with the standard graph judgment data to determine a first graph judgment quality detection result.

Standard decision map data can be understood as correct decision map data.

Illustratively, the associated security inspection image and eye movement data may be obtained by an eye movement analysis device disposed at the security inspection map end.

As shown in fig. 3, according to the security inspection judgment chart quality detection method of the embodiment of the disclosure, comparing judgment chart data to be evaluated with standard judgment chart data in operation S220, determining the first judgment chart quality detection result may include operations S21 to S23.

In operation S21, the graph judgment data to be evaluated is processed according to the graph judgment index to obtain graph judgment index data to be evaluated.

In operation S22, the to-be-evaluated graph index data and the standard graph index data with the same graph index attribute are compared respectively to obtain a graph quality index result.

In operation S23, a first graph quality detection result is determined according to the graph quality index result.

The graph judging index may be understood as an index which is preset and may be used to characterize a certain attribute of graph judging data. The image judgment data to be evaluated is obtained by correlating the security inspection image with the eye movement data, so that the image judgment data to be evaluated is comprehensive and complete image judgment data. The graph judgment index data to be evaluated can be processed according to the graph judgment index to obtain graph judgment index data to be evaluated, and the graph judgment index data to be evaluated can represent the graph judgment data to be evaluated with a certain graph judgment index attribute.

The detection of the quality of the security inspection graph is a comprehensive problem, and the evaluation of the quality of the security inspection graph of the security inspection data to be evaluated from multiple angles is a reasonable and accurate detection mode. The quality detection method for the security check judgment chart can evaluate the security check quality of the to-be-evaluated judgment chart data from the angles of all the judgment chart indexes, and is more accurate in security check judgment chart quality detection and higher in efficiency.

For example, in operation S22, the to-be-evaluated graph index data and the standard graph index data having the same graph index attribute are compared, and the graph quality index result obtained may be understood as: presetting standard judgment chart index data, and further respectively comparing the to-be-evaluated judgment chart index data with the same judgment chart index attribute with the standard judgment chart index data to obtain judgment chart quality index results; or, the quality index data of the judgment chart to be evaluated is evaluated manually by a security inspection personnel, for example, so as to obtain the quality index result of the judgment chart.

Illustratively, the decision graph data to be evaluated may include a gaze point, which may represent: aiming at a specific security inspection image, a user focuses on the gazing position point of the security inspection image.

The gaze point can be understood as: the user gazes at a location point whose duration exceeds a certain threshold range. The threshold range may characterize the user for a valid decision graph. For example, the user only looks at a certain position point for 0.0001 seconds, and within 0.0001 seconds, the image of the position point is hardly recognized and analyzed, so the position point is not the point of regard, but the user looks at a certain position point for 1 second, and within 1 second, the user can recognize the image of the position point and analyze the image of the position point, so the position point is the point of regard.

Illustratively, the graph-judging index may include at least one of:

judgment chart attention degree, the judgment chart attention degree can be expressed as follows: and in a specific time period, averaging the total duration of the fixation time of the attention point per unit time period, wherein the attention point represents the fixation point in the security inspection image.

For example, the user should perform an effective security check map by looking at the position of the goods in the security check image, and thus, the point of regard should include the position point of the goods in the security check image.

For example, the unit time period may be minutes.

Graph judging operation activity, the graph judging operation activity can be expressed as follows: the user averages the frequency of graph judging operation per unit time period in a specific time period.

Illustratively, the graph determining operation may include: scaling and processing the security inspection images, and judging the images by the image processing keys.

First completion rate, first completion rate may represent: for a particular security inspection image, the time it takes for the user to first look at the first point of interest is proportional to the total length of the decision graph.

For example, the total time period for the user to judge the security inspection image I is 20 seconds, and the time taken from the start of judging the image to the fixation of the first attention point is 1 second, so that the first completion rate is 5%.

Review rate, review rate may represent: for a specific attention point, the proportion of the times that the user looks back at the specific attention point to the times that the user looks at the specific attention point; alternatively, the review rate represents: for each point of interest of the specific security inspection image, the number of points of interest that the user looks back at is a proportion of the total number of each point of interest of the specific security inspection image.

A time length of interest distribution, which may represent: for a particular security inspection image, the user's gaze duration for each region of interest, the region of interest representing the region of interest comprising at least one point of interest.

