CN112558554A - Task tracking method and system - Google Patents

Disclosed are a task tracking method, system and platform, the method comprising: acquiring a target image of a task; judging the execution state of the task according to the target image; acquiring the progress status of the task; and determining a current status of the task based on the execution status and the progress status. Therefore, the quality of the task is tracked through image comparison, and the current state of the task can be accurately grasped by combining the acquisition of the progress state. The solution is particularly suitable for implementation as a documentary system for digital printing production tasks.

Task tracking method and system

Technical Field

The invention relates to the field of automation, in particular to a task tracking method and a task tracking system.

Background

The order tracking means tracking the operation flow of the production task based on the customer order in the enterprise operation process. The receipt is also called as a processing route receipt, and refers to a production certificate which follows the movement of a workpiece and records the receiving and sending movement conditions among all working procedures in the processing process. The production planning and scheduling personnel give workers in the first procedure, and then follow each procedure to sequentially transfer and record one by one until the last procedure is finished. The existing order following mode mainly comprises manual data entry, order production association and data entry are required to be carried out by specific workers, and the production process on a production line is separated from the order progress, so that the order production progress cannot be fed back in real time, and the production cost of a factory is greatly improved. In other areas such as logistics, the lack of timely tracking and feedback of task status greatly affects the system's delivery and monitoring of tasks, and thus overall efficiency.

Accordingly, there is a need for an improved task tracking scheme.

Disclosure of Invention

In order to solve at least one problem, the invention provides a task tracking scheme, which tracks tasks through computer vision comparison and combines the acquisition of production progress conditions, so that the current conditions of the production tasks can be accurately grasped. This solution is particularly suitable for implementing a tracking system for production tasks, for example for digital printing tasks.

According to an aspect of the present invention, a task tracking method is provided, including: acquiring a target image of a task; judging the execution state of the task according to the target image; acquiring the progress status of the task; and determining a current status of the task based on the execution status and the progress status. Therefore, the execution state of the production task is acquired based on the image through task image acquisition, and the current production state can be accurately grasped in combination with the acquisition of the production progress state.

Preferably, the task is a production task, and the target image of the production task on the production line may be acquired by an image acquisition device installed on the production line. Preferably, a production progress sensor arranged on or near the production line, for example, a reading of a length or number counter, may be acquired as the production progress status of the production task.

Preferably, the determination of the execution status may include determining whether the target image conforms to a prescribed image of the production task. For example, feature extraction may be performed on the target image; comparing features extracted from the target image with features extracted from a prescribed image of the production task; and judging whether the target image meets the specified image of the task or not according to the comparison result. The image feature extraction may be, for example, feature point extraction based on a conventional CV (computer vision); or neural network feature extraction based on deep learning.

Specifically, a target area image for the determination may be extracted from the acquired target image. For example, continuous target images of a current production task on a production line can be acquired, and motion area detection is performed according to the established background model; so as to extract the target area image based on the motion area detected from the continuous target image.

The comparison may be a direct comparison against a determined image, or a search comparison against an existing database. To this end, determining whether the target image conforms to a prescribed image of the production task may include: and searching a specified image which is consistent with the target image from a task specified image database.

Further, the tracking method of the present invention may be used to implement automatic order following, and then the method may further include: based on the conformed specification images, order information of the task is searched, and the current completion degree of the task can be determined based on the order information and the progress condition.

Further, the tracking method of the present invention may be used for task status aggregation and reporting, and then the method may further include: reporting the current status of the task. Reporting the current status of the task may include at least one of: actively pushing the current state of the task to a client; providing the current state of the task when the client side inquires; and displaying the current state of the task in real time. In the invention, the method can be simultaneously executed for a plurality of tasks so as to simultaneously track the current conditions of the plurality of tasks.

Further, the plurality of tasks may be tasks belonging to different task executors, and the method further includes: calculating executive task condition information of the different task executors based on the current conditions of the plurality of tasks; and the task issuing party selects a task executing party to execute the new task based on the task condition information of the executing parties of the different task executing parties.

The plurality of tasks may also be tasks belonging to different task performers belonging to the same product supply chain, and the method further comprises: calculating executive task condition information of the different task executors based on the current conditions of the plurality of tasks; determining current supply chain condition information for the supply chain based on the executive task condition information of the different task executors; and determining a new task to perform based on the current supply chain condition information.

