CN115829502A - Machine inspection task display method and device and electronic equipment - Google Patents

Abstract

The disclosure provides a machine inspection task display method and device and electronic equipment. The machine inspection task display method comprises the following steps: acquiring an image to be analyzed, and determining the type information of a target analysis object in the image to be analyzed; determining a target inspection person corresponding to the image to be analyzed; and displaying the image to be analyzed and the recommended image analysis operation combination queue corresponding to the image to be analyzed at the inspection terminal corresponding to the target inspector according to the type information of the target analysis object and the historical operation data of the target analysis object. The image analysis operation efficiency and the checking accuracy of the machine check checking task can be improved.

Description

Method, device and electronic device for machine inspection and inspection task demonstration

technical field

The present disclosure relates to the field of machine inspection technology, and in particular, to a machine inspection task display method, device and electronic equipment.

Background technique

In the field of machine inspection inspection, image analysis is usually performed on the scanned image of the machine inspection object to determine whether the machine inspection object has contained or restricted items. Image analysis includes a variety of image analysis operations. The machine inspection inspector selects one or more image analysis operations to combine based on the actual situation of the image to be analyzed to process the image to be analyzed, and based on the observation results of the processed image to be analyzed Get the analysis conclusion.

In related technologies, due to the large variety of image analysis operations and numerous parameters, the image analysis of machine inspection inspection usually requires experienced machine inspection personnel to operate, and the training process usually requires manual guidance, and less experienced machine inspection personnel can obtain The analysis conclusions are usually not comprehensive and accurate enough, and there may be omissions.

Therefore, improving the operational accuracy and efficiency of image analysis operations in the manual machine inspection process has become a major demand in the field of machine inspection.

It should be noted that the information disclosed in the above background section is only for enhancing the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to those of ordinary skill in the art.

Contents of the invention

The purpose of the present disclosure is to provide a machine inspection task display method, device and electronic equipment for improving the efficiency and accuracy of manual image analysis in the machine inspection process.

According to the first aspect of the embodiments of the present disclosure, there is provided a machine inspection inspection task display method, including: acquiring an image to be analyzed, determining the type information of the target analysis object in the image to be analyzed; determining the corresponding The target inspector; according to the type information of the target analysis object and the historical operation data of the target analysis object, the image to be analyzed and the recommended image corresponding to the image to be analyzed are displayed on the inspection terminal corresponding to the target inspector Analyze operation composition queues.

In an exemplary embodiment of the present disclosure, the recommended image analysis operation combination queue includes a first image analysis operation combination, and according to the type information of the target analysis object and the historical operation data of the target analysis object, Displaying the image to be analyzed and the recommended image analysis operation combination queue corresponding to the image to be analyzed on the inspection terminal corresponding to the target inspector includes: according to the type information of the target analysis object and the historical operation of the target analysis object The historical inspector of the data acquisition target analysis object performs a first image analysis operation combination queue on the target analysis object, and the first image analysis operation combination queue includes a plurality of image analysis operation combinations arranged in a first order. Determining the first image analysis operation combination in the first image analysis operation combination queue as the first image analysis operation combination; displaying the first image analysis operation combination and the second image analysis operation combination in the recommended image analysis operation combination queue An operation control for an image analysis operation combination.

In an exemplary embodiment of the present disclosure, the recommended image analysis operation combination queue includes a second image analysis operation combination, and according to the type information of the target analysis object and the historical operation data of the target analysis object, Displaying the image to be analyzed and the recommended image analysis operation combination queue corresponding to the image to be analyzed on the inspection terminal corresponding to the target inspector includes: according to the historical operation data of the target inspector and the type of the target analysis object information, determining a second image analysis operation combination queue for the target analysis object in the target area where the target inspector is located, the second image analysis operation combination queue includes a plurality of image analysis operation combinations arranged in a second order, Determine the first image analysis operation combination in the second image analysis operation combination queue to be the second image analysis operation combination; display the second image analysis operation combination and the recommended image analysis operation combination queue in the recommended image analysis operation combination queue Operational controls for the second image analysis operation combination.

In an exemplary embodiment of the present disclosure, the recommended image analysis operation combination queue includes a third image analysis operation combination, according to the type information of the target analysis object and the historical operation data of the target analysis object, Displaying the image to be analyzed and the recommended image analysis operation combination queue corresponding to the image to be analyzed on the inspection terminal corresponding to the target inspector includes: according to the historical operation data of the target inspector and the type of the target analysis object information, determining a third image analysis operation combination queue arranged according to the operation frequency of the target inspector on the target analysis object, the third image analysis operation combination queue including a plurality of image analysis operation combinations arranged in a third order , determining the first image analysis operation combination in the third image analysis operation combination queue to be the third image analysis operation combination; in the recommended image analysis operation combination queue, the third image analysis operation combination and the Operation controls for the third image analysis operation combination.

In an exemplary embodiment of the present disclosure, the formation process of the first image analysis operation combination queue includes: regularly acquiring machine-check inspection tasks with correct machine-check inspection conclusions within a preset time range: determining each of the The image analysis operation combination and the target analysis object corresponding to the machine inspection inspection task with a correct machine inspection conclusion; determine the image analysis operation combination set corresponding to each target analysis object; according to the same one in each image analysis operation combination set The number of image analysis operation combinations appearing from large to small forms the first image analysis operation combination queue of the target analysis object corresponding to the image analysis operation combination.

In an exemplary embodiment of the present disclosure, further comprising: determining a plurality of candidate images according to the first image analysis operation combination queue, the second image analysis operation combination queue, and the third image analysis operation combination queue Analyzing operation combinations; determining one or more sequence numbers corresponding to each of the candidate image analysis operation combinations, the one or more sequence numbers including the candidate image analysis operation combination in the first image analysis operation combination queue A sequence number, and/or, a second sequence number in the combination queue of the second image analysis operation, and/or, a third sequence number in the combination queue of the second image analysis operation; according to the first image analysis The first weight corresponding to the operation combination queue, the second weight corresponding to the second image analysis operation combination queue, the third weight corresponding to the third image analysis operation combination queue, and each of the candidate image analysis operation combination The one or more serial numbers determine the score of each of the candidate image analysis operation combinations; according to the scores of each of the candidate image analysis operation combinations, a comprehensive recommended image analysis operation corresponding to the image to be analyzed is generated from large to small Combined queue.

In an exemplary embodiment of the present disclosure, the determining the type information of the target analysis object in the image to be analyzed includes: determining the target analysis object with the largest area ratio in the image to be analyzed; identifying the target The type of the analysis object to form the type information of the target analysis object.

