Process management system and device

Abstract

The embodiment of the invention provides a process management system and device, and the system comprises an acquisition module which is configured to obtain the process information of an operator completing a target operation, and the process information is configured to reflect the completion condition of the operator on the target operation; and the storage module is configured to match timestamps with the process information acquired by the acquisition module and store the process information with the timestamps.

Description

Technical Field

[0001] This specification relates to the field of construction quality management, and particularly to a process management system and device. Background Art

[0002] In production and processing environments such as parts production, machinery manufacturing, and component assembly, how to control construction quality to reduce product defects is an important key factor. Since many work projects often involve a large number of participants, complex processes, and tight schedules, the operators responsible for actual production and processing operations tend to overlook the importance of process records and supplement the work process records after the work is completed. This may result in discrepancies between the work processes filled in by the operators and the actual operations, causing unnecessary troubles during the later review process.

[0003] Moreover, existing process management systems often focus on guiding operators to record the sequence of work progress, operation steps, etc., lacking supervision of the actual completion of work and means to deal with false reporting, omission reporting, and misreporting by operators. This will not only lead to a decrease in work efficiency but may also induce serious accidents.

[0004] Therefore, it is necessary to propose a process management system and device that can accurately record the project progress and completion status of the current work during the production and processing process, and analyze and judge whether the current work process is compliant and error-free, so as to improve the quality of construction work and reduce unnecessary mistakes. Summary of the Invention

[0005] One or more embodiments of this specification provide a process management system. The process management system includes: a collection module configured to obtain process information of an operator completing a target operation, where the process information is configured to reflect the completion status of the operator for the target operation; a storage module configured to match a time stamp to the process information collected by the collection module and store the process information with the time stamp.

[0006] One or more embodiments of this specification provide a process management device. The process management device includes: an input device, a recording device, and a processor; the input device is configured to collect time information of an operator completing a target operation; the recording device is configured to collect process information of the operator completing the target operation; the processor is configured to: obtain the process information; match a time stamp to the process information and store the process information with the time stamp. Brief Description of the Drawings

[0007] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not restrictive. In these embodiments, the same reference numerals represent the same structures, where:

[0008] Figure 1 is a schematic diagram of an application scenario of a process management device according to some embodiments of this specification;

[0009] Figure 2 is an exemplary schematic diagram of a process management system according to some embodiments of this specification;

[0010] Figure 3 is an exemplary schematic diagram of consistency verification according to some embodiments of this specification;

[0011] Figure 4 is an exemplary schematic diagram of auxiliary verification according to some embodiments of this specification;

[0012] Figure 5 is an exemplary schematic diagram of an acquisition module according to some embodiments of this specification.

[0013] Figure 6 is an exemplary schematic diagram of determining an acquisition frequency according to some embodiments of this specification. Detailed implementation manners

[0014] To more clearly illustrate the technical solutions of the embodiments of this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some examples or embodiments of this specification. For those of ordinary skill in the art, without creative efforts, this specification can also be applied to other similar scenarios based on these drawings. Unless obvious from the context or otherwise stated, the same reference numerals in the figures represent the same structures or operations.

[0015] It should be understood that the "system", "device", "unit" and / or "module" used herein is a way to distinguish different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the said words can be replaced by other expressions.

[0016] As shown in this specification and the claims, unless the context clearly indicates an exception, words such as "a", "an", "one" and / or "the" are not specifically singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0017] Flowcharts are used in this specification to illustrate the operations performed by the systems according to the embodiments of this specification. It should be understood that the preceding or subsequent operations are not necessarily executed precisely in sequence. On the contrary, the steps can be processed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps can be removed from these processes.

[0018] Figure 1 It is a schematic diagram of the application scenario of the process management device shown in some embodiments of this specification.

[0019] In some embodiments, the process management device 100 may include an input device 110, a recording device 120, and a processor 130.

[0020] An input device is a device that has an information input function and can interact with an operator. For example, the input device may include a tablet computer, a smart watch, a VR glasses, a microphone, etc.

[0021] In some embodiments, the input device is configured to receive the time information generated by the operator during the completion of the target operation. Among them, the target operation may include actual repair, processing, production, etc. operations that need to be completed; the time information may include the start time of the target operation, the total duration of the target operation, the end time of the target operation, and other information.

[0022] The input device can obtain the time information in various ways. In some embodiments, the input device can receive the start time and end time of the current work process manually input by the operator, etc., as the required time information.

[0023] For more descriptions about the target operation and the time information, reference can be made to Figure 2 and its related descriptions.

[0024] In some embodiments, the input device can also collect other information input by the operator, such as the operator's work number, operation type (i.e., the target operation type), etc.

[0025] The recording device 120 is configured to record the relevant information generated by the operator during the completion of the target operation. In some embodiments, the recording device can be the same device as the input device, or can be a different device. Exemplarily, the input device can be a tablet computer, while the recording device can be VR glasses.

[0026] The recording device 120 can obtain the process information in the completion of the target operation in various ways. In some embodiments, the recording device is a device including a camera. When the operator completes the target operation, the operator needs to wear the recording device. The recording device can capture the image data generated by the operator in the completion of the target operation through the camera, and identify and judge the image data through common image recognition algorithms to obtain the process information of the current target operation. For example, in the process of the operator using a torque wrench to install a bolt, the recording device can record the installation process of the bolt, and through common image recognition algorithms, confirm whether the bolt is installed in the corresponding hole position, and take a comparison picture before and after installation, and determine the comparison picture before and after installation as the required process information.

[0027] In some embodiments, the recording device 120 may include one or more sensors. The one or more sensors may be sensors with the same function or sensors with different functions. The recording device 120 can obtain the corresponding process information through the sensors. Exemplarily, the recording device can obtain image and / or video information through a camera, obtain audio information through a microphone, obtain distance information through a depth sensor, etc.

[0028] In some embodiments, the recording device 120 can start or end recording under the manual setting of the operator. For example, the operator triggers the corresponding control button by himself to trigger or end recording. In some embodiments, the recording device can automatically trigger or end recording. For example, in response to meeting a preset condition, the recording device can automatically start or end recording. Only as an example, the preset condition can be to automatically start recording when a preset component is detected, and automatically stop recording when the preset component is not detected.