Further, the tracking method of the present invention may be used for automated production of combined documentaries, and then the method may further comprise: and starting the next production task under the condition that the current condition is at least that the production task is completed.

In the invention, the production task can be especially a cloth printing task, and a target image after the printing process on a production line is finished can be obtained, so that the execution condition of the production task is judged according to the printing image on the cloth.

In the present invention, the task may also be a logistics task, and determining the execution status of the task according to the target image includes: judging the task object and/or the task object condition of the logistics task according to the target image, wherein the step of acquiring the progress condition of the task comprises the following steps: and acquiring the progress status of the task according to the position of the logistics task.

According to yet another aspect of the present invention, there is provided a task tracking system, comprising: the image acquisition equipment is used for acquiring a target image of the task; the computing equipment is used for judging the execution condition of the task according to the target image; a sensor, such as a length or number counter, to collect a production progress status of the task, wherein the computing device determines a current status of the task based on the execution status and the progress status.

Preferably, the computing device may be configured to: and judging whether the target image conforms to the specified image of the task.

Preferably, the computing device may be further configured to: and extracting a target area image for the judgment from the acquired target image.

Preferably, the image acquisition device may be configured to: acquiring successive target images of the task (e.g., a current production task on a production line), and the computing device may be further operable to: detecting a motion area according to the established background model; extracting the target area image from the motion areas detected from the continuous target images.

Preferably, the computing device may be further configured to: extracting the features of the target image; comparing features extracted from the target image with features extracted from a prescribed image of the task; and judging whether the target image meets the specified image of the task or not according to the comparison result.

Preferably, the system may further comprise: a database to store production task specification images, wherein the computing device is further to: and searching a specified image which is consistent with the target image from the database. Preferably, the computing device is further configured to: searching order information of the task based on the matched specified image; and determining the current completion degree of the task based on the order information and the progress condition.

Preferably, the system may further comprise: and the client is used for acquiring and reporting the current state of the production task. The client may receive the current status of the actively pushed task, or obtain the current status of the task when queried by the user.

Preferably, the system can track the current status of multiple tasks simultaneously. The computing device may be further to: and calculating system task condition information based on the current conditions of the plurality of tasks, and reporting the system task condition information. The system may also be one that belongs to a particular supply chain, the computing device receiving current supply chain condition information and determining a new task to perform based on the current supply chain condition information.

Preferably, the computing device is further configured to: determining a next task to be started if the current condition is at least the task completed.

The tracking system of the present invention may be a production task tracking system, said system further comprising: a production line for performing production tasks thereon. The production task tracking system is particularly suitable for being implemented as a system for cloth printing production tracking system, whereupon the image acquisition device may be mounted for: and acquiring a target image after the printing process on the production line is finished. The computing device can judge the execution status of the production task according to the printing image on the cloth.

The tracking system of the present invention may also be a logistics task tracking system, and the computing device is configured to: and judging the task object and/or the task object condition of the logistics task according to the target image acquired by the image acquisition equipment, and determining the progress condition of the logistics task according to the position of the logistics task acquired by the sensor.

According to one aspect of the invention, a task tracking platform is provided, comprising a server and a plurality of task tracking systems as described above connected to the server via the internet.

In the case where edge calculations are performed by the local computing device, the server may only be used to issue image feature extraction models to the computing devices of the task tracking system. In the case of cloud computing, the server needs to: acquiring a target image uploaded by the task tracking system; judging the execution state of the task according to the target image; and issuing the execution status to the computing equipment of the task tracking system.

Preferably, the platform may further comprise: a client for: receiving the current state of the task actively pushed by the server; and/or obtaining the current state of the task from the server when queried by a user.

Preferably, the plurality of task tracking systems connected to the server may include a plurality of task performers performing tasks of the same kind, and the server is configured to: executing side task condition information of the plurality of task executing sides calculated based on the current conditions of the plurality of tasks; and providing the executive task condition information to a task assigning party so that the task assigning party selects a task executing party to execute a new task based on executive task condition information of the plurality of task executing parties.