In an exemplary embodiment of the present disclosure, the determining the type information of the target analysis object in the image to be analyzed includes: determining the declaration information corresponding to the image to be analyzed, and the declaration information includes a plurality of analysis objects type and value information; according to the value information of the plurality of analysis objects, determine the analysis object with the highest value as the target analysis object.

In an exemplary embodiment of the present disclosure, the displaying the image to be analyzed on the inspection terminal corresponding to the target inspector and the recommended image analysis operation combination queue corresponding to the image to be analyzed includes: according to the recommendation A plurality of corresponding image analysis operation combinations in the image analysis operation combination queue perform image processing on the image to be analyzed to generate an effect image corresponding to each image analysis operation combination in the recommended image analysis operation combination queue; The image to be analyzed, the effect image corresponding to each image analysis operation combination, and the image analysis operation combination corresponding to each effect image are displayed together on the inspection terminal.

In an exemplary embodiment of the present disclosure, it further includes: according to the category information of the target analysis object, displaying a queue of recommended inspection conclusions corresponding to the image to be analyzed on the inspection terminal corresponding to the target inspector.

According to the second aspect of the embodiments of the present disclosure, there is provided a machine inspection task display device, including:

The target analysis object determination module is configured to acquire the image to be analyzed, and determine the type information of the target analysis object in the image to be analyzed;

A target inspector determination module, configured to determine the target inspector corresponding to the image to be analyzed;

The recommended operation display module is configured to display the image to be analyzed and the image corresponding to the image to be analyzed on the inspection terminal corresponding to the target inspector according to the type information of the target analysis object and the historical operation data of the target analysis object. A combined queue of recommended image analysis operations.

According to a third aspect of the present disclosure, there is provided an electronic device, including: a memory; and a processor coupled to the memory, the processor is configured to execute any one of the above-mentioned operations based on instructions stored in the memory. method described in the item.

According to a fourth aspect of the present disclosure, there is provided a computer-readable storage medium, on which a program is stored, and when the program is executed by a processor, the method for presenting a machine inspection inspection task as described in any one of the above items is implemented.

According to the target analysis object of the machine inspection task and the historical inspection operation data of the target analysis object, the embodiment of the present disclosure can automatically generate and display the recommended image analysis operation combination queue that is most conducive to obtaining accurate analysis conclusions, thereby improving the inspection efficiency of the inspector , reduce the experience requirements for inspectors, and at the same time improve the analysis accuracy of inspectors.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description serve to explain the principles of the disclosure. Apparently, the drawings in the following description are only some embodiments of the present disclosure, and those skilled in the art can obtain other drawings according to these drawings without creative efforts.

Fig. 1 is a flowchart of a method for presenting a machine inspection inspection task in an exemplary embodiment of the present disclosure.

FIG. 2A to FIG. 2C are respectively sub-flow charts of step S3 in three embodiments of the present disclosure.

Fig. 3 is a flow chart of the formation process of the first image analysis operation combination queue in one embodiment of the present disclosure.

Fig. 4 is a sub-flow chart of step S3 in another embodiment of the present disclosure.

Fig. 5 is a sub-flowchart of step S3 in yet another embodiment of the present disclosure.

6A to 6C are schematic diagrams showing a combination queue of recommended image analysis operations in an embodiment of the present disclosure.

Fig. 7 is a flow chart of execution of inspection tasks in one embodiment of the present disclosure.

Fig. 8 is a block diagram of a machine inspection task display device in an exemplary embodiment of the present disclosure.

FIG. 9 is a block diagram of an electronic device in an exemplary embodiment of the present disclosure.

Detailed ways

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided in order to give a thorough understanding of embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details being omitted, or other methods, components, devices, steps, etc. may be adopted. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.

In addition, the drawings are only schematic illustrations of the present disclosure, the same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different network and/or processor means and/or microcontroller means.

Exemplary implementations of the present disclosure will be described in detail below in conjunction with the accompanying drawings.

Fig. 1 is a flowchart of a method for presenting a machine inspection inspection task in an exemplary embodiment of the present disclosure.

Referring to FIG. 1 , a method 100 for displaying machine inspection inspection tasks may include:

Step S1, acquiring the image to be analyzed, and determining the type information of the target analysis object in the image to be analyzed;

Step S2, determining the target inspector corresponding to the image to be analyzed;

Step S3, according to the type information of the target analysis object and the historical operation data of the target analysis object, display the image to be analyzed and the recommended image analysis corresponding to the image to be analyzed on the inspection terminal corresponding to the target inspector. Operates on a combined queue.

According to the target analysis object of the machine inspection task and the historical inspection operation data of the target analysis object, the embodiment of the present disclosure can automatically generate and display the recommended image analysis operation combination queue that is most conducive to obtaining accurate analysis conclusions, thereby improving the inspection efficiency of the inspector , reduce the experience requirements for inspectors, and at the same time improve the analysis accuracy of inspectors.

The image to be analyzed in the embodiment of the present disclosure may be a scanned image in the machine inspection process, and the method in the embodiment of the present disclosure may be executed after the image to be analyzed is formed and before the manual image review task in the machine inspection process is generated. In some embodiments, an intelligent map review link is set before the manual map review task, and an inspection task judged to have suspicious elements in the intelligent map review link will generate a manual map review task. In some other embodiments, it is also possible not to set an intelligent image review link, as long as the image to be analyzed corresponding to the machine inspection task is formed, the method of the embodiment of the present disclosure is executed.

Next, each step of the method 100 for machine inspection and inspection task presentation will be described in detail.

In step S1, an image to be analyzed is acquired, and type information of a target analysis object in the image to be analyzed is determined.

In one embodiment, after the image to be analyzed is acquired, the target analysis object with the largest area ratio in the image to be analyzed can be determined, and then the type of the target analysis object can be automatically identified to form the target analysis object. Kind information.

Among them, the process of automatically identifying the target analysis object can be to extract the image feature points in the image to be analyzed, and automatically identify one or more items according to these feature points, and based on the corresponding features of each item recorded in the preset database Click Type to identify the type of the one or more items. Only one or more types of items occupying the largest area of the image to be analyzed (that is, the proportion of the involved pixels to all pixels of the image to be analyzed) may be identified. For example, item A, item B, item C, and item D are respectively identified in the image to be analyzed, and the proportions of these four items in the image to be analyzed are 37%, 26%, 15%, and 8% respectively. At this time, It is possible to identify only the type of item A with the largest occupied area, or to identify the types of item A, item B, and item C with a preset value before the occupied area (the default value is, for example, 3), or to identify the types of items whose occupied area is within the preset value. Types of A and B items above a threshold (for example, 20%).