A degree of interest distribution, which may represent: the user averages the total number of judgment charts and attention degree of judgment charts in a specific time period.

Search accuracy distribution, which may represent: for a particular security inspection image, the area of the region of interest is a proportion of the area of the particular security inspection image.

Graph judging proficiency, the graph judging proficiency can be expressed as follows: the total time length of the graph judgment of the user in a specific time period.

Graph judging track, which can be expressed as: the image is detected for a particular security check, a trajectory formed by the user's gaze point over time.

Illustratively, the quality detection method of the security check chart of the embodiment of the disclosure may further include: and playing back the judgment chart track, and displaying the fixation point of the user at the security check judgment chart end in real time.

As shown in fig. 4, according to the security inspection graph quality detection method according to the embodiment of the present disclosure, determining the first graph quality detection result according to the graph quality index result in operation S23 may include: operation S231.

In operation S231, a weighted sum of the quality index results of each judgment chart is determined according to the weights of the quality indexes of each judgment chart, so as to obtain a first quality detection result of the judgment chart.

When the quality evaluation of the security check judgment chart is carried out through the judgment chart indexes, each judgment chart index is respectively and partially stressed. According to the quality detection method for the security check graph, the reference degree of each graph judgment index to the quality detection result of the first security check graph can be differentiated through the weight of each graph judgment index, the more accurate quality detection result of the first security check graph can be obtained, and the accuracy and efficiency of the quality detection of the security check graph are improved.

It should be noted that, when the graph judgment index includes one, the weight of the corresponding graph judgment index is 1, and the weighted sum of the graph judgment quality index results is the corresponding graph judgment quality index result itself.

Illustratively, the first decision quality detection result may be quantified in a scored manner.

As shown in fig. 5, comparing the to-be-evaluated decision chart data with the standard decision chart data according to operation S220 of another embodiment of the present disclosure, determining the first decision chart quality detection result may include: operations S31 to S32.

In operation S31, the to-be-evaluated decision chart data is compared with the standard decision chart data, and decision chart deviation data of the to-be-evaluated decision chart data relative to the standard decision chart data is determined.

In operation S32, the decision-making deviation data is compared with a standard threshold value to determine a first decision-making quality detection result.

Illustratively, comparing the to-be-evaluated decision chart data with the standard decision chart data in operation S31, determining decision chart deviation data of the to-be-evaluated decision chart data relative to the standard decision chart data may be understood as: presetting standard judgment chart data, and further comparing the judgment chart data to be evaluated with the standard judgment chart data to determine judgment chart deviation data of the judgment chart data to be evaluated relative to the standard judgment chart data; or, the judgment chart data to be evaluated is evaluated manually by a security inspection personnel, for example, so as to obtain judgment chart deviation data.

Illustratively, comparing the graph deviation data with the standard threshold in operation S32, determining the first graph quality detection result may be understood as: presetting a standard threshold value, and comparing the judgment chart deviation data with the standard threshold value to determine a first judgment chart quality detection result; or, evaluating the judgment chart deviation data manually by a security inspection personnel, for example, so as to obtain a first judgment chart quality detection result.

The quality detection method for the security check chart can accurately detect the quality of the security check chart, and has higher quality detection efficiency of the security check chart.

As shown in fig. 6, the security check map quality detection method 300 according to still another embodiment of the present disclosure may further include operation S310.

In operation S310, standard judgment chart data is determined according to the attribute of the security inspection image.

The security inspection image judgment personnel conduct image judgment operation on the security inspection detection images, different security inspection images possibly have different attributes, the security inspection images with different attributes show different characteristics, and standard image judgment data serve as comparison objects of the image judgment data to be evaluated and also influence the accuracy of the quality detection result of the first image judgment, so that the security inspection image quality detection method can determine standard image judgment data according to the attribute adaptability of the security inspection images, and the accuracy of the security inspection image quality detection is improved.

Illustratively, the attribute of the security inspection image may include a complexity attribute, for example, the complexity attribute of a certain security inspection image a is: complexity, another security inspection detection image B has the following complexity attribute: is simple. Then, illustratively, the total time length of the standard graph judgment data corresponding to the security detection image a is longer than that of the standard graph judgment data corresponding to the security detection image B. The number of the attention points of the standard judgment chart data corresponding to the security detection image A is larger than that of the attention points of the standard judgment chart data corresponding to the security detection image B.