Preferably, the plurality of task tracking systems connected to the server may include a plurality of task performers performing the same product supply chain, and the server is configured to: acquiring executive task condition information of the plurality of task executors calculated based on the current conditions of the plurality of tasks; determining current supply chain condition information for the supply chain based on executive task condition information for the plurality of task executors; determining a new task to perform based on the current supply chain condition information; and issuing the determined new task to a corresponding task executive party.

According to yet another aspect of the invention, there is provided a computing device comprising: a processor; and a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform the production task tracking method as described above.

According to yet another aspect of the present invention, a non-transitory machine-readable storage medium is presented having executable code stored thereon, which when executed by a processor of an electronic device, causes the processor to perform the production task tracking method as described above.

According to the invention, a camera is installed to collect image information in a task execution process for algorithm intelligent analysis, adaptive area detection is carried out on an effective image area, image characteristics of an effective target area are extracted, the effective target area is compared and sorted in a characteristic library according to the characteristic vector, a corresponding image is searched in a base library and is further associated with order information, production of a current task is carried out by combining a sensing counter, and various functions based on task tracking, such as an automatic order following function, are finally realized.

Drawings

The above and other objects, features and advantages of the present disclosure will become more apparent by describing in greater detail exemplary embodiments thereof with reference to the attached drawings, in which like reference numerals generally represent like parts throughout.

FIG. 1 shows a schematic flow diagram of a production task tracking method according to one embodiment of the invention.

Fig. 2 shows an embodiment of the flow of the digital printing automatic order following according to the invention.

FIG. 3 illustrates a schematic diagram of the components of a production task tracking system according to one embodiment of the present invention.

FIG. 4 is a schematic diagram of a computing device that can be used to implement the production task tracking method according to an embodiment of the present invention.

Fig. 5 shows an example of a technical implementation flow of the digital printing automatic order following according to the invention.

Fig. 6 shows a diagram of the presentation effect of the single example shown in fig. 5.

Detailed Description

Preferred embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While the preferred embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

The order tracking means tracking the operation flow of the production task based on the customer order in the enterprise operation process. The following list is also called as a processing route list. A production certificate for recording the receiving and transmitting movement condition of each working procedure in the processing process along with the movement of a workpiece. The production planning and scheduling personnel give workers in the first procedure, and then follow each procedure to sequentially transfer and record one by one until the last procedure is finished. The existing order following mode mainly comprises manual data entry, order production association and data entry are required to be carried out by specific workers, and the production process on a production line is separated from the order progress, so that the order production progress cannot be fed back in real time, and the production cost of a factory is greatly improved.

Taking digital printing as an example, the management efficiency of current digital printing processing factory is low, the production and marketing are disjointed, most in the industry are to the order following of digital printing, what adopt is that the production is that the order following personnel carries out special manual data entry operation on the day, production and order progress control are disjointed, consequently need to have one set of complete digital solution help mill to carry out production management, help the user to obtain printing process data in real time simultaneously, know order production progress, finally realize efficient production and marketing in coordination, promote the purpose that mill's management efficiency and reduce cost improve the productivity.

In other areas such as logistics, the lack of timely tracking and feedback of task status greatly affects the system's delivery and monitoring of tasks, and thus overall efficiency.

Therefore, the invention provides a task tracking scheme, which has little modification to the existing facilities of factories or logistics warehouses and the like, does not need to change the working mode of workers, only needs to install a camera in the area near a machine which is the main link of the task, and can complete the automatic tracking of the task in a non-invasive mode by carrying out algorithm analysis on image/video data under the condition that the workers do not feel, such as an associated order following function.

Fig. 1 shows a schematic flow diagram of a task tracking method according to an embodiment of the invention. The method is suitable for a control center of a factory or a logistics service provider and the like, and can acquire cloud service of the current task state or be realized by combining local and cloud.

In step S110, a target image of the task is acquired. Herein, a "task" refers to a job, such as being dispatched via a customer. For example, a production line of a factory may perform production tasks according to customer orders, a logistics office may perform logistics transportation tasks according to customer orders, and the like. The target image of the acquisition task may be a target image of an object of the acquisition task, for example, an image of an object being produced on a production line or an image of an object being shipped by logistics.