When identifying the type of an item, set the item as the target analysis object, and record its type information according to the recognition result; when identifying multiple types of items, each item can be set as the target analysis object, and based on each The article generates and displays a queue of recommended image analysis operations combinations.

In another embodiment of the present disclosure, if there is declaration information for the machine inspection task, such as the customs machine inspection task, the item type and value information (including unit price or total price) recorded in the declaration information can be obtained, and then the value The largest item is identified as the target analysis object. In this case, the item with the most analytical value can be directly determined as the main item for inspection, and the efficiency is high.

In addition, the identified items may be displayed as target analysis items in turn, and the method provided by the embodiment of the present disclosure is executed for each identified item, and the recommended image analysis operation combination queue for each item is switched through a label or other controls .

In step S2, the target inspector corresponding to the image to be analyzed is determined.

In the process of generating a manual image review task for the image to be analyzed, the target inspector who performs the machine inspection and inspection task can be determined in real time according to the preset rules.

The number of target inspectors can be one or more. For example, a machine-based inspection task (manual drawing review task) can correspond to multiple inspection posts, and each inspection post can correspond to multiple inspectors, so each inspector can be used as the target inspection people.

Since each target inspector corresponds to an inspection terminal, the methods of the embodiments of the present disclosure are executed for each target inspector to generate a combined queue of recommended image analysis operations for each target inspector, and correspondingly displayed in each On the inspection terminal where the target inspector is located.

Multiple inspection terminals corresponding to multiple target inspectors can be located in one geographic location (such as an office) or in different geographic locations (such as two cities). No matter where they are, the information can be transmitted through a wired or wireless network. The information corresponding to the machine inspection inspection task. In some embodiments, the method provided by the embodiments of the present disclosure may be executed by multiple servers that check the connection of the terminals.

In addition, since an inspection terminal may be used by different inspectors at different times, the process of identifying the target inspector is not based on the identifier of the inspection terminal, but on the basis of the identifier of each inspector logging into the machine inspection inspection system. (ID) shall prevail to accurately match the target inspector and the inspection terminal currently used. In this case, the historical operation information of each inspector can be saved in the server according to its identifier (ID), so as to avoid the loss of historical operation data after the inspector replaces the inspection information.

In step S3, according to the type information of the target analysis object and the historical operation data of the target analysis object, the image to be analyzed and the recommended image corresponding to the image to be analyzed are displayed on the inspection terminal corresponding to the target inspector Analyze operation composition queues.

The historical operation data includes the historical inspection operation data of multiple inspectors, and the analysis objects and historical inspection results corresponding to each set of historical inspection operation data. The historical operation data can be obtained by cleaning, processing and extracting the image analysis record data during the inspection process after each inspection task is completed. For example, after the on-site inspectors complete the inspection and labeling operation through the mobile PAD or PC computer, they can automatically conduct multi-dimensional analysis of the task execution results. The statistical analysis content includes but is not limited to the following dimensions: task import, export type (entry, Exit)/port location/origin (country)/destination (country)/current time, season/current operator/inspection result/suspicious area intelligent map review result and final result confirmed by the operator. In the end, the task is used as a unit to perform statistical summary on the above dimension data, and update the historical statistical data.

At the business site, some special scenarios and atypical tasks may be encountered, such as business site process testing, smart map review and contraband mapping, etc. Such data will be included in the scope of historical statistical data, which will have a certain impact on the system recommendation. Therefore, operators with system administrator privileges can add tags to such tasks, and do not include such tasks in historical statistics.

The historical operation data of each inspector can be periodically summarized and analyzed to generate historical inspection operation data corresponding to each item. After the target analysis object is determined, the historical inspection operation data of the target analysis object is directly extracted.

The historical operation data also includes the historical operation data of the target inspector. After the target inspector is determined, the historical operation data and analysis conclusions of the target inspector can be extracted to improve the efficiency of generating the recommended image analysis operation combination queue.

The historical operation data formed based on historical statistical data includes at least the inspection tasks performed by each inspector, the inspection conclusion of each inspection task, the correctness of each inspection conclusion determined based on subsequent information, and the image corresponding to each inspection task Analyze operation combinations. Wherein, the combination of image analysis operations includes one or more image analysis operations.

Image analysis operations can also be called image analysis algorithms, which are selected by the inspector by operating the image analysis software by clicking, inputting characters, etc., so as to perform global image processing on the image to be analyzed to form different image processing effects. For example, when the image analysis operation includes five operations of 1, 2, 3, 4, and 5, for an image to be analyzed, the inspector can use 3, 5, and 2 to perform image processing successively, and perform image processing based on the processed image effect. The conclusions were obtained by manual observation.

Due to the different operating habits of different inspectors and the different characteristics of each target analysis object, the image analysis operation combinations set by different inspectors for different target analysis objects are also different. Therefore, the purpose of the embodiments of the present disclosure is to recommend an appropriate sequence of image analysis operation combinations based on the target inspector and the target analysis object, so that the target inspector can select an image analysis operation combination from the queue of recommended image analysis operation combinations to Reduce the impact of the subjective factors of the target inspector on the sequence of image analysis operations. When the target inspector selects an image analysis operation combination in the recommended image analysis operation combination queue, multiple image analysis operations can be automatically performed in the order of the image analysis operation combination, so that the target inspector can perform multiple image analysis through one selection operation, greatly improving the efficiency of image analysis.

Image analysis operations may include operations shown in Table 1.

Table 1

The operations and sub-operations in Table 1 are only examples. In actual applications, the image analysis operation may include more content or other content. Embodiments of the present disclosure do not limit the specific content of the image analysis operation. Those skilled in the art can Set it up yourself.

What needs to be added is that, in addition to the type of operation, the image analysis operation can also include operating parameters. For example, in the above-mentioned logarithmic change operation, multiple operating parameters (logarithm 1, logarithm 2, logarithm 3) can be preset for Selection, the selection process of the operation parameters can also be referred to as a sub-operation. In practical applications, the inspector can modify the operation parameters corresponding to each operation. When the modified operation parameters do not exist in the historical records, a new sub-operation will be automatically generated and recorded for subsequent direct selection.

What is shown in Table 1 is only an example. In practical applications, the image analysis operation may also include more types of operations and sub-types of operations.

Table 2 is a schematic illustration of historical operation records of inspectors on images to be analyzed for a machine inspection inspection task.