As shown in fig. 7, the security inspection map quality detection method 400 according to still another embodiment of the present disclosure may further include operations S410 to S420.

In operation S410, user state data is determined according to a face image of a user.

In operation S420, a second decision quality detection result is determined according to the user status data.

The quality of the decision map is also related to the user's state, e.g. the user state data determined from the facial image of the user characterizes the user as being in a tired state, there may be a problem with the low quality of the decision map for the user. The quality detection method for the security check map can evaluate the user state data different from the user fixation point, and can detect the quality of the security check map from the angle of the user state, so that the accuracy of the quality detection of the security check map is improved.

For example, the user status data and the second decision quality detection result may be determined manually by, for example, a security inspection personnel.

As shown in fig. 8, according to the security check judgment chart quality detection method of the embodiment of the present disclosure, determining the second judgment chart quality detection result according to the user state data of operation S420 may include operation S421.

In operation S421, a face image of a user is recognized, and user state data having a state label is determined.

For example, the user status data with status tags may be determined by identifying facial images of the user through a detection model. The input of the detection model is a face image of the user, and the detection model can perform feature extraction on the face image of the user and output data (user state data) representing the state of the user. The user status data is in the form of a tag. For example, the tag may include: fatigue, eye closure, line of sight transfer, yawning.

Illustratively, the detection model may include a CNN (Convolutional Neural Networks, convolutional neural network) model.

As shown in fig. 9, the security inspection map quality detection method 500 according to still another embodiment of the present disclosure may further include operation S510.

In operation S510, a target quality detection result of the graph is determined according to the first quality detection result and the second quality detection result.

The quality detection method for the security check judgment chart can be used for accurately determining the quality detection result of the target judgment chart by combining the quality detection result of the first judgment chart and the quality detection result of the second judgment chart, and improves the quality detection efficiency of the security check judgment chart.

For example, a weighted sum of the first judgment chart quality detection result and the second judgment chart quality detection result may be determined as the target judgment chart quality detection result according to weights of the first judgment chart quality detection result and the second judgment chart quality detection result, respectively.

As shown in fig. 10, according to a security inspection map quality detection method 600 of still another embodiment of the present disclosure, a first map quality detection result, a second map quality detection result, and a target map quality detection result may include pass and fail, respectively, and the security inspection map quality detection method 600 may include operation S610.

In operation S610, in response to at least one of the first quality detection result, the second quality detection result, and the target quality detection result being failed, a prompt signal is sent to the security inspection graph end.

The alert signal may comprise, for example, an audible and visual signal or a text alert signal. The text prompting signal can be displayed on the security check graph judging end in a popup window mode. According to the quality detection method for the security check graph, timely intervention can be performed on the security check graph judging process of security check graph judging personnel in a mode of sending the prompt signal to the security check graph judging terminal, and the efficiency of the quality detection of the security check graph is improved.

Based on the security inspection graph quality detection method, the present disclosure also provides a security inspection graph quality detection device. The device will be described in detail below with reference to fig. 11.

Fig. 11 schematically illustrates a block diagram of a security inspection chart quality detection apparatus according to an embodiment of the present disclosure.

As shown in fig. 11, the security check judgment chart quality detection apparatus 700 of this embodiment includes a judgment chart to be evaluated data acquisition module 710 and a first judgment chart quality detection result determination module 720.

The to-be-evaluated graph judging data obtaining module 710 is configured to obtain to-be-evaluated graph judging data according to the associated security inspection image and eye movement data. In an embodiment, the to-be-evaluated decision chart data obtaining module 710 may be configured to perform the operation S210 described above, which is not described herein.

The first quality detection result determining module 720 is configured to compare the to-be-evaluated quality detection result with the standard quality detection result, and determine a first quality detection result. In an embodiment, the first decision quality detection result determining module 720 may be configured to perform the operation S220 described above, which is not described herein.