Here, a "production line" may be referred to as a production line or an assembly line, and is an industrial production method, which means that each production unit is dedicated to only processing a certain piece of work. The production line can be used for producing or assembling parts, or aiming at different steps of a processing object, or assembling the parts or various combinations of processing steps. "production task" refers to an object processed on a production line. In some embodiments, a "production job" is the object itself, and in other embodiments, a "production job" is the task of processing a plurality of objects in a batch, or the plurality of objects themselves. The target image of the production task is the image of the object being processed on the production line.

For example, in digital printing plants, digital printing of the raw piece of cloth produced is required. Digital printing is printing by digital technology, which inputs various digital patterns into a computer through various digital means such as scanning, digital photos, images or computer manufacturing processing, then the digital patterns are processed by a computer color separation printing system, various special dyes (active, dispersed and acidic main paints) are directly sprayed and printed on various fabrics or other media through a special RIP (Raster Image Processor) software through a spraying and printing system, and various high-precision printing products required are obtained on various textile fabrics after processing. The digital printing process is mainly divided into five links: printing, steaming, washing, shaping, weft straightening, sizing and drying.

For this reason, in an application scenario of digital printing, a production line may refer to an industrial production line for performing the above five links of digital printing to complete accurate printing on an original cloth. The production task may then refer to a certain task in the order, for example, 1000 meters of the piece of cloth producing the star pattern, or the piece of cloth producing the star pattern itself. The target image of the production job may then be a printed pattern of the piece of cloth being processed on the production line.

In the following description of the present invention, it will be mainly described in conjunction with digital printing as an example. It will be appreciated by those skilled in the art that the present invention is also applicable to other product lines where the determination of production conditions is based on profile comparison. In other embodiments, the invention is also applicable to tasks other than production tasks, for example, logistics transportation tasks, as long as the performance of these tasks can be analyzed using the captured images.

In step S110, an image capturing device installed on a production line may be used to capture a target image of a production task on the production line. Here, the "on-line" may refer to an arrangement that is installed in any direction of up, down, left, and right of the production line, and around, near, etc. the production line, depending on actual needs. For example, in a digital printing scenario, a target image after completion of a printing process on a production line can be acquired by an image capture device installed between the printing and cooking processes, for example, a camera installed directly above the production line and vertically downward. In other embodiments, the image capturing device may be installed after all or part of other production processes to capture and analyze images, and the invention is not limited thereto.

In a logistics task, the acquisition of the target image may be performed using an image acquisition device installed at a logistics warehouse fixed location (e.g., an entrance or exit location) or a transportation fixed location (e.g., the cabin of a cargo plane).

In various embodiments, the "image capture device" may be a camera or a video camera to meet the requirements for image or video capture in subsequent steps. In some scenarios, the identities of the camera and camcorder may be interchanged, e.g., pictures taken at sufficiently short intervals for use as a video stream may be taken quickly enough, or videos may be captured at sufficiently large intervals for processing as images. In one embodiment, the target image is preferably acquired in real time or near real time for subsequent timely processing, thereby facilitating immediate control of the production process.

Subsequently, in step S120, the execution status of the task is determined according to the target image. Here, the determining of the execution status of the task may be determining a specific task based on the image, for example, determining the order to which the current cloth production task belongs from the design and color of the printing, or determining whether the task is being executed normally based on the graph, for example, determining whether the shape of the parcel box in the logistics task is complete, determining whether the design and color of the printing are wrong, and the like.

Specifically, a comparison of the target image with the existing image may be performed, and thus it may be determined whether the task is normally executed. Specifically, it may be determined whether the target image conforms to a prescribed image of the job (e.g., an image in a print library). For example, the target image may be determined based on comparison of image features by using an image feature extraction technique. Here, the "image feature extraction technology" may be part of "computer vision", which refers to machine vision, such as recognizing, tracking, and measuring a target by using an image acquisition device (e.g., a camera) and a computer instead of human eyes, and further performing image processing, and processing the image into an image more suitable for human eyes or for transmission to an instrument for detection by using the computer. Computer vision attempts to create artificial intelligence systems that can extract "information" from images or multidimensional data. The information referred to herein is that defined by shannon and can be used to help make a "decision". Thus, in the present invention, the "image feature extraction technique" may refer to an operation of extracting a meaningful feature (a feature representing the above-described "information") from an acquired image using a computer. In the present invention, the image feature extraction technique utilized may be feature point extraction based on conventional CV (computer vision); deep learning based neural network (e.g., CNN, convolutional neural network) feature extraction is also possible.