[0029] The processor 130 is configured to implement the operations of the entire process management system and function modules for data processing and computing tasks. The processor can receive data such as time information and process information transmitted from the input device and the recording device, and perform data processing and computing. In some embodiments, the processor may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and can control other components in the process management system to perform desired functions.

[0030] In some embodiments, the process management apparatus 100 may further include a storage device 140. The storage device may include one or more storage units, which may include local storage units built into the input device and / or the recording device, or may include cloud storage units located on the Internet. One or more computer program instructions may be stored on the storage device, and the processor may run the program instructions to implement the process management methods of the various embodiments disclosed herein and / or other desired functions. Various contents such as image data and audio data may also be stored in the storage device.

[0031] For more information about the input device 110, the recording device 120, the processor 130, and the storage device 140, please refer to the following description in the specification.

[0032] It should be noted that the above description of the process management apparatus 100 and its modules is only for convenience of description, and does not limit this specification to the scope of the examples given. It can be understood that for those skilled in the art, after understanding the principle of the system, they may, without departing from this principle, make any combination of the various modules, or form a subsystem and connect it with other modules. In some embodiments, Figure 1 the input device 110, the recording device 120, the processor 130, and the storage device 140 disclosed in may be different modules in a system, or a module may implement the functions of two or more of the above modules. For example, the various modules may share a storage module, or each module may have its own storage module. Such variations are all within the scope of protection of this specification.

[0033] Figure 2 is an exemplary schematic diagram of a process management system according to some embodiments of this specification. In some embodiments, the process management system 200 may be integrated into the processor 130 of the process management apparatus.

[0034] In some embodiments, the process management system 200 includes a collection module 210 and a storage module 220. The collection module is configured to obtain the process information of the operator completing the target operation, and the process information is configured to reflect the completion situation of the operator for the target operation; the storage module is configured to match a time stamp to the process information collected by the collection module and store the process information with the time stamp.

[0035] In some embodiments, the process management system 200 may further include a control module 230. The control module 230 is a functional module configured to control and manage the collection module. Exemplarily, the control module may determine the collection frequency of the collection module based on the target operation type and the collection content corresponding to the process information.

[0036] For more information about the control module, target operation type, collected content, and collection frequency, see Figure 6 and its related descriptions.

[0037] The acquisition module 210 refers to a functional module used to monitor and collect process-related information generated by an operator during the completion of a target operation. In some embodiments, the acquisition module 210 may receive time information from an input device and process information sent by a recording device. For more descriptions of the acquisition module, see Figure 5 the corresponding content.

[0038] The target operation refers to operations such as maintenance, processing, and production carried out by an operator during the actual work process. Exemplarily, the target operation may include: installing bolts on the wing, welding the gap between metal shells, etc.

[0039] The process information refers to the information generated during the work process, which can reflect the specific steps, completion progress, and completion status of the operator's target operation. In some embodiments, the process information includes at least one of voice information, picture information, and video information of the operator completing the target operation.

[0040] Exemplarily, when an operator installs bolts on the wing, the process information may include pictures of the bolts and corresponding mounting holes, videos of the installation process, the sounds emitted by the torque wrench during the installation process, and the operator's voice, etc.

[0041] The acquisition module 210 can obtain process information in various ways. For example, the acquisition module can obtain process information through a recording device, or can obtain the already collected process information through a storage device.

[0042] The storage module 220 refers to a functional module used to receive the relevant information collected by the acquisition module, match timestamps to the collected process information, and store it. For example, the storage module 220 can be implemented based on the storage device 140. The storage module can perform data transmission with the acquisition module.

[0043] In some embodiments, the storage module 220 is communicatively connected to the distributed database of the blockchain, and the storage module can store the timestamped process information into the distributed database of the blockchain.

[0044] In some embodiments, the storage module 220 can also receive input information input by an input device and match a timestamp to the input information. For example, when the input information includes the operation type, the start time of the corresponding operation type, and the end time of the corresponding operation type, the storage module can also match timestamps to the start time and the end time and store them.

[0045] A timestamp refers to complete and verifiable data used to prove that a certain piece of data existed before a specific time, and each timestamp corresponds to only one moment in time. In some embodiments, a timestamp can be represented by a character sequence. The timestamp can be determined based on the occurrence time of process information. For example, a timestamp can include the occurrence time and a random character sequence.

[0046] Exemplarily, when an operator performs circuit soldering, and the starting time point is 01:27:44 on December 08, 2023, then the timestamp corresponding to the process information (such as the corresponding image information) at the start of circuit soldering can be 2023120801274425415.

[0047] In some embodiments, the storage module can match timestamps to all process information. In some embodiments, the storage module can determine the process information that needs to be timestamped and only match timestamps to the process information that needs to be timestamped.

[0048] In some embodiments, the storage module can determine the process information that needs to be timestamped based on multiple methods. In some embodiments, the storage module can determine the importance of the process information based on an importance determination model, and in response to the importance of the process information exceeding an importance threshold, determine that the process information needs to be matched with a timestamp.

[0049] Taking only the process information as picture information as an example, the storage module can determine based on the importance determination model whether the importance of the picture information exceeds the importance threshold, determine the picture information with an importance exceeding the importance threshold as important picture information, perform timestamp matching on the important picture information and store it in the storage module.

[0050] The importance determination model can be a machine learning model used to determine the importance of picture information. The importance determination model can be obtained through training, and the training sample data includes multiple groups of pictures taken. The training label can be the importance corresponding to each group of pictures. The training label can be obtained through manual annotation. For example, an operator can select the pictures taken at the start and end of the operation process from all the pictures corresponding to the process information taken and determine their importance as 1, and determine the importance of other pictures as 0. During training, a loss function is constructed based on the difference between the importance output by the importance determination model and the label, and through parameter update, a trained importance determination model is obtained.

[0051] By collecting the process information of an operator completing a target operation, matching it with a timestamp and saving it, the system can achieve real-time monitoring and recording of the operation process to ensure that the operation complies with the specifications. When data needs to be retrieved later, relevant data can be quickly selected through the timestamp, and the accurate recording time can be obtained, facilitating data query and management.