Table 2:

Referring to Table 2, in an inspection task, historical operation records can include operation date, operation time, image analysis operations and their codes. With the increase of operations, the combination of image analysis operations changes in real time, recording each image analysis operation and its code. order of execution. After the inspection task is completed, record the final image analysis operation sequence as the image analysis operation combination corresponding to the inspection task. The image analysis operations in Table 2 may be different image analysis operations, which are only examples.

For each completed inspection task, record its image analysis operation combination, the target inspection object corresponding to the inspection task (main types of items to be inspected), and the inspection conclusion. Finally, obtain the follow-up seized data and review data corresponding to the inspection task on a regular basis , to record whether the inspection conclusion is correct. The re-inspection data is the analysis conclusion of the same inspection task by a higher-level drawing review post, and the subsequent seizure data includes but is not limited to the results of unpacking inspection, manual inspection, dog sniffing inspection, and other law enforcement agencies.

If the inspection conclusion is that there is no abnormality, but the subsequent review data or seized data is abnormal, the inspection conclusion is incorrect; if the inspection conclusion is that an abnormality is found, but the subsequent review data or seized data is no abnormality, the inspection conclusion is incorrect; If the inspection conclusion is that there is no abnormality, and the subsequent review data or seized data shows that there is no abnormality, the inspection conclusion is correct;

Judgments on inspection conclusions can be made on a regular basis based on the latest data and end within a certain period. For example, within three days after the end of the inspection task, update the re-inspection data once, update the subsequent seized data every day, and end the data update on the fourth day after the end of the inspection task, and save the final judgment on the inspection conclusion.

Next, the historical operation data, the image to be analyzed and the target analysis object corresponding to the current inspection task can be comprehensively used to determine the recommended image analysis operation combination queue corresponding to the image to be analyzed.

FIG. 2A to FIG. 2C are respectively sub-flow charts of step S3 in three embodiments of the present disclosure.

Referring to FIG. 2A, in one embodiment, the recommended image analysis operation combination queue includes a first image analysis operation combination, and step S3 may include:

Step S31, according to the type information of the target analysis object and the historical inspection operation data of the target analysis object, obtain the first image analysis operation combination queue of the target analysis object's historical inspector on the target analysis object, the The first image analysis operation combination queue includes a plurality of image analysis operation combinations arranged in a first order, and the first image analysis operation combination in the first image analysis operation combination queue is determined to be the first image analysis operation combination;

Step S32, displaying the first image analysis operation combination and the operation controls of the first image analysis operation combination in the recommended image analysis operation combination queue.

Referring to FIG. 2B, in one embodiment, the recommended image analysis operation combination queue includes a second image analysis operation combination, and step S3 may include:

Step S33, according to the historical operation data of the target inspector and the type information of the target analysis object, determine the second image analysis operation combination queue for the target analysis object in the area where the target inspector is located, the second The image analysis operation combination queue includes a plurality of image analysis operation combinations arranged in a second order, and the first image analysis operation combination in the second image analysis operation combination queue is determined to be the second image analysis operation combination;

Step S34, displaying the second image analysis operation combination and the operation controls of the second image analysis operation combination in the recommended image analysis operation combination queue.

Referring to FIG. 2C, in one embodiment, the recommended image analysis operation combination queue includes a third image analysis operation combination, and step S3 may include:

Step S35, according to the historical operation data of the target inspector and the type information of the target analysis object, determine the third image analysis operation combination queue arranged according to the operation frequency of the target inspector on the target analysis object, so The third image analysis operation combination queue includes a plurality of image analysis operation combinations arranged in a third order, and the first image analysis operation combination in the third image analysis operation combination queue is determined to be the third image analysis operation combination;

Step S36 , displaying the operation controls of the third image analysis operation combination in the recommended image analysis operation combination queue.

In an embodiment of the present disclosure, the recommended image analysis operation combination queue may also include two or three of the three image analysis operation combinations formed by the above three factors. In addition, those skilled in the art can set the image analysis operation combination queue formed by other factors by themselves, and combine one or more image analysis operations in the image analysis operation combination in the image analysis operation combination queue into the recommended image analysis operation combination queue displayed in . Although in the above-mentioned embodiment, only one image analysis operation combination in each image analysis operation combination queue is selected to be displayed in the recommended image analysis operation combination, it can be understood that each image analysis operation combination can also be sequentially displayed each time. Select two or more image analysis operation combinations in the queue to be displayed in the recommended image analysis operation combination queue.

Next, the formation process of the combination queues of the above three image analysis operations will be described in detail.

Firstly, the database is read, and the corresponding combination queue for generating the first image analysis operation is directly acquired according to the type of the target analysis object.

Fig. 3 is a flow chart of the formation process of the first image analysis operation combination queue in one embodiment of the present disclosure.

Referring to FIG. 3, the formation process of the first image analysis operation combination queue may include:

Step S311, regularly obtain the machine-checked inspection tasks with correct machine-checked inspection conclusions within the preset time range:

Step S312, determining the image analysis operation combination and the target analysis object corresponding to each machine-inspection inspection task whose machine-inspection inspection conclusion is correct;

Step S313, determining an image analysis operation combination set corresponding to each target analysis object;

Step S314, according to the number of occurrences of the same image analysis operation combination in each of the image analysis operation combination sets from large to small, forming the first image analysis operation of the target analysis object corresponding to the image analysis operation combination Combined queue.

In the embodiment shown in FIG. 3 , only inspection tasks with correct inspection conclusions are selected for analysis to ensure the accuracy of image analysis conclusions. Among them, the inspection tasks with correct inspection conclusions come from the historical database of all completed inspection tasks, and are performed by different inspectors.

Next, summarize and classify the target analysis objects of each inspection task with correct inspection conclusions, and obtain the image analysis operation combination set corresponding to each target analysis object. For example, the image analysis operation combination set corresponding to item A includes 5 image analysis operations. Image analysis operation combination a appeared 3 times, image analysis operation combination b appeared 4 times, image analysis operation combination c appeared 1 time, image analysis operation combination d appeared 10 times, image analysis operation combination e appeared 6 times.

Finally, the first image analysis operation combination queue corresponding to item A can be formed according to the occurrence number of each image analysis operation combination from large to small. In the above example, the image operation of the first image analysis operation combination queue corresponding to item A The combination numbers are (d, e, b, a, c), and it should be noted that each number is a combination of image analysis operations rather than an image analysis operation.

The first image analysis operation combination queue may be formed regularly and stored in the database, so that after the target analysis object is determined, the first image analysis operation combination queue corresponding to the target analysis object is directly read from the database.

After the first image analysis operation combination is formed, the first image analysis operation combination in the first image analysis operation combination queue may be selected as the first image analysis operation combination in the recommended image analysis operation combination queue.