Although it is possible to acquire an image of an object closer to a prescribed image acquisition angle by the precision and mounting of the camera, various differences are introduced in actual operation. For example, the actual pattern image acquired by the camera in the digital printing production process still has a certain difference with the image corresponding to the stencil pattern issued by the order base, such as size, rotation, light and shade of illumination, color depth, pattern repetition degree, image noise of other contents, angle change, etc., which is a technical difficulty that needs to be overcome in the aspect of related matching. Therefore, further processing of the acquired images is often required for subsequent alignment.

Accordingly, in one embodiment, the tracking method of the present invention further includes extracting a target area image for the determination from the acquired target image. Specifically, a continuous target image, such as a video, of a current production task on a production line may be acquired, and then motion region detection may be performed according to the established background model; and extracts the target area image based on the motion area detected from the continuous target image.

In one embodiment, the comparison of the target image to the existing image may be a comparison to the extracted features. To this end, step S120 may include: extracting the features of the target image; comparing features extracted from the target image with features extracted from a prescribed image of the production task; and judging whether the target image meets the specified image of the task or not according to the comparison result.

The comparison may be a direct comparison against a determined image, or a search comparison against an existing database. To this end, step S120 may include: and searching a specified image which is consistent with the target image from a task specified image database. For example, the extracted target image features are compared with existing features in a prescribed image database to find a prescribed image in which the features match.

Subsequently, based on the conformed specification images, the order information of the task may be searched, and thus the current completion degree of the task may be determined based on the order information and the progress status acquired in the subsequent step S130.

In step S130, a progress status of the task is acquired, e.g. readings of a production progress sensor arranged on or near the production line are acquired. The production progress sensor may be a length or number counter. For example, the finished length of the printed piece of cloth can be determined by a meter counter mounted on the axis of rotation of the production line. For example, the current position of the transportation object in the logistics task may be acquired, thereby estimating the transportation completion.

Subsequently, in step S140, the current status of the task is determined based on the execution status and the progress status.

Thus, the present invention is able to determine the current completion of a task through the acquisition of performance and progress conditions (e.g., real-time acquisition and analysis of images and sensor data). The current status of the task can be fed into the control center of the local or cloud end, so as to perform the subsequent operation.

In one embodiment, the method may further comprise: and reporting the current status of the production task. For example, the determined current condition may be displayed in real time on a display of the plant control center, even on the customer's client. For example, the current status of the task may be actively pushed to the client; the current status of the task may also be provided when the client makes a query.

In the invention, the method can be simultaneously executed for a plurality of tasks so as to simultaneously track the current conditions of the plurality of tasks. For example, in the case of multiple production lines, the method of the present invention can track the production status of the current production task of each production line, and summarize and report the status.

Under the condition of cloud implementation, tracking of the current production condition of each production line of each factory can be achieved in the server, and the current production condition is fed back to the corresponding client.

In one embodiment, the plurality of tasks tracked are tasks belonging to different task executors, and the method further comprises: calculating executive task condition information of the different task executors based on the current conditions of the plurality of tasks; and the task issuing party selects a task executing party to execute the new task based on the task condition information of the executing parties of the different task executing parties.

Here, the different task performers may be performers of the same type of task, such as cloth suppliers A, B and C. Each cloth supplier A, B and C has multiple production lines for printed cloth production. Thus, the print time, efficiency, busyness (e.g., inventory count) of each piece goods provider may be aggregated and provided to a job-issuing party (e.g., an orderer), for example, who may view the status of the producer on a client, either in real time or updated at a fixed time (e.g., updated daily), to select one of the piece goods providers A, B and C to sign in an order, e.g., an electronic order, based on the status.

In one embodiment, the plurality of tasks tracked are tasks belonging to different task performers belonging to the same product supply chain, and the method further comprises: calculating executive task condition information of the different task executors based on the current conditions of the plurality of tasks; determining current supply chain condition information for the supply chain based on the executive task condition information of the different task executors; and determining a new task to perform based on the current supply chain condition information. For example, the supply of tires a and engines B throughout the supply chain restricts the production of the entire vehicle. For this purpose, the current production situation of the individual task performers on the entire supply chain can be summarized and the subsequent production tasks of the individual production lines of the individual task performers can be determined therefrom.