According to an embodiment of the present disclosure, any plurality of modules in the to-be-evaluated decision chart data acquisition module 710 and the first decision chart quality detection result determination module 720 may be combined in one module to be implemented, or any one of the modules may be split into a plurality of modules. Alternatively, at least some of the functionality of one or more of the modules may be combined with at least some of the functionality of other modules and implemented in one module. According to embodiments of the present disclosure, at least one of the decision to be evaluated data acquisition module 710 and the first decision quality detection result determination module 720 may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware in any other reasonable manner of integrating or packaging the circuits, or in any one of or a suitable combination of three of software, hardware, and firmware. Alternatively, at least one of the to-be-evaluated decision data acquisition module 710 and the first decision quality detection result determination module 720 may be at least partially implemented as a computer program module, which, when executed, may perform the corresponding functions.

Fig. 12 schematically illustrates a block diagram of an electronic device adapted to implement a security decision quality detection method in accordance with an embodiment of the disclosure.

As shown in fig. 12, an electronic device 800 according to an embodiment of the present disclosure includes a processor 801 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 802 or a program loaded from a storage section 808 into a Random Access Memory (RAM) 803. The processor 801 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or an associated chipset and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), or the like. The processor 801 may also include on-board memory for caching purposes. The processor 801 may include a single processing unit or multiple processing units for performing the different actions of the method flows according to embodiments of the disclosure.

In the RAM 803, various programs and data required for the operation of the electronic device 800 are stored. The processor 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. The processor 801 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 802 and/or the RAM 803. Note that the program may be stored in one or more memories other than the ROM 802 and the RAM 803. The processor 801 may also perform various operations of the method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.

According to an embodiment of the present disclosure, the electronic device 800 may also include an input/output (I/O) interface 805, the input/output (I/O) interface 805 also being connected to the bus 804. The electronic device 800 may also include one or more of the following components connected to the I/O interface 805: an input portion 806 including a keyboard, mouse, etc.; an output portion 807 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and a speaker; a storage section 808 including a hard disk or the like; and a communication section 809 including a network interface card such as a LAN card, a modem, or the like. The communication section 809 performs communication processing via a network such as the internet. The drive 810 is also connected to the I/O interface 805 as needed. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 810 as needed so that a computer program read out therefrom is mounted into the storage section 808 as needed.

The present disclosure also provides a computer-readable storage medium that may be embodied in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the apparatus/device/system. The computer-readable storage medium carries one or more programs which, when executed, implement methods in accordance with embodiments of the present disclosure.

According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, the computer-readable storage medium may include ROM 802 and/or RAM 803 and/or one or more memories other than ROM 802 and RAM 803 described above.

Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowcharts. When the computer program product runs in a computer system, the program code is used for enabling the computer system to realize the security check graph quality detection method provided by the embodiment of the disclosure.

The above-described functions defined in the system/apparatus of the embodiments of the present disclosure are performed when the computer program is executed by the processor 801. The systems, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed, and downloaded and installed in the form of a signal on a network medium, and/or from a removable medium 811 via a communication portion 809. The computer program may include program code that may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 809, and/or installed from the removable media 811. The above-described functions defined in the system of the embodiments of the present disclosure are performed when the computer program is executed by the processor 801. The systems, devices, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

According to embodiments of the present disclosure, program code for performing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, such computer programs may be implemented in high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. Programming languages include, but are not limited to, such as Java, c++, python, "C" or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Those skilled in the art will appreciate that the features recited in the various embodiments of the disclosure and/or in the claims may be provided in a variety of combinations and/or combinations, even if such combinations or combinations are not explicitly recited in the disclosure. In particular, the features recited in the various embodiments of the present disclosure and/or the claims may be variously combined and/or combined without departing from the spirit and teachings of the present disclosure. All such combinations and/or combinations fall within the scope of the present disclosure.

The embodiments of the present disclosure are described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the embodiments cannot be used advantageously in combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be made by those skilled in the art without departing from the scope of the disclosure, and such alternatives and modifications are intended to fall within the scope of the disclosure.

Claims

1. A quality detection method of a security check judgment chart comprises the following steps:

obtaining judgment chart data to be evaluated according to the associated security inspection detection image and eye movement data;

And comparing the to-be-evaluated judgment chart data with standard judgment chart data to determine a first judgment chart quality detection result.