[0052] In some embodiments, the storage module may also determine a key time point corresponding to the process information; and match a timestamp to the process information based on the key time point.

[0053] A critical time point refers to a time period or moment of decisive significance in the process of an operator completing a target operation. A critical time point often has a significant impact on the results and requires special attention and supervision.

[0054] In some embodiments, for operations related to processing and production, the key time points may include the time when the operation starts and ends. For operations related to maintenance and testing, the key time points may be the time when the testing tool is used to test the object to be tested and the test results are displayed during the testing process. For example, when a metal shell is polished, the time points when the polishing starts and ends are key time points; when a multimeter is used to measure the voltage of a circuit, the time point when the multimeter displays the voltage reading is the key time point.

[0055] In some embodiments, the storage module may determine the key time point corresponding to the process information based on a variety of methods.

[0056] For example, when the process information is voice information, the storage module can determine the time point corresponding to the key voice based on voice recognition, and use the time point as the key time point. The key voice can be the voice indicating the start of the operation, the voice when the operation ends, or the voice related to the operation result. The key voice can be preset based on the specific target operation type.

[0057] For another example, when the process information is video or image information, the storage module can determine the time point corresponding to the key image based on image recognition, and use the time point as the key time point. The key image may include an image before the operation, an image after the operation is completed, an image collected when the detection tool is placed, etc. The key image can be preset based on the specific target operation type.

[0058] Exemplarily, the storage module can use a voice recognition program to perform voice recognition on the operator. When the operator is recognized to issue specific commands such as starting or ending an operation, the corresponding time point is determined as a key time point. When the operator is recognized to orally read the reading of the measuring device during the maintenance measurement process, the corresponding time point can also be determined as a key time point.

[0059] After identifying the key time point, the storage module can match the time stamp to the process information of the key time point based on the key time point. For instructions on how to match the time stamp, please refer to the corresponding content in the previous text.

[0060] In some embodiments of this specification, key time points are first selected and then timestamp matching is performed. This can not only reduce the time point data for timestamp matching, making the data structure clearer and facilitating management and query, but also reduce unnecessary matching and storage requirements, and more efficiently utilize system resources.

[0061] In some embodiments, the storage module can also determine key video frames based on video information and match timestamps for the key video frames.

[0062] Video information refers to the information corresponding to the video data obtained by the acquisition module. In some embodiments, video information may include video images, video start time, shooting device parameters, and the location of the shooting device, etc. In some embodiments, video information may include two-dimensional video information or three-dimensional video information with depth.

[0063] A key video frame refers to a video frame in the entire video that contains more important information compared to other video frames. For example, when an operator detects the voltage of a circuit board, the video frame when the detection device displays the reading or result is more important than the video frame when the operator installs and adjusts the detection device. When an operator connects two components, the video frame when the connection is completed is more important than the video frame after the connection is completed.

[0064] In some embodiments, the storage module can determine key video frames based on multiple methods. For example, a key video frame comparison table for different operation types can be pre-stored in the storage module, and based on the current operation type, the key video frames can be determined by looking up the table. The key video frame comparison table contains the key video frames corresponding to the target operations of different operation types. The key video frames corresponding to one target operation can include video frames of one or more stages, and the key video frames can reflect information such as the completion status or quality of the target operation.

[0065] The key video frames corresponding to the target operation can be preset based on historical experience. Taking the target operation of installing screws on the wing as an example, this process may include the process of the operator selecting bolts, selecting tools, and installing the screws in the corresponding positions. Among them, the processes of selecting bolts and tools are not important. What needs to be concerned about is whether the operator has installed the screws in the corresponding positions. Therefore, during this operation process, the video frames corresponding to the process of the operator installing the screws in the corresponding positions are the key video frames. That is, the key video frames include: (1) Key frames before screwing: Video frames with hands, screw holes, screws, and tools in the picture; (2) Key frames during screwing: Video frames where the tool (wrench) acts on the screw; (3) Key frames after the screw has been installed: Video frames with hands and the screw already in the screw hole after the video frames of operating with the tool.

[0066] Correspondingly, the storage module can sequentially identify video frames, determine whether the content of the video frames meets the content requirements of the corresponding key video frames, and use the video frames that meet the requirements as key video frames.

[0067] In some embodiments, the storage module can also process video information and operation types through a video recognition model, determine key video frames, perform timestamp matching on the obtained key video frames, and store them in the storage module.

[0068] The video recognition model is a machine learning model and can be obtained through training. The training sample data includes multiple groups of video information and corresponding operation types. The training label can be the key video frame in each group of video information. The training label can be obtained through manual annotation. For example, an operator can select the key video frame corresponding to the operation type from the video information. The training of the video recognition model is similar to the training of the importance determination model. For specific details, reference can be made to the training description of the importance determination model.

[0069] By performing timestamp matching and saving on the key video frames instead of the entire video, the amount of information to be saved can be reduced, only the key information is stored, avoiding information redundancy caused by saving a large amount of videos, and improving the efficiency of information storage and management.

[0070] In some embodiments, the storage module can also store the process information with the timestamp in the blockchain.

[0071] Blockchain is a distributed database technology that groups data into one block after another and links them. Each block can store a part of the information. Once the data is written into the blockchain, it cannot be tampered with or deleted, thus ensuring the integrity and traceability of the stored data.

[0072] In some embodiments, the storage module can store the process information in the blockchain in the order of timestamps.

[0073] By storing the process information in the blockchain, the traceability of the process information can be ensured, preventing someone from tampering with the recorded process information and ensuring the authenticity and reliability of the saved information.

[0074] Figure 3 It is an exemplary schematic diagram of consistency verification shown in some embodiments of this specification.

[0075] In some embodiments, as Figure 3 shown, the storage module can be further configured to: perform consistency verification 320 on the timestamped process information 301; in response to the process information 310 passing the consistency verification 320, store the process information in the blockchain 330.

[0076] For relevant descriptions about storage modules, timestamps, process information, blockchains, etc., reference can be made to Figure 2 the corresponding descriptions.