In one embodiment, the tracking scheme of the present invention may also be incorporated into a factory automation system, whereby the method may further comprise: in the case of the current situation at least the task having been completed, the next task to be started is confirmed, whereby this next task can be started automatically or with manual confirmation. For example, when order scheduling is performed, tasks to be executed can be scheduled reasonably according to the current overall order and execution condition.

The production task tracking method according to the present invention and its preferred embodiment are described above in connection with fig. 1. In the case of digital printing production, the digital printing cloth printing area can be detected in a self-adaptive manner by performing algorithm intelligent analysis on video image information acquired by mounting cameras in each link in the printing process, an effective pattern printing area is extracted, then, the pattern printing area image is subjected to feature extraction, and comparison and sequencing are performed according to the extracted feature vector and the feature vector in the pattern base, so that base samples corresponding to the currently produced pattern are determined to be further related to order information of a database, the number of production meters of the current pattern is obtained according to the data of a current machine meter counter, and finally, the function of automatic order following is realized.

Fig. 2 shows an embodiment of the flow of the digital printing automatic order following according to the invention. As shown in the figure, a video image of a main link, for example, a video image after a printing link, is first acquired in step S210. Subsequently, in step S220, the input real-time video image is subjected to a filtering denoising process, for example, a gaussian denoising process may be adopted.

Then, in step S230, background modeling is performed on the working environment of the worker in the camera, for example, gaussian mixture background modeling may be adopted, and since the printing cloth is tiled and moved in 5 main links of printing to perform the processing operation, the motion region detection may be performed according to any established background model, and then the printing ROI (region of interest) region is segmented according to the motion region detected in the video. Herein, the print ROI area may refer to an image content corresponding to a cloth area on which a print is effectively printed in a video picture acquired by a camera in a print production process.

In step S240, an image feature extraction algorithm is used to perform image retrieval and comparison. Image Retrieval mainly refers to Content-based Image Retrieval (CBIR) technology, that is, Image Retrieval technology for analyzing and retrieving the Content semantics of an Image, such as color, texture, layout, and the like of the Image. In a different implementation, the printing ROI region may be subjected to feature extraction by using a computer vision algorithm, such as feature point extraction of a traditional CV, convolutional neural network feature extraction of deep learning, and the like, for example, the feature extraction may be performed by using resnet50 in the deep learning algorithm in this example, and the feature extraction is compared with the feature vector of the image data set of the order pattern base. Here, the order pattern base may refer to a pattern template image set issued to a printing side by the order management system. The above comparison can obtain a similar characteristic pattern such as Top10, and if the similarity of the characteristic of the bottom-library pattern corresponding to Top1 is greater than a certain threshold (for example, 0.8 is assumed in this example), it is determined that the pattern is correctly corresponding.

Then, in step S250, the length of the processed meter number of the current pattern is obtained by reading the data of the current meter counter and subtracting the value of the meter counter after the previous pattern is finished, and the result is reported by combining the order information of the pattern of the corresponding bottom library in the database. Finally, in step S260, the automatic order following system receives the reported information, and performs result summarizing analysis and display.

In one embodiment, the tracking scheme of the present invention may also track logistics tasks. To this end, step S120 may include determining a task object and/or a task object status of the logistics task according to the target image. Step S130 may include acquiring a progress status of the logistics task according to the location of the task. For example, the current shipping status of a previously produced printed cloth order may be further determined from the printed image of the shipped goods. For example, a cloth with a color of a is now in order a that was shipped in warehouse a by inspection. Meanwhile, the transportation progress of the logistics task can be obtained according to the position of the logistics warehouse A or real-time GPS data in a subsequent transportation tool. Thereby determining the current state of the logistics task at step S140.

The tracking scheme of the present invention may also be implemented as a task tracking system. A task tracking system according to the present invention may include: the image acquisition equipment is used for acquiring a target image of the task; the computing equipment is used for judging the execution condition of the task according to the target image; a sensor to collect a progress status of the task, wherein the computing device determines a current status of the task based on the execution status and the progress status. The system of the present invention will be described below in connection with an example of a production task tracking system that further includes a production line.