In addition, a second image analysis operation combination queue for the target analysis object may also be formed according to the target area where the target inspector is located. The scope of the target area where the target inspector is located can be set by those skilled in the art, such as the customs inspection station where the target inspector is located, the city where the target inspector is located, the province where the target inspector is located, etc. The process of forming the second image analysis operation combination queue based on the target area where the target inspector is located is similar to the process of forming the first image analysis operation combination queue. The only difference is that the historical operation data used is not the historical operation data corresponding to all inspection tasks, but It is the historical operation data corresponding to the target area where the target inspector is located. The second combination queue of image analysis operations may also be periodically formed and stored in the database, so that after the target analysis object is determined, the second image analysis operation combination queue corresponding to the target analysis object is directly read from the database.

After the second image analysis operation combination is formed, the first image analysis operation combination in the second image analysis operation combination queue may be selected as the second image analysis operation combination in the recommended image analysis operation combination queue.

In the inspector's inspection task execution history, each inspector usually has a combination of conventional image analysis operations for different analysis objects. It is possible to regularly analyze the combination of conventional image analysis operations with correct inspection conclusions of each inspector for each analysis object, and generate a third image analysis operation combination for each inspector for each analysis object according to the frequency of use of each image analysis operation combination queue, so that after the target inspector and the target inspection object are determined, the database is directly read to obtain the third image analysis operation combination queue. After the third image analysis operation combination is formed, the first image analysis operation combination in the third image analysis operation combination queue may be selected as the third image analysis operation combination in the recommended image analysis operation combination queue.

The use of the third image analysis operation combination queue can improve the adaptability of the image analysis process and the target inspector, improve the familiarity of the target inspector with the effect of the image to be analyzed after image processing, thereby improving the inspection conclusion drawn by the target inspector efficiency and accuracy.

In other embodiments of the present disclosure, the acquisition of the second image analysis operation combination queue and the third image analysis operation combination queue can be enabled or disabled through manual or automatic settings. When the second image analysis operation combination queue and/or the third image analysis operation combination queue are disabled, the disabled image analysis operation combination queue is set to be empty.

Finally, the first image analysis operation combination and the operation controls of the first image analysis operation combination, the second image analysis operation combination and the operations of the second image analysis operation combination can be displayed on the page where the image to be analyzed is located controls, the third image analysis operation combination, and operation controls of the third image analysis operation combination. Operation controls include but are not limited to buttons, drop-down boxes, check boxes, etc. For detailed display effects, please refer to subsequent embodiments.

In another embodiment of the present disclosure, a comprehensive recommended image analysis operation combination queue can also be generated based on the above three image analysis operation combination queues, and the comprehensive recommended image analysis operation combination queue is displayed in the recommended image analysis operation combination queue One or more elements in .

Fig. 4 is a sub-flow chart of step S3 in another embodiment of the present disclosure.

Referring to Fig. 4, in one embodiment, step S3 may also include:

Step S371, determining multiple candidate image analysis operation combinations according to the first image analysis operation combination queue, the second image analysis operation combination queue, and the third image analysis operation combination queue;

Step S372, determining one or more serial numbers corresponding to each of the candidate image analysis operation combinations, the one or more serial numbers including the first one of the candidate image analysis operation combination in the first image analysis operation combination queue A sequence number, and/or, a second sequence number in the second image analysis operation combination queue, and/or, a third sequence number in the second image analysis operation combination queue;

Step S373, according to the first weight corresponding to the first image analysis operation combination queue, the second weight corresponding to the second image analysis operation combination queue, the third weight corresponding to the third image analysis operation combination queue, and said one or more sequence numbers of each of said candidate image analysis operation combinations, determining a score for each of said candidate image analysis operation combinations;

Step S374, generating a queue of recommended image analysis operation combinations corresponding to the image to be analyzed according to the scores of each candidate image analysis operation combination in descending order.

First, the image analysis operation combinations involved in the first image analysis operation combination queue, the second image analysis operation combination queue, and the third image analysis operation combination queue can be summarized to obtain all candidate images involving the target inspector and the target analysis object The combination of analysis operations facilitates subsequent comprehensive analysis.

Then, the serial numbers of each candidate image analysis operation combination in each queue are determined, and the candidate image analysis operation combinations with higher serial numbers have a greater impact on the correctness of the analysis results. The second image analysis operation combination queue and the third image analysis operation combination queue may be empty, or a candidate image analysis operation combination only appears in one or two queues, so it is possible to obtain only one sequence number or two sequence numbers.

In addition, because the first image analysis operation combination queue, the second image analysis operation combination queue, and the third image analysis operation combination queue have different influences on the correctness of the final image analysis result, the influence of the first image analysis operation combination queue is greater than that of the second image analysis operation combination queue. The influence of the three image analysis operation combination queues, the influence of the third image analysis operation combination queue is greater than the influence of the second image analysis operation combination queue, therefore, the weight value can be preset for each image analysis operation combination queue, for example Set the weight of the first image analysis operation combination queue to the first weight 0.6, set the weight of the third image analysis operation combination queue to the third weight 0.25, and set the weight of the second image analysis operation combination queue to the second weight 0.15 , to coordinate the practical importance of each combination of image analysis operations. The above numerical values of the first weight, the second weight, and the third weight are only examples, and those skilled in the art can make adjustments according to actual needs.

Finally, according to the serial number of each candidate image analysis operation combination in each queue and the weight of each queue, the score of each candidate image analysis operation combination is calculated. Among them, the initial scores corresponding to different serial numbers are different. For example, in a certain queue, the initial score of the image analysis operation combination with the serial number 1 is 100, the initial score of the image analysis operation combination with the serial number 2 is 80, and the image analysis operation combination with the serial number 3 An initial score of 60 is given to the action portfolio, and so on. The initial scores of different cohorts can be set the same for subsequent calculations.

Assume that the sequence number of a candidate image analysis operation combination in the first image analysis operation combination queue is 1, does not appear in the second image analysis operation combination queue, and the sequence number in the third image analysis operation combination queue is 3, and the first weight , the second weight, and the third weight are as in the above example, then the final score S of the candidate image analysis operation combination is calculated according to the value in the above example: S=100*0.6+0*0.15+60*0.25=75.

After the score is calculated for each candidate image analysis operation combination, a queue of comprehensively recommended image analysis operation combinations corresponding to the image to be analyzed is generated according to the scores from large to small.

The above scoring generation rules can be set by those skilled in the art, and the present disclosure is not limited thereto.