[0077] Consistency verification 320 refers to the verification of whether process information needs to be stored. Process information 310 that passes the consistency verification indicates that its authenticity or validity is relatively high and can be stored for subsequent use.

[0078] In some embodiments, the consistency verification 320 may include multiple verification methods. For example, the consistency verification includes: comparing the time differences between the timestamps of different types of process information (such as image information and sound information) corresponding to the same operation process, and determining that the process information passes the consistency verification when the time difference is within a preset time range (such as not exceeding a preset difference threshold). Among them, the preset time range can be preset manually.

[0079] In some embodiments, as Figure 3 shown, the consistency verification 320 may include: determining the first detection information 321 based on the image information 311; determining the second detection information 322 based on the sound information 312; and determining that the process information 310 passes the consistency verification 320 in response to the first detection information 321 and the second detection information 322 meeting the preset detection conditions.

[0080] The image information 311 refers to images and related information related to the operation process of the operator. In some embodiments, the image information 311 may include images taken at a single point (including before and after the operation), images taken at multiple points (including before and after the operation), images of the operation process, etc. Among them, a point refers to the position, angle, distance, etc. where a recording device (such as a camera) collects process information. For example, a certain point may be a point taken horizontally at the center 1 m directly in front of device X (on the same horizontal line as device X).

[0081] In some embodiments, the image information 311 can be obtained by a recording device (such as a camera) taking pictures before, after, during, or during detection of the operation, or can be automatically extracted from video information. For descriptions about video information, reference can be made to Figure 2 or Figure 4 the corresponding descriptions.

[0082] The first detection information 321 refers to the information to be verified extracted from the image information 311. For example, the first detection information may include the reading value of the detection tool in the detection image included in the image information.

[0083] In some embodiments, the storage module may identify image information through an image recognition algorithm, and use the identified information as the first detection information. For example, the storage module may detect the images in the image information based on the corresponding process standard, extract the corresponding detection device and its reading value as the first detection information, such as [pressure detector A, 100 kPa]; or it may also detect the images in the image information based on the corresponding process standard, identify the images corresponding to each step in the process standard in the image information, and use the identified steps and completion results as the first detection information for the corresponding images, such as [install bolt C at position B, completed].

[0084] The sound information 312 refers to the sounds and related information related to the operation process of the operator. In some embodiments, the sound information 312 may include the reading information of the worker on the measuring tool and the corresponding sounds emitted by the construction tool during the construction process. For example, the sound information may be the information obtained by collecting the voice of the worker when reading the value; or for another example, the sound information may be the corresponding sound (such as the sound of "click click click") emitted by the torque wrench when it reaches the set torque.

[0085] In some embodiments, the sound information 312 can be obtained by recording before operation, after operation, during operation, and during detection, or can be automatically extracted from the video information.

[0086] In some embodiments, the acquisition module may collect sound through a recording device (such as a microphone), generate a sound file, and divide the sound file into multiple frames as the sound information. Among them, a frame of sound refers to the smallest unit of sound signal processing. Since the sound signal has short-term stationarity, in actual processing, the sound signal can be divided into time periods of about 10-30 ms as frames. The non-overlapping part between frames is called the frame shift; dividing the frame into small parts can clearly depict the time-varying characteristics of the sound signal but has a large amount of calculation, while dividing the frame into large parts can reduce the amount of calculation but the change between adjacent frames is small, and it is easy to lose signal characteristics. Therefore, the frame length can be taken as 20 ms, and the frame shift is 1 / 3 to 1 / 2 of the frame length.

[0087] The second detection information 322 refers to the information to be verified extracted from the sound information 312. For example, the second detection information may include the reading value of the detection tool in the sound information 312.

[0088] In some embodiments, before determining the second detection information, the acquisition module may first process the sound information. For example, in order to maintain the short-term stationarity of the speech signal, the acquisition module may perform windowing on the sound information, multiplying it by a window function (such as a Hamming window) to reduce the Gibbs effect caused by truncation processing. In some embodiments, in order to store and process only valid information, the acquisition module may use an endpoint detection method to find the starting point and ending point of a segment of sound information. The endpoint detection method may be a double-threshold endpoint detection based on short-term energy and short-term zero-crossing rate.

[0089] In some embodiments, the acquisition module may identify the processed sound information through a sound recognition algorithm and use the identified information as the second detection information. For example, when the sound information contains speech (such as the voice of a worker reading a value), the acquisition module may use a speech recognition algorithm to extract the device corresponding to the speech and its read value as the second detection information.

[0090] For another example, when the sound information contains the sound emitted by a device during an operation (such as the "click, click, click" sound of a torque wrench), the acquisition module may use the DTW (Dynamic Time Warping) algorithm to compare the sound with a pre-recorded standard sound, classify the sounds of different operation steps, and use the identified steps and their completion status as the second detection information. For example, using the pre-recorded "click, click, click" sound of a torque wrench when tightening a bolt as template Q, calculate the distance between each frame with the sound information D to be identified, find the shortest path among the frame matching distances, and calculate the cumulative distance. When the cumulative distance of the shortest path (i.e., the sum of the distances of each shortest path) is less than a preset distance threshold, it is considered that the "click, click, click" sound is recognized, that is, it is determined that the bolt is tightened, and the second detection information is determined to be [Install bolt C at position B, completed]. The preset distance threshold can be preset manually.

[0091] The preset detection condition is a condition for verifying the consistency of the detection information. In some embodiments, the preset detection condition may be that all detection information is consistent. For example, the readings of the corresponding devices in the first detection information and the second detection information are the same; for another example, the completion status of the corresponding operation steps in the first detection information and the second detection information is the same.

[0092] For more descriptions of the preset detection conditions, please refer to Figure 4 the corresponding descriptions.

[0093] In some embodiments, in response to the first detection information and the second detection information satisfying a preset detection condition, the storage module may determine that the process information passes the consistency verification. For example, when the first detection information and the second detection information include read values, the storage module may match the worker readings identified in the second detection information with the readings in the image identified in the first detection information at the corresponding moment. When the read values are the same, it is determined that the first detection information and the second detection information are consistent, and it is determined that the process information passes the consistency verification.