Thus, the present invention is able to determine the current completion of a production task through the acquisition of performance status and production progress status (e.g., real-time acquisition and analysis of images and sensor data). The current status of the production task can be fed into the local or cloud control center to perform the subsequent operations,

In one embodiment, the system is one that belongs to a particular supply chain. The cloud platform may aggregate information from the entire supply chain to calculate current supply chain condition information and determine the system to perform subsequent tasks. The computing devices of the respective systems may receive current supply chain condition information and determine a new task to perform based on the current supply chain condition information.

In other embodiments, the task tracking system of the present invention may also be a logistics task tracking system. The logistics task tracking system can be a system independent from the production task tracking system, and can also be a subsequent system related to the logistics task tracking system, so that comprehensive tracking from production to transportation is realized. The computing device of the logistics task tracking system can be configured to: and judging the task object and/or the task object condition of the logistics task according to the target image acquired by the image acquisition equipment, and determining the progress condition of the logistics task according to the position of the logistics task acquired by the sensor.

In the case of local computing power deficiency or network bandwidth operation, the cloud can be used for computing. At this point, the server may be configured to: acquiring a target image uploaded by the production task tracking system; judging the execution state of the production task according to the target image; and issuing the execution status to the computing equipment of the production task tracking system. Specifically, the server may perform feature extraction of the target image based on the trained CNN model at the cloud, and compare the feature extraction with the features of the database to find out a corresponding prescribed image, and send the result of the search and comparison to the local.

To facilitate reporting of information, the platform may further comprise: a client for: receiving the current state of the task actively pushed by the server; and/or obtaining the current state of the task from the server when queried by a user. For example, the tracking platform may publish a tracking App for downloading by the client, and then the user may be adapted to view the target task, the provider, and the current operating conditions of the supply chain at any time (e.g., different viewing permissions are required) by the client on which the corresponding App is installed, and to control the progress of the task, etc., as required.

In one embodiment, the plurality of task tracking systems connected to the server includes a plurality of task performers performing homogeneous tasks, and the server is configured to: executing side task condition information of the plurality of task executing sides calculated based on the current conditions of the plurality of tasks; and providing the executive task condition information to a task assigning party so that the task assigning party selects a task executing party to execute a new task based on executive task condition information of the plurality of task executing parties.

In one embodiment, the plurality of task tracking systems connected to the server includes a plurality of task performers performing a same product supply chain, and the server is configured to: acquiring executive task condition information of the plurality of task executors calculated based on the current conditions of the plurality of tasks; determining current supply chain condition information for the supply chain based on executive task condition information for the plurality of task executors; determining a new task to perform based on the current supply chain condition information; and issuing the determined new task to a corresponding task executive party.

In addition, tracking systems with different attributes, such as a production task tracking system and a logistics task tracking system, can be further included in the platform, so that the tracking of a specific object (such as printed cloth of the printed order A) from production to transportation is completed through linkage of the tracking systems with different attributes.

FIG. 4 is a schematic diagram of a computing device that can be used to implement the production task tracking method according to an embodiment of the present invention.

Referring to fig. 4, computing device 400 includes memory 410 and processor 420.

The processor 420 may be a multi-core processor or may include a plurality of processors. In some embodiments, processor 420 may include a general-purpose host processor and one or more special coprocessors such as a Graphics Processor (GPU), a Digital Signal Processor (DSP), or the like. In some embodiments, processor 420 may be implemented using custom circuits, such as an Application Specific Integrated Circuit (ASIC) or a Field Programmable Gate Array (FPGA).

The memory 410 may include various types of storage units, such as system memory, Read Only Memory (ROM), and permanent storage. Wherein the ROM may store static data or instructions that are required by the processor 420 or other modules of the computer. The persistent storage device may be a read-write storage device. The persistent storage may be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the persistent storage device employs a mass storage device (e.g., magnetic or optical disk, flash memory) as the persistent storage device. In other embodiments, the permanent storage may be a removable storage device (e.g., floppy disk, optical drive). The system memory may be a read-write memory device or a volatile read-write memory device, such as a dynamic random access memory. The system memory may store instructions and data that some or all of the processors require at runtime. Further, the memory 410 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic and/or optical disks, may also be employed. In some embodiments, memory 410 may include a removable storage device that is readable and/or writable, such as a Compact Disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, dual layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (e.g., SD card, min SD card, Micro-SD card, etc.), a magnetic floppy disc, or the like. Computer-readable storage media do not contain carrier waves or transitory electronic signals transmitted by wireless or wired means.