After the recommended image analysis operation combination queue is generated, the image to be analyzed and the recommended image analysis operation combination queue can be displayed together on the terminal screen of the target inspector currently logged in. When the target inspector performs the inspection operation, he can use functional options such as selection box, drop-down list, check operation, note text information, etc. to select the image analysis operation combination in the recommended image analysis operation combination queue. When the operator thinks that the recommended option is incorrect, he can click to perform a change operation to change the image analysis operation combination, for example, adjust the first image analysis operation combination to the first image analysis operation combination queue on the operation control of the first image analysis operation combination Other operation combinations in , or adjust the enabling or disabling and weight values of the first image analysis operation combination queue, the second image analysis operation combination queue, and the third image analysis operation combination queue on the operation control of the recommended image analysis operation combination .

Fig. 5 is a sub-flowchart of step S3 in yet another embodiment of the present disclosure.

Referring to Fig. 5, in one implementation, the process of showing the image to be analyzed in step S3 may include:

Step S38: Perform image processing on the image to be analyzed according to the corresponding multiple image analysis operation combinations in the recommended image analysis operation combination queue to generate an image corresponding to each image analysis operation combination in the recommended image analysis operation combination queue. effect image;

Step S39, displaying the image to be analyzed, the effect image corresponding to each of the image analysis operation combinations, and the image analysis operation combination corresponding to each of the effect images on the inspection terminal.

In the embodiment shown in Figure 5, in order to improve the processing efficiency of the target inspector, the image analysis operation combinations in the recommended image analysis operation combination queue can be directly used to directly perform image processing on the image to be analyzed, and display the processed image on the inspection terminal. Among them, the top-ranked image analysis operation combinations can be displayed by highlighting, bolding, flashing, etc., reducing the operator's operation process and effectively improving work efficiency.

In another embodiment of the present disclosure, according to the type information of the target analysis object, a queue of recommended inspection conclusions corresponding to the image to be analyzed may be displayed on the inspection terminal corresponding to the target inspector. The recommended inspection conclusion queue can be formed according to the type identification of the target analysis object and the historical inspection conclusion corresponding to the target analysis object, wherein, the order of the inspection conclusions in the recommended inspection conclusion queue can be based on the appearance of the historical inspection conclusion corresponding to the target analysis object The frequency is determined. For example, the sequence of recommended inspection conclusions for commodity A may be (inclusions in area a, inclusions in area b, and no inclusions). According to the dimensional statistical information such as the type of import and export of the task, the location of the port, etc., the recommendation conclusions can be sorted to facilitate the operator to quickly select the appropriate option.

In addition to displaying the recommended inspection conclusion, it can also display the inspection mark and remark information corresponding to the recommended inspection conclusion. The inspection mark can be the risk area mark of the target inspection object in the historical operation data of multiple inspectors; the remark information can be Text information or multiple types of annotation information to indicate the risk (missing negative, false positive) information or image processing suggestions of a certain area of the target analysis object in the image to be analyzed. The content of the remark information of each target analysis object can be input by multiple inspectors, and will be summarized and displayed in the subsequent image analysis process.

Finally, the recommended image analysis operation combination queue and the recommended inspection conclusion queue can be simultaneously displayed on the inspection terminal for analysis by the target inspector.

6A to 6C are schematic diagrams showing a combination queue of recommended image analysis operations in an embodiment of the present disclosure.

Referring to FIG. 6A, in one embodiment, an image to be analyzed 61 and a recommended image analysis operation combination queue 62 can be displayed at the same time. The recommended image analysis operation combination queue 62 includes a plurality of image analysis operation combinations 621-62N, and each image analysis operation All combinations can be selected by the target inspector to perform automatic image processing on the image to be analyzed 61, and finally the image processing result 63 is displayed at the position of the image to be analyzed 61, as shown on the right side of FIG. 6A. Among them, the multiple image analysis operation combinations 621-62N may include the operation controls of the first image analysis operation combination, the operation controls of the second image analysis operation combination, the operation controls of the third image analysis operation combination, and may also include comprehensive recommendation analysis An action control for manipulating a composition.

Referring to FIG. 6B, in another embodiment, the image to be analyzed 61, the recommended image analysis operation combination queue 62, and the effect images corresponding to each image analysis operation combination 621-62N in the recommended image analysis operation combination queue 62 can be simultaneously displayed 631-63i, if one screen cannot be displayed, more effect images can be displayed through tools such as slide bar 65. Wherein, N is the number of image analysis operation combinations in the recommended image analysis operation combination queue 62 , and i is the serial number of the image analysis operation combination in the recommended image analysis operation combination queue 62 .

Referring to Fig. 6C, in another embodiment, the image to be analyzed 61, the recommended image analysis operation combination queue 62, the recommended inspection conclusion queue 64, the tag recommendation 65 and the remark information 66 can be displayed at the same time, or the recommended image analysis can also be displayed at the same time Each image analysis operation combination 621-62N in the operation combination queue 62 corresponds to the effect images 631-63i.

It can be seen from FIG. 6A to FIG. 6C that, compared with the traditional solution, which only shows images to be analyzed and optional image analysis operations, the embodiments of the present disclosure provide more intuitive operation recommendations for target inspectors. The operation recommendations are based on All inspection tasks and the historical operation data of the target inspector can be obtained, which can take into account the accuracy and the operating habits of the target inspector, and greatly improve the inspection efficiency and accuracy of the target inspector.

In some other embodiments, before displaying the image 61 to be analyzed, the image 61 to be analyzed may also be preprocessed first, so as to improve the recognition accuracy.

For example, after acquiring the image to be analyzed, it can automatically identify the position of the container and cab in the image, and then obtain the recommended image analysis operation combination queue according to the inspection cargo (target analysis object), target inspection person and other information, and load priority The processing effect corresponding to the highest-level operation combination (the icon is highlighted) and other operation combinations are loaded into the toolbar as a recommendation item for the target inspector to choose. Horizontal flip is superimposed in the combination of image analysis operations (the machine inspection equipment scans back and forth, causing part of the image to be on the right side of the cab and part of the cab to be on the left side of the image) to more accurately display the image to be analyzed.

Fig. 7 is a flow chart of execution of inspection tasks in one embodiment of the present disclosure.