[0094] For another example, when the first detection information and the second detection information include the identified classification information, such as the second detection information (the result of identifying a specific sound) shows that the installation is up to standard, and the first detection information at the corresponding moment (that is, the result identified from the image) is also up to standard, it is determined that the first detection information and the second detection information are consistent; it is determined that the process information passes the consistency verification.

[0095] In some embodiments of this specification, by determining the first detection information based on image information, determining the second detection information based on sound information, and judging whether the first detection information and the second detection information, and whether the process information passes the consistency verification through preset detection conditions, the accuracy of the detection information can be verified based on the degree of conformity of the information in both the image and sound aspects, so that the process information passing the consistency verification has higher reliability.

[0096] In some embodiments, in response to the process information passing the consistency verification, the storage module may store the process information in the blockchain. For example, the storage module may store the timestamped image information and sound information in the process information passing the consistency verification in the blockchain.

[0097] In some embodiments, in response to the process information failing to pass the consistency verification, the storage module may perform auxiliary verification on the process information based on the video information. For specific content, see Figure 4 and its corresponding description.

[0098] In some embodiments of this specification, by performing consistency verification on the timestamped process information and storing the process information passing the consistency verification in the blockchain, the process information can be screened, and only the process information passing the consistency verification is retained, ensuring that the information stored in the blockchain is accurate.

[0099] Figure 4 is an exemplary diagram of the auxiliary verification shown in some embodiments of this specification.

[0100] In some embodiments, such as Figure 4As shown, the storage module is further configured to: in response to the process information 310 failing the consistency verification, perform an auxiliary verification 410 of the process information 310 based on the video information 313; in response to the process information 310 passing the auxiliary verification 410, store the process information 310 in the blockchain 330.

[0101] For the relevant descriptions regarding the consistency verification, reference can be made to Figure 3 and its corresponding descriptions.

[0102] The video information 313 refers to the video and related information related to the operation process of the operator. In some embodiments, the video information 313 may include the video of a single point, the video of multiple points, etc. during the worker's operation process. In some embodiments, the video information 313 can be obtained by shooting with a camera device during the operation and detection.

[0103] The auxiliary verification 410 refers to the verification performed on the process information that fails the consistency verification.

[0104] In some embodiments, the auxiliary verification can be implemented in various ways. For example, the auxiliary verification can be manual review. Only as an example, workers or managers different from the operator can review the video information and sound information of the process information that fails the consistency verification, and judge whether the second detection information and the third detection information are consistent according to prior knowledge and historical experience. If they are consistent, it is considered to pass the auxiliary verification.

[0105] In some embodiments, the auxiliary verification 410 may include: based on the video information 313, determining whether the preset operation 411 when the operator completes the target operation meets the preset operation requirements 412; in response to not meeting the preset operation requirements, prompting to re - complete the preset operation 413; in response to meeting the preset operation requirements, based on the video information 313, obtaining the third detection information 414; determining whether the third detection information 414 and the second detection information 322 meet the preset detection conditions 323; in response to meeting the preset detection conditions, determining that the process information 310 passes the auxiliary verification 410.

[0106] For the relevant descriptions regarding the second detection information, reference can be made to Figure 3 the corresponding descriptions.

[0107] The target operation refers to the operation that needs to be performed by the operator. For more descriptions, reference can be made to Figure 1 、 2 the corresponding content.

[0108] The preset operation 411 refers to the actual operation process when the operator completes the target operation. The preset operation can be an operation that affects the completion quality or the accuracy of the data result. For example, the preset operation 411 can include the final data measurement process after construction is completed. Another example is that the preset operation can be the specific installation process of a screw.

[0109] The preset operation requirements are used to determine whether the preset operation meets the specification requirements. For example, the preset operation requirements can be whether each step in the preset operation is correct, whether it is executed in place, and whether it is completed in sequence, etc.

[0110] In some embodiments, the storage device can determine whether the preset operation meets the preset operation requirements in various ways based on the video information. For example, the storage device can perform an intelligent comparison between the video information and the standard operation corresponding to the target operation to determine whether the preset operation meets the preset operation requirements.

[0111] In some embodiments, in response to the preset operation not meeting the preset operation requirements, the storage device can prompt to re - complete the preset operation. For example, the storage device can prompt the operator to re - perform the preset operation corresponding to the target operation through voice prompts, vibration prompts, etc.; until the preset operation meets the preset operation requirements.

[0112] In some embodiments, in response to the preset operation meeting the preset operation requirements, the storage device can obtain the third detection information based on the video information.

[0113] The third detection information 414 refers to the information that needs to be verified extracted from the video information 313. For example, the third detection information can include the reading value of the detection tool recorded in the video information 313.

[0114] In some embodiments, the storage device can obtain the third detection information in various ways based on the video information. For example, the storage device can obtain multiple video frames based on the video information, and based on a video recognition model, etc., screen out the key video frames that are different from the image information that fails the consistency verification, and then read the values of the screened video frames, and use the read values as the third detection information. Among them, the relevant description about the video recognition model can be found in Figure 2 the corresponding description, and the method of reading the values of the video frames can refer to Figure 3 the method of determining the first detection information based on the image information described in

[0115] In some embodiments, the preset detection conditions can also include that the second detection information and the third detection information are both consistent.

[0116] In some embodiments, the storage device may determine whether the third detection information and the second detection information meet a preset detection condition in various ways based on the third detection information and the second detection information. For example, the storage device may compare the read values of the corresponding devices in the second detection information and the third detection information. When the read values of the corresponding devices are the same, it is determined that the third detection information and the second detection information meet the preset detection condition.

[0117] In some embodiments, in response to the third detection information and the second detection information meeting the preset detection condition, the storage device may determine that the process information passes the auxiliary verification.

[0118] In some embodiments of the present specification, by judging whether a preset operation meets the preset operation requirements based on the video information in the process information, giving corresponding prompts to the operators who do not meet the preset operation requirements, and for those who meet the preset operation requirements, obtaining the third detection information based on the video information, judging whether the third detection information and the second detection information meet the preset detection condition, and regarding the process information that meets the preset detection condition as passing the auxiliary verification, the accuracy of the process information can be judged in combination with the video information, making the verification process more rigorous and reliable.