The memory 410 has stored thereon executable code that, when processed by the processor 420, causes the processor 420 to perform the production task tracking method described above.

[ application example ]

The task tracking scheme of the present invention is particularly useful for production tasks that can determine that production is proceeding normally based on image comparison, such as digital printing tasks. Fig. 5 shows an example of a technical implementation flow of the digital printing automatic order following according to the invention.

In step S510, a camera captures a printing machine live video. For example, live image frames acquired at 20XX year, 7 month, 4 days 15:35:22 are shown. Subsequently, in step S520, the adaptive ROI obtains the actual flower type region, as shown by the corresponding red box region in the figure. Subsequently, in step S530, feature extraction of the stamp ROI is performed.

In the lower branch, however, a library pattern features database is built from the printing library pattern dataset at step S540. This step S540 may be performed well before the upper part branches to steps S510-530, or may be continued, for example, whenever a new pattern is input, it is subjected to pattern feature analysis and the base library pattern feature database is updated.

Thus, in step S550, the features extracted from the ROI for printing can be compared with the pattern feature database of the base, and the similarity calculation ranking of the feature comparison can be performed.

Then, in step S560, Top10 sorting results are output, Top1 order information is correlated, and the current number of pattern processing meters is calculated through meter counter reading.

And the automatic order following system receives the reported information, and summarizes, analyzes and displays the results. Fig. 6 shows a diagram of the presentation effect of the single example shown in fig. 5. As shown, the left side of the figure finds the corresponding printed pattern from the feature database based on image feature comparison. And then, combining the comparison result with the current degree of the meter counter, and summarizing and reporting the comparison result to a display interface of the automatic order following system, such as a display of local computing equipment or a display screen of a client.

The production task tracking method, system and platform according to the present invention have been described in detail above with reference to the accompanying drawings. The scheme is particularly suitable for being implemented as a digital printing automatic order following scheme based on computer vision, an effective ROI (region of interest) of printing is detected by changing a motion region in a camera picture by utilizing video intelligent algorithm analysis, then the image features of the ROI of the printing are extracted by an image feature extraction algorithm and compared with the feature vectors of a pattern data set of a printing base to be sorted, the pattern of TOP1 is confirmed to be a correct corresponding pattern according to an identification threshold, the number of production processing meters corresponding to the pattern after corresponding order information and meter counter data processing is obtained, and finally the obtained number is output to an automatic order following system for data analysis integration and result display.

The technology of the invention effectively reduces the cost and the transformation difficulty of digital transformation of a digital printing factory, has the characteristics of light weight deployment and strong reproducibility, obtains the real-time progress of printing processing of the factory through algorithm analysis in real time under the condition of not changing the original working mode of workers, synchronizes the real-time progress to a producer, a platform side and a consumer, achieves efficient production and marketing cooperation, accurately controls the production condition of printing orders, improves the management efficiency of the factory, reduces the cost and improves the productivity. The invention provides a digital printing automatic order following technical framework based on image feature extraction, and provides self-adaptive printing area ROI detection, thereby reducing the influence of other non-printing area contents in a video picture on the printing area ROI feature extraction and improving the matching accuracy of a printing ROI area and a pattern base.

Furthermore, the method according to the invention may also be implemented as a computer program or computer program product comprising computer program code instructions for carrying out the above-mentioned steps defined in the above-mentioned method of the invention.

Alternatively, the invention may also be embodied as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) having stored thereon executable code (or a computer program, or computer instruction code) which, when executed by a processor of an electronic device (or computing device, server, etc.), causes the processor to perform the steps of the above-described method according to the invention.

Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented as electronic hardware, computer software, or combinations of both.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of the present invention. 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 and/or flowchart illustration, and combinations of blocks in the block diagrams and/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.

Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.