Referring to FIG. 7 , in one embodiment, the execution process of the inspector task may include:

Step S701, the scanning system scans the item to be inspected to generate a scanned image;

Step S702, the scanning system sends the scanned image to the intelligent image review system, requesting intelligent review calculation;

Step S703, the intelligent image review system receives the scanned image and performs intelligent review calculation;

Step S704, the intelligent image review system completes the intelligent image analysis, and sends the analysis conclusion to the machine inspection system;

Step S705, the machine-based inspection system receives the intelligent trial conclusion, obtains the scanned image information from the scanning system, and completes the association and binding of the conclusion and the scanned image;

Step S706, the machine-based inspection system acquires historical statistical data and historical operation data of inspectors;

Step S707, the machine inspection system determines the recommended image analysis operation combination queue and the recommended analysis conclusion queue according to the inspected goods or the machine inspection personnel;

Step S708, the inspector analyzes the image according to the recommended guidance and experience;

Step S709, the machine-based inspection system records the operation process of the operator, and obtains the image analysis operation record corresponding to the inspection task;

Step S710, after the image analysis is completed, automatically perform multi-dimensional historical data statistics and update historical data;

Step S711, the machine inspection system performs data cleaning on the image analysis operation records, and analyzes effective user behaviors;

Step S712, the inspection is completed, and the inspection conclusion is sent to the intelligent drawing review system and the scanning system;

Step S713, the intelligent drawing review system receives the confirmation conclusion of the intelligent review, and performs operation learning optimization;

Step S714, the scanning system receives the inspection conclusion, and performs release or next step of disposal;

Step S715, the process ends.

To sum up, the embodiment of the present disclosure records and analyzes the operation process of the inspector during the inspection process, and uses the image analysis function, multi-dimensional inspection historical statistical data, and inspection tasks based on the inspection conclusions of the inspectors. Analyzing personnel’s historical operation behavior, analyzing and clustering data such as inspection goods, accuracy of inspection conclusions, and accuracy of inspection marks, etc., to obtain recommended image analysis operation combinations corresponding to the current inspection goods and current inspectors, and high-frequency image analysis operations for inspectors Combination, personalized image analysis operation combination of inspectors, providing the best combination of image analysis functions for inspection tasks, recommending the operations of inspectors, and sorting the options reasonably for the inspectors to choose and operate, based on massive historical inspection records , providing best practices for inspection operations and improving the availability of the inspection system.

Corresponding to the above-mentioned method embodiments, the present disclosure further provides a machine inspection task display device, which can be used to execute the above-mentioned method embodiments.

Fig. 8 is a block diagram of a machine inspection task display device in an exemplary embodiment of the present disclosure.

Referring to FIG. 8 , the machine inspection task display device 800 may include:

The target analysis object determination module 81 is configured to acquire the image to be analyzed, and determine the type information of the target analysis object in the image to be analyzed;

The target inspector determination module 82 is configured to determine the target inspector corresponding to the image to be analyzed;

The recommended operation display module 83 is configured to display the image to be analyzed and the image to be analyzed on the inspection terminal corresponding to the target inspector according to the type information of the target analysis object and the historical operation data of the target analysis object. The corresponding recommended image analysis operation composition queue.

Since each function of the apparatus 800 has been described in detail in its corresponding method embodiment, the present disclosure will not repeat them here.

It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. Actually, according to the embodiment of the present disclosure, the features and functions of two or more modules or units described above may be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided to be embodied by a plurality of modules or units.

In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

Those skilled in the art can understand that various aspects of the present invention can be implemented as systems, methods or program products. Therefore, various aspects of the present invention can be embodied in the following forms, that is: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which can be collectively referred to herein as "circuit", "module" or "system".

An electronic device 900 according to this embodiment of the present invention is described below with reference to FIG. 9 . The electronic device 900 shown in FIG. 9 is only an example, and should not limit the functions and scope of use of this embodiment of the present invention.

As shown in FIG. 9, electronic device 900 takes the form of a general-purpose computing device. Components of the electronic device 900 may include but not limited to: at least one processing unit 910 , at least one storage unit 920 , and a bus 930 connecting different system components (including the storage unit 920 and the processing unit 910 ).

Wherein, the storage unit stores program codes, and the program codes can be executed by the processing unit 910, so that the processing unit 910 executes various exemplary methods according to the present invention described in the "Exemplary Methods" section of this specification. Implementation steps. For example, the processing unit 910 may execute the method shown in the embodiment of the present disclosure.

The storage unit 920 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 9201 and/or a cache storage unit 9202 , and may further include a read-only storage unit (ROM) 9203 .

The storage unit 920 may also include a program/utility 9204 having a set (at least one) of program modules 9205, such program modules 9205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, Implementations of networked environments may be included in each or some combination of these examples.

Bus 930 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local area using any of a variety of bus structures. bus.

The electronic device 900 can also communicate with one or more external devices 1000 (such as keyboards, pointing devices, Bluetooth devices, etc.), and can also communicate with one or more devices that enable the user to interact with the electronic device 900, and/or communicate with Any device (eg, router, modem, etc.) that enables the electronic device 900 to communicate with one or more other computing devices. Such communication may occur through input/output (I/O) interface 950 . Moreover, the electronic device 900 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN) and/or a public network such as the Internet) through the network adapter 960 . As shown, the network adapter 960 communicates with other modules of the electronic device 900 through the bus 930 . It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives And data backup storage system, etc.

Through the description of the above implementations, those skilled in the art can easily understand that the example implementations described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of software products, and the software products can be stored in a non-volatile storage medium (which can be CD-ROM, U disk, mobile hard disk, etc.) or on the network , including several instructions to make a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) execute the method according to the embodiments of the present disclosure.

In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium on which a program product capable of implementing the above-mentioned method in this specification is stored. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes program code, and when the program product is run on a terminal device, the program code is used to make the The terminal device executes the steps according to various exemplary embodiments of the present invention described in the "Exemplary Method" section above in this specification.

The program product for implementing the above method according to the embodiment of the present invention may adopt a portable compact disk read-only memory (CD-ROM) and include program codes, and may run on a terminal device such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program, and the program may be used by or in combination with an instruction execution system, apparatus or device.

The program product may reside on any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: electrical connection with one or more conductors, portable disk, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

A computer readable signal medium may include a data signal carrying readable program code in baseband or as part of a carrier wave. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages—such as Java, C++, etc., as well as conventional procedural programming languages. Programming language - such as "C" or a similar programming language. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server to execute. In cases involving a remote computing device, 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., using an Internet service provider). business to connect via the Internet).

In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above figures do not imply or limit the chronological order of these processes. In addition, it is also easy to understand that these processes may be executed synchronously or asynchronously in multiple modules, for example.

Other embodiments of the present disclosure will be readily apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any modification, use or adaptation of the present disclosure, and these modifications, uses or adaptations follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field not disclosed in the present disclosure . The specification and examples are to be considered exemplary only, with the true scope and concept of the disclosure indicated by the appended claims.