[0119] In some embodiments, in response to the process information passing the auxiliary verification, the storage device may store the process information in the blockchain. For example, the storage device may store the identified and extracted video frames with timestamps in the blockchain.

[0120] In some embodiments of the present specification, for the process information that fails the consistency verification, by using the auxiliary verification and further verifying the consistency of the process information in combination with the video information, the verification process can be made more perfect, with a high error tolerance rate, and it can be ensured that the information stored in the blockchain is accurate.

[0121] Figure 5 It is an exemplary schematic diagram of the acquisition module shown in some embodiments of the present specification.

[0122] In some embodiments, as Figure 5 shown, the acquisition module 210 may include an acquisition unit 211 and an analysis unit 212; the analysis unit 212 is configured to generate process information based on the information acquired by the acquisition unit 211. For more content about the acquisition module, reference can be made to the relevant description in Figure 2 , and for the relevant description of the process information, reference can be made to the corresponding description in Figure 2 - 4 .

[0123] In some embodiments, the storage module is further configured to: determine the task completion status based on the process information and store the task completion status in the blockchain. For more content about the blockchain, reference can be made to the corresponding description in Figure 3 .

[0124] The acquisition unit 211 is a unit for acquiring relevant information during the operation of an operator. In some embodiments, the acquisition unit may include a sound acquisition unit, an image acquisition unit, etc. Among them, the sound acquisition unit is used to control an input device or a recording device to acquire sound information, and the image acquisition unit is used to control an input device or a recording device to acquire image information and video information. For more descriptions of the sound information, image information, and video information, reference can be made to Figure 2 - 4 the corresponding description.

[0125] In some embodiments, the sound acquisition unit may control a recording device such as a microphone of an input device or a recording device to acquire sound information.

[0126] In some embodiments, the image acquisition unit may control devices such as a camera and an infrared detector of an input device or a recording device to acquire two-dimensional image information, three-dimensional image information, etc.

[0127] The analysis unit 212 is a unit for analyzing the information acquired by the acquisition unit.

[0128] In some embodiments, the analysis result obtained by the analysis unit analyzing the information acquired by the acquisition unit can at least reflect the completion situation of the corresponding target operation.

[0129] For example, the analysis unit can determine whether the corresponding work step is completed based on the acquired sound information. The analysis unit can determine whether the operation of a single point is completed or whether the operations of multiple points are all completed based on the images before and after the operation; for another example, the analysis unit can determine whether the operation sequence reflected by each image is correct according to the shooting time based on the images of the operations at each point; for yet another example, in the picture information acquired by the acquisition unit, a placement and measurement picture of a measuring device such as a vernier caliper is shown, and the analysis unit can determine the reading value of the measuring device based on this placement and measurement picture.

[0130] In some embodiments, the analysis unit can generate process information in various ways based on the information acquired by the acquisition unit. For example, the analysis unit can identify key operation steps through a preset analysis algorithm, and determine the sound information, image information, video information, etc. related to the key operation steps as process information. The preset analysis algorithm may include a machine learning model, such as an identification model, and the identification model may be a neural network model (Neural Network, NN), etc.

[0131] In some embodiments, the recognition model in the preset analysis algorithm can be obtained by training with labeled training samples. Taking the recognition model of image information as an example, the training samples can be sample images that record the operation process in the historical records, and the training labels can be "0" and "1". "0" indicates that the step in the sample image is a non-critical operation step, and "1" indicates that the step in the sample image is a critical operation step (i.e., the sample image can be determined as process information). The training labels can be manually labeled. The training of the recognition model is similar to the training of the importance determination model. For details, please refer to Figure 2 the description of the training of the importance determination model in

[0132] The task completion situation refers to the situation where the operator completes the operation steps. In some embodiments, the task completion situation may include the completion progress and the completion quality. The completion progress can be represented by a percentage. For example, the task has been completed 50%, and the quality is qualified.

[0133] In some embodiments, the storage module can determine the task completion situation of each task based on the analysis result of the analysis unit.

[0134] For example, the analysis result of the analysis unit includes the number of collected process standard parameters. The storage module can calculate the completion progress based on the number of collected process standard parameters and the total number of process standard parameters that need to be collected. Another example is that each process standard parameter has an optimal measurement value and a measurement range value (the measurement value is qualified within the measurement range value). The analysis unit can calculate the difference between the actual measurement value and the optimal measurement value, and determine the completion quality based on the difference. The smaller the difference, the higher the quality. Another example is that the storage module can also comprehensively consider multiple parameters such as the completion speed and the error value, and comprehensively determine the completion quality through an evaluation model. In some embodiments, the evaluation model can be a machine learning model. For example, it can include a neural network model.

[0135] In some embodiments, the evaluation model can be obtained by training with evaluation training samples with evaluation labels. The evaluation training samples can include the completion speed and error value of each sample operation step in the historical records. The evaluation labels can be the completion quality level of the sample operation steps, which can be labeled by the system or manually. For example, the completion quality level can be divided into 3 levels: unqualified, qualified, and excellent. Only as an example, when both the completion speed and the error do not meet the preset standards, it is unqualified. When the completion speed does not meet the preset standards and the error meets the preset standards, it is qualified. When both the completion speed and the error meet the preset standards, it is excellent. The preset standards can be preset by technical personnel. The training of the evaluation model is similar to the training of the importance determination model. For details, please refer to Figure 2 the description of the training of the importance determination model in

[0136] In some embodiments, the storage module may store the determined task completion status in the blockchain. For example, the storage module may record the task completion status on the blockchain at preset intervals, and the preset intervals can be set manually.

[0137] In some embodiments of this specification, the analysis unit generates process information based on the information collected by the collection unit, and then the storage module determines the task completion status based on the process information and stores the task completion status in the blockchain, which can effectively retain important process information and the corresponding task completion status, efficiently record the completion process of each task, so as to achieve better process management.

[0138] In some embodiments, the control module 230 is configured to determine the collection frequency of the collection module, and the collection frequency is determined based on the target operation type 612 and the collection content 613 corresponding to the process information.