2. The method of claim 1, wherein comparing the graph data to be evaluated with standard graph data, determining a first graph quality test result comprises:

processing the graph judgment data to be evaluated according to graph judgment indexes, obtaining the index data of the judging graph to be evaluated;

respectively comparing the to-be-evaluated graph judging index data with the standard graph judging index data with the same graph judging index attribute to obtain a graph judging quality index result;

and determining the first judgment chart quality detection result according to the judgment chart quality index result.

3. The method of claim 2, wherein,

the to-be-evaluated judgment chart data comprises a fixation point, wherein the fixation point represents: aiming at a specific security inspection image, a user focuses on the gazing position point of the security inspection image;

the graph judging index at least comprises one of the following:

a judgment chart attention degree, the judgment chart attention degree representing: the user averages the total duration of the fixation time of the fixation point per unit time period in a specific time period, wherein the fixation point represents the fixation point in the security inspection image;

Graph judging operation liveness, wherein the graph judging operation liveness represents: the user averages the frequency of graph judging operation per unit time period in a specific time period;

a first completion rate, the first completion rate representing: aiming at a specific security inspection image, the proportion of time spent by a user to watch a first attention point for the first time to the total duration of the judging graph;

a review rate, the review rate representing: for a specific focus point, the number of times the user looks back at the specific focus point occupies the proportion of the number of times the user looks at the specific focus point; alternatively, the review rate represents: aiming at each concern point of a specific security inspection image, the number of the concern points which are reviewed by a user accounts for the proportion of the total number of each concern point of the specific security inspection image;

a time duration distribution of interest, the time duration distribution of interest representing: for a specific security inspection image, the gazing time length of a user for each concerned area, wherein the concerned area represents the area comprising at least one concerned point;

a degree of interest distribution, the degree of interest distribution representing: the user averages the total number of the judgment pictures and the attention degree of the judgment pictures in each unit time period in a specific time period;

a search accuracy distribution, the search accuracy distribution representing: for a specific security inspection image, the area of the concerned region occupies the proportion of the area of the specific security inspection image;

Graph judging proficiency, the graph judging proficiency represents: the total time length of judging the graph of the user in a specific time period;

a graph interpretation trace, the graph interpretation trace representing: the image is detected for a particular security check, the trajectory formed by the gaze point of the user over time.

4. The method of claim 2, wherein the determining a first graph quality measure based on the graph quality index result comprises:

and determining a weighted sum of the quality index results of each judgment chart according to the weight of each judgment chart index to obtain the first quality detection result of the judgment chart.

5. The method of claim 1, wherein comparing the graph data to be evaluated with standard graph data, determining a first graph quality test result comprises:

comparing the to-be-evaluated judgment chart data with the standard judgment chart data, and determining judgment chart deviation data of the to-be-evaluated judgment chart data relative to the standard judgment chart data;

and comparing the judgment chart deviation data with a standard threshold value, and determining the first judgment chart quality detection result.

6. The method of any one of claims 1 to 5, further comprising:

and determining the standard judgment chart data according to the attribute of the security inspection detection image.

7. The method of any one of claims 1 to 5, further comprising:

determining user state data according to the facial image of the user;

and determining a second judgment chart quality detection result according to the user state data.

8. The method of claim 7, wherein determining the second decision quality detection result from the user status data comprises:

the facial image of the user is identified and the user status data with status tags is determined.

9. The method of claim 7, further comprising:

and determining a target judgment chart quality detection result according to the first judgment chart quality detection result and the second judgment chart quality detection result.

10. The method of claim 9, the first quality inspection result, the second quality inspection result, and the target quality inspection result respectively include pass and fail, the security inspection quality inspection method further comprising:

and sending a prompt signal to a security check graph judging end in response to at least one of the first graph judging quality detection result, the second graph judging quality detection result and the target graph judging quality detection result being unqualified.

11. A quality detection device for a security check judgment chart comprises:

the judging graph data acquisition module to be evaluated is used for acquiring judging graph data to be evaluated according to the associated security inspection image and eye movement data;

and the first judgment chart quality detection result determining module is used for comparing the judgment chart data to be evaluated with the standard judgment chart data to determine a first judgment chart quality detection result.

12. An electronic device, comprising:

one or more processors;

storage means for storing one or more programs,

wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-10.

13. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method according to any of claims 1 to 10.

14. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 10.