Claims (13)

1. A machine inspection inspection task display method, characterized in that, comprising: Acquiring the image to be analyzed, and determining the type information of the target analysis object in the image to be analyzed; determining the target inspector corresponding to the image to be analyzed; According to the type information of the target analysis object and the historical operation data of the target analysis object, the image to be analyzed and the recommended image analysis operation combination queue corresponding to the image to be analyzed are displayed on the inspection terminal corresponding to the target inspector . 2. The machine inspection task display method according to claim 1, wherein the recommended image analysis operation combination queue includes a first image analysis operation combination, and the type information of the target analysis object and the The historical operation data of the target analysis object, displaying the image to be analyzed on the inspection terminal corresponding to the target inspector, and the recommended image analysis operation combination queue corresponding to the image to be analyzed include: According to the type information of the target analysis object and the historical operation data of the target analysis object, obtain the first image analysis operation combination queue of the target analysis object by the historical examiner on the target analysis object, the first image analysis The operation combination queue includes a plurality of image analysis operation combinations arranged in a first order, and the first image analysis operation combination in the first image analysis operation combination queue is determined to be the first image analysis operation combination; The first image analysis operation combination and the operation controls of the first image analysis operation combination are displayed in the recommended image analysis operation combination queue. 3. The machine inspection task display method according to claim 1 or 2, wherein the recommended image analysis operation combination queue includes a second image analysis operation combination, and the type information of the target analysis object and The historical operation data of the target analysis object, displaying the image to be analyzed on the inspection terminal corresponding to the target inspector, and the recommended image analysis operation combination queue corresponding to the image to be analyzed include: According to the historical operation data of the target inspector and the type information of the target analysis object, determine the target region where the target inspector is located and the second image analysis operation combination queue for the target analysis object, the second image The analysis operation combination queue includes a plurality of image analysis operation combinations arranged in a second order, and the first image analysis operation combination in the second image analysis operation combination queue is determined to be the second image analysis operation combination; The second image analysis operation combination and the operation controls of the second image analysis operation combination are displayed in the recommended image analysis operation combination queue. 4. The machine inspection task display method according to claim 1 or 2, wherein the recommended image analysis operation combination queue includes a third image analysis operation combination, and the type information of the target analysis object and The historical operation data of the target analysis object, displaying the image to be analyzed on the inspection terminal corresponding to the target inspector, and the recommended image analysis operation combination queue corresponding to the image to be analyzed include: According to the historical operation data of the target inspector and the type information of the target analysis object, determine a third image analysis operation combination queue arranged according to the operating frequency of the target inspector on the target analysis object, the third The image analysis operation combination queue includes a plurality of image analysis operation combinations arranged in a third order, and the first image analysis operation combination in the third image analysis operation combination queue is determined to be the third image analysis operation combination; The third image analysis operation combination and the operation controls of the third image analysis operation combination in the recommended image analysis operation combination queue. 5. The computer-based inspection task presentation method according to claim 2, wherein the forming process of the first image analysis operation combination queue comprises: Regularly obtain machine-check inspection tasks with correct machine-check inspection conclusions within the preset time range: Determine the image analysis operation combination and the target analysis object corresponding to each machine inspection inspection task whose conclusion is correct; determining a combination set of image analysis operations corresponding to each target analysis object; The first image analysis operation combination queue of the target analysis object corresponding to the image analysis operation combination is formed according to the occurrence number of the same image analysis operation combination in each image analysis operation combination set in descending order. 6. The method for displaying machine inspection tasks according to claim 1, further comprising: Determine multiple candidate image analysis operation combinations according to the first image analysis operation combination queue, the second image analysis operation combination queue, and the third image analysis operation combination queue; determining one or more sequence numbers corresponding to each of the candidate image analysis operation combinations, the one or more sequence numbers including the first sequence number of the candidate image analysis operation combination in the first image analysis operation combination queue, and /or, a second sequence number in the second image analysis operation combination queue, and/or, a third sequence number in the second image analysis operation combination queue; According to the first weight corresponding to the first image analysis operation combination queue, the second weight corresponding to the second image analysis operation combination queue, the third weight corresponding to the third image analysis operation combination queue, and each of the the one or more sequence numbers of the candidate image analysis operation combinations, and determine the score of each of the candidate image analysis operation combinations; A sequence of comprehensively recommended image analysis operation combinations corresponding to the image to be analyzed is generated in descending order of scores of each candidate image analysis operation combination. 7. The computer-based inspection task display method according to claim 1, wherein said determining the type information of the target analysis object in the image to be analyzed comprises: Determining the target analysis object with the largest area ratio in the image to be analyzed; The type of the target analysis object is identified to form type information of the target analysis object. 8. The computer-based inspection task display method according to claim 1, wherein said determining the type information of the target analysis object in the image to be analyzed comprises: determining the declaration information corresponding to the image to be analyzed, where the declaration information includes types and value information of a plurality of analysis objects; According to the value information of the plurality of analysis objects, it is determined that the analysis object with the highest value is the target analysis object. 9. The machine-based inspection task display method according to claim 1, wherein the image to be analyzed and the recommended image analysis operation corresponding to the image to be analyzed are displayed on the inspection terminal corresponding to the target inspector Combined queues include: Perform image processing on the image to be analyzed according to a plurality of corresponding image analysis operation combinations in the recommended image analysis operation combination queue, so as to generate an effect image corresponding to each image analysis operation combination in the recommended image analysis operation combination queue ; The image to be analyzed, the effect image corresponding to each image analysis operation combination, and the image analysis operation combination corresponding to each effect image are displayed together on the inspection terminal. 10. The machine inspection task display method according to claim 1, further comprising: According to the type information of the target analysis object, a queue of recommended inspection conclusions corresponding to the image to be analyzed is displayed on the inspection terminal corresponding to the target inspector. 11. A machine inspection task display device, characterized in that it comprises: The target analysis object determination module is configured to acquire the image to be analyzed, and determine the type information of the target analysis object in the image to be analyzed; A target inspector determination module, configured to determine the target inspector corresponding to the image to be analyzed; The recommended operation display module is configured to display the image to be analyzed and the image corresponding to the image to be analyzed on the inspection terminal corresponding to the target inspector according to the type information of the target analysis object and the historical operation data of the target analysis object. A combined queue of recommended image analysis operations. 12. An electronic device, characterized in that it comprises: storage; and A processor coupled to the memory, the processor configured to execute the machine inspection task presentation method according to any one of claims 1-10 based on instructions stored in the memory. 13. A computer-readable storage medium, on which a program is stored, and when the program is executed by a processor, the machine inspection task presentation method according to any one of claims 1-10 is implemented.

Images