[0139] The collection frequency refers to the information collection frequency of the collection module for the process information of the operator to complete the target operation. In some embodiments, the collection frequency may include the collection frequencies of multiple collection channels, such as audio collection frequency, video collection frequency, image collection frequency, etc., and the collection frequency may also include the collection frequencies of different collection methods, such as the frequency of multiple sensors collecting data in sequence, the frequency of multiple sensors collecting data simultaneously, etc.

[0140] The target operation type 612 refers to the category to which the target operation performed by the operator belongs during the actual work process. In some embodiments, the target operation type may include maintenance, processing, production, inspection, installation, etc. Exemplarily, the target operation types of installing bolts on the wing and installing the dashboard in the cab both belong to installation, and the target operation types of grinding the burrs of mechanical parts and painting the metal surface both belong to processing.

[0141] In some embodiments, the target operation type can be determined by the current operator and input through the input device.

[0142] The collection content 613 refers to the data collected by the collection module from the input device or the recording device according to the collection frequency, and the collection content can reflect the working status of the current operator and the process information in completing the target operation. In some embodiments, the form of the collection content may include, but is not limited to, audio, video, image, text, etc. The collection module can store the obtained collection content in the storage module.

[0143] The control module 230 can determine the acquisition frequency based on various methods. In some embodiments, the control module can determine the acquisition frequency by constructing a vector database. The control module can construct a vector to be matched based on the target operation type, the acquisition content, and the proficiency of the operator. The control module can retrieve in the vector database based on the vector to be matched, obtain a reference vector whose vector distance from the vector to be matched is less than the distance threshold, and determine the historical acquisition frequency corresponding to the reference vector as the currently required acquisition frequency. Among them, the vector database is used to store a number of historical vectors and their corresponding historical acquisition frequencies. The historical vectors are constructed based on the historical target operation type, the historical acquisition content, and the historical operator proficiency.

[0144] By using the control module to regulate the acquisition frequency, system resources can be utilized more effectively, and the adverse effects on data recording caused by over-acquisition or under-acquisition can be avoided.

[0145] In some embodiments, the control module 230 can also evaluate the acquisition effect 621 of the candidate acquisition frequency based on the candidate acquisition frequency 611, the target operation type 612, and the acquisition content 613 through the acquisition effect evaluation model 620; and determine the target acquisition frequency 630 based on the acquisition effect.

[0146] The acquisition effect evaluation model 620 refers to a model used to evaluate the acquisition effect. In some embodiments, the acquisition effect evaluation model can be a machine learning model. For example, the acquisition effect evaluation model can include any one or a combination of a neural network (NN) model or other custom model structures, etc.

[0147] In some embodiments, the input of the acquisition effect evaluation model 620 can include the candidate acquisition frequency, the target operation type, and the acquisition content, and the output can include the acquisition effect of the candidate acquisition frequency.

[0148] The candidate acquisition frequency 611 refers to one or more acquisition frequencies to be selected. In some embodiments, the candidate acquisition frequency can be preset according to historical data or prior experience, or randomly generated, etc. For example, the candidate acquisition frequency can include the camera taking a picture every two seconds, the depth sensor scanning depth information every five seconds, etc.

[0149] The acquisition effect can characterize the degree to which the acquisition content 613 obtained by the acquisition module 210 based on the corresponding acquisition frequency reflects information such as the completion situation or completion quality of the target operation. The acquisition effect can be represented by a numerical value or a level, etc. For example, the larger the numerical value, the more sufficient and comprehensive the acquisition content reflects information such as the completion situation and completion quality of the target operation.

[0150] In some embodiments, the control module may train an acquisition effect evaluation model based on a large number of first training samples with a first label. The first training samples may include sample acquisition content, the sample acquisition frequency of the sample acquisition content, the sample target operation type, etc. The first label may be the actual acquisition effect at the sample acquisition frequency corresponding to the first training sample. The training process of the acquisition effect evaluation model is similar to that of the importance determination model. For specific details, please refer to the training description of the importance determination model.

[0151] In some embodiments, the control module may determine the actual acquisition effect corresponding to the first label in various ways. For example, the actual acquisition effect may be positively correlated with the number of problems that occur when collecting the acquisition data corresponding to the acquisition content of the collected sample and the severity of the problems. The severity can be represented by a numerical value. Among them, the number of problems and the severity can be determined by manually analyzing and annotating the problems that occur in the acquisition data during the subsequent actual acquisition process, including determining the number of problems therein, classifying the problems, and determining the severity scores corresponding to different types of problems. By accumulating the severity scores of all problems and the occurrence times of the corresponding problems, the actual acquisition effect corresponding to the first label can be obtained.

[0152] Exemplarily, the control module may determine the tolerance limit according to formula (1):

[0153]

[0154] where E is the actual acquisition effect corresponding to the first label, n is the total number of categories of various problems that occur when collecting the acquisition content corresponding to the first training sample, A i is the severity score corresponding to the i-th type of problem, and C i is the occurrence times of the i-th type of problem when collecting the acquisition content corresponding to the first training sample at the sample acquisition frequency.

[0155] In some embodiments, the control module 230 may determine the target acquisition frequency 630 based on the acquisition effects of candidate acquisition frequencies in various ways. Exemplarily, the control module may use the candidate acquisition frequency with the largest acquisition effect value among the acquisition effects of candidate acquisition frequencies as the target acquisition frequency, indicating that collecting data at the target acquisition frequency can most reflect the problems that occur during the operation process.

[0156] By using the acquisition effect evaluation model to evaluate the acquisition effects of candidate acquisition frequencies and determining the finally adopted acquisition frequency, the acquisition performances of different candidate acquisition frequencies can be evaluated more precisely, and the best target acquisition frequency can be selected accordingly to achieve a balance between acquisition efficiency and acquisition quality.

[0157] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification, so such modifications, improvements, and corrections still fall within the spirit and scope of the exemplary embodiments of this specification.

[0158] At the same time, this specification uses specific terms to describe the embodiments of this specification. Such as "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that the "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0159] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences, the use of numerical letters, or the use of other names in this specification are not used to limit the order of the processes and methods in this specification. Although some currently considered useful embodiments of the invention are discussed through various examples in the above disclosure, it should be understood that such details only serve the purpose of illustration, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through software solutions, such as installing the described system on existing servers or mobile devices.

[0160] Similarly, it should be noted that, in order to simplify the expression of the disclosure of this specification and thus help the understanding of one or more embodiments of the invention, in the previous description of the embodiments of this specification, sometimes multiple features are grouped into one embodiment, drawing, or description thereof. However, this disclosure method does not mean that the features required by the object of this specification are more than those mentioned in the claims. In fact, the features of the embodiments are less than all the features of the individual embodiments disclosed above.

[0161] In some embodiments, numbers are used to describe components and the quantity of attributes. It should be understood that such numbers used in the description of embodiments are, in some examples, modified by the modifiers "about", "approximately" or "substantially". Unless otherwise specified, "about", "approximately" or "substantially" indicate that the said numbers are allowed to have a variation of ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, and such approximate values may vary according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should consider the specified significant digits and adopt the method of retaining the general number of digits. Although the numerical ranges and parameters used in some embodiments of this specification to confirm the breadth of their scope are approximate values, in specific embodiments, such numerical settings are as precise as possible within the feasible range.

[0162] For each patent, patent application, patent application publication, and other materials cited in this specification, such as articles, books, specifications, publications, documents, etc., their entire contents are hereby incorporated into this specification by reference. This excludes the application history documents that are inconsistent with or conflict with the content of this specification, as well as the documents (currently or subsequently attached to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if there are inconsistencies or conflicts between the descriptions, definitions, and / or uses of terms in the supplementary materials of this specification and the content described in this specification, the descriptions, definitions, and / or uses of terms in this specification shall prevail.

[0163] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered to be consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

[0164] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are proposed in this specification, so such modifications, improvements, and corrections still fall within the spirit and scope of the exemplary embodiments of this specification.

[0165] In the meantime, this specification uses specific terms to describe the embodiments of this specification. For example, "an embodiment", "one embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "an embodiment" or "one embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0166] In addition, unless clearly stated in the claims, the order of the processing elements and sequences, the use of numerical letters, or the use of other names in this specification are not used to limit the order of the processes and methods in this specification. Although some currently considered useful embodiments of the invention are discussed through various examples in the above disclosure, it should be understood that such details only serve the purpose of illustration. The appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through software solutions, such as installing the described system on existing servers or mobile devices.

[0167] Similarly, it should be noted that, in order to simplify the expression of the disclosure in this specification and thus help the understanding of one or more embodiments of the invention, in the previous description of the embodiments of this specification, sometimes multiple features are grouped into one embodiment, drawing, or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than those mentioned in the claims. In fact, the features of the embodiments are fewer than all the features of the individual embodiments disclosed above.

[0168] In some embodiments, numbers are used to describe the components and the quantity of attributes. It should be understood that such numbers used for the description of embodiments are modified by the modifiers "about", "approximate", or "substantially" in some examples. Unless otherwise stated, "about", "approximate", or "substantially" indicate that the said numbers allow a variation of ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, and such approximate values can change according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should consider the specified significant digits and adopt the method of retaining the general number of digits. Although the numerical ranges and parameters used to confirm the breadth of the scope in some embodiments of this specification are approximate values, in specific embodiments, such numerical settings are as precise as possible within the feasible range.

[0169] For each patent, patent application, published patent application, and other materials cited in this specification, such as articles, books, specifications, publications, documents, etc., their entire contents are hereby incorporated by reference into this specification. This does not include application history files that are inconsistent with or conflict with the content of this specification, nor does it include files that limit the broadest scope of the claims of this specification (currently or subsequently appended to this specification). It should be noted that if there are any inconsistencies or conflicts between the descriptions, definitions, and / or uses of terms in the supplementary materials of this specification and the content described in this specification, the descriptions, definitions, and / or uses of terms in this specification shall prevail.

[0170] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered to be consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A process management system, comprising: An acquisition module, configured to obtain process information of an operator completing a target operation, where the process information is configured to reflect the completion situation of the operator for the target operation; A storage module, configured to match a time stamp to the process information collected by the acquisition module and store the process information with the time stamp.

2. The system according to claim 1, where the storage module is further configured to: Determine a key time point corresponding to the process information; Based on the key time point, match the time stamp to the process information.

3. The system according to claim 1, where the process information includes video information; The storage module is further configured to: Based on the video information, determine key video frames; Match the time stamp to the key video frames.

4. The system according to claim 1, where the storage module is further configured to: store the process information with the time stamp into a blockchain.

5. The system according to claim 4, where the storage module is further configured to: Perform consistency verification on the process information with the time stamp; In response to the process information passing the consistency verification, store the process information into the blockchain.

6. The system according to claim 5, where the process information includes image information and sound information; The consistency verification includes: Based on the image information, determine first detection information; Based on the sound information, determine second detection information; In response to the first detection information and the second detection information meeting a preset detection condition, determine that the process information passes the consistency verification.

7. The system according to claim 6, where the process information further includes video information; The storage module is further configured to: In response to the process information not passing the consistency verification, perform auxiliary verification on the process information based on the video information; In response to the process information passing the auxiliary verification, store the process information into the blockchain.

8. The system according to claim 7, where the auxiliary verification includes: Based on the video information, determine whether a preset operation when the operator completes the target operation meets preset operation requirements; In response to not meeting the preset operation requirements, prompt to re - complete the preset operation; In response to meeting the preset operation requirements, based on the video information, obtain third detection information; Determine whether the third detection information and the second detection information meet the preset detection condition; In response to meeting the preset detection condition, determine that the process information passes the auxiliary verification.

9. The system according to claim 4, where the acquisition module includes an acquisition unit and an analysis unit; the analysis unit is configured to generate the process information based on the information collected by the acquisition unit; The storage module is further configured to: determine the task completion situation based on the process information and store the task completion situation into the blockchain.

10. A process management device, comprising an input device, a recording device, and a processor; The input device is configured to collect the time information of the operator completing the target operation; The recording device is configured to collect the process information of the operator completing the target operation; The processor is configured to: Obtain the process information; Match a timestamp to the process information and store the process information with the timestamp.

Images