Detection report tracing method based on image recognition

Abstract

The invention discloses a detection report traceability method based on image recognition, and relates to the technical field of image recognition, and the method comprises the steps: generating a product two-dimensional code label of a to-be-detected product, scanning a code to obtain initial record information of the product, creating a collection timestamp, shooting a code scanning process to obtain collection video information, and storing the collection video information in a database; creating an initial node of a traceability chain based on the product two-dimensional code label, the product initial record information and the collected video information; setting circulation information of the to-be-detected product is determined according to the technological process information of the to-be-detected product, a plurality of product circulation nodes of a feature traceability chain are created, real-time circulation record information of the to-be-detected product is detected, the real-time circulation record information and the setting circulation information are compared to judge whether abnormity exists or not, and circulation abnormity information is recorded if abnormity exists; full-process shooting is carried out on a to-be-detected product to obtain full-process video information, and detection is carried out based on the environment sensing integration module to obtain environment detection parameter information. The method and the device have the effect of improving the working efficiency of detection report traceability based on image recognition.

Description

Technical Field

[0001] This application relates to the field of image recognition technology, and in particular to a method for tracing the source of detection reports based on image recognition. Background Technology

[0002] Currently, consumers are most concerned about whether products are genuine when shopping. On the one hand, counterfeiting, knowingly selling counterfeit goods, and other illegal activities are rampant in the market; on the other hand, products from reputable companies are being counterfeited, and the source of counterfeit products cannot be detected and determined in a timely manner, thus harming the legitimate interests of these companies. Test report traceability is a systematic management method that ensures the authenticity, reliability, and reproducibility of test results by recording and tracking key information during the testing process. Product traceability systems are production control systems that can track products forward, backward, and non-directionally, and are widely used in various fields. Therefore, test report traceability based on image recognition is crucial.

[0003] Existing image recognition-based traceability methods for inspection reports involve capturing images of the product, extracting and parsing key information, associating and storing the data, generating an inspection report, and then using the inspection report to verify the product's origin. However, existing methods do not consider the temporal consistency of various product data or anomalies during the product's circulation process, affecting the transparency and security of inspection report traceability. This results in low efficiency for image recognition-based inspection report traceability and warrants improvement. Summary of the Invention

[0004] To improve the efficiency of image recognition-based detection report tracing, this application provides an image recognition-based detection report tracing method.

[0005] Firstly, this application provides a method for tracing the source of detection reports based on image recognition, which adopts the following technical solution:

[0006] A method for tracing the source of detection reports based on image recognition includes the following steps:

[0007] Step S1: Generate a product QR code label for the product to be tested, scan the product QR code label of the product to be tested and collect and record the initial record information of the product, and create a collection timestamp. Capture the scanning process in real time to obtain the collection video information. Based on the product QR code label, the initial record information of the product and the collection video information, obtain the product collection data, and then create the initial node of the traceability chain. Upload the traceability chain to the blockchain system.

[0008] Step S2: During the flow of the product under test, determine the set flow information of the product under test according to the process flow information of the product under test, create multiple product flow nodes of the feature traceability chain, detect the real-time flow record information of the product under test, compare the real-time flow record information with the set flow information, determine whether there is abnormal flow, and if so, record the flow abnormal information.

[0009] Step S3: Capture the entire process of the product under test to obtain full-process video information, create and detect environmental detection parameter information based on the environmental sensing integration module, and combine the full-process video information and environmental detection parameter information to determine whether there is any abnormality in the environment during the flow process. If there is an abnormality, record the environmental abnormality information.

[0010] Step S4: Combining abnormal flow information and abnormal environment information to form abnormal product tracking information; collecting relevant staff information for each product flow node; fusing real-time flow record information, full-process video information, abnormal product tracking information, and relevant staff information; marking and recording the data in the corresponding product flow node of the feature traceability chain; updating the feature traceability chain in real time and uploading it to the blockchain system.

[0011] Step S5: Create a dynamic feature code for the product to be tested and generate a time-series feature QR code based on the feature traceability chain; generate a product test report based on the feature traceability chain; bind the product test report with the dynamic feature code; encrypt the dynamic feature code; scan the time-series feature QR code to verify the authenticity of the product test report and trace the historical version of the product test report; record user query traceability information and upload it to the blockchain system.

[0012] Step S6: Send the feature tracing chain and the user query tracing information to the background monitoring system.

[0013] Preferably, the basic information of the product to be tested is obtained, including product type information and product ID information;

[0014] Generate a product QR code label for the product to be tested based on the product type information and the product ID information;

[0015] The product QR code label of the product to be tested is scanned, and the relevant parameters of the scanning process are collected and recorded to obtain the initial record information of the product to be tested. The initial record information includes the information of the collector, the collection time, and the collection location.

[0016] The timestamp for scanning the product QR code label of the product to be tested is created based on the collection time information; that is, the collection timestamp.

[0017] Preferably, the scanning and recording process of the product under test is captured in real time to obtain the video information of the product under test;

[0018] The product QR code label of the product under test, the initial record information of the product under test, and the collected video information of the product under test are time-series aligned. After the time-series alignment is completed, the data is fused to obtain the product collection data. Based on the product collection data, an initial node of the feature traceability chain is created, and the collection timestamp is marked and displayed on the initial node of the feature traceability chain.

[0019] The feature traceability chain is uploaded to the blockchain system for storage.

[0020] Preferably, the process flow information of the product under test is obtained, the product flow nodes of the product under test are determined based on the process flow information of the product under test, and the set flow information of the product under test is determined based on the process flow information of the product under test.

[0021] Based on the implementation priority of each process in the process flow information of the product under test, the occurrence priority of the product flow node of the product under test is determined to obtain the node occurrence priority information.

[0022] Based on the product flow nodes and node occurrence priority information of the product under test, multiple product flow nodes of the feature traceability chain are created sequentially.

[0023] The product under test is located in real time to obtain real-time location information. The real-time location time is recorded to obtain product location time information. Based on the real-time location information, the movement path of the product under test at each circulation node is identified to obtain product dynamic path information at each circulation node. The real-time location information, product location time information, and product dynamic path information are combined to form real-time circulation record information of the product under test.

[0024] The set flow information of the product under test is compared with the real-time flow record information of the product under test to determine whether there is an anomaly. If there is an anomaly, the flow anomaly determination result is output and the flow anomaly information is recorded.

[0025] Preferably, the entire process of the product under test is filmed to obtain full-process video information of the product under test;

[0026] Based on the occurrence time of the entire process of the product under test, timestamps at different times in each node are created to obtain the process node timestamps;

[0027] Based on the set flow information of the product under test, the full-process video information is segmented to obtain the sub-flow video information of each product flow node. The sub-flow video information includes multiple video frame images.

[0028] Based on the product type of the product to be tested, the testing items for the environment in which the product to be tested is located are determined to obtain the environmental testing items;

[0029] An environmental sensing integration module is created based on the environmental monitoring project. The environmental sensing integration module is moved based on the real-time location information of the product under test. The environmental sensing integration module tracks and detects the product under test to obtain environmental monitoring parameter information.

[0030] The environmental detection parameter information and the video frame images in the sub-stream video information of the corresponding streaming node are time-aligned, and the environmental timing alignment signal is output after completion.

[0031] Upon receiving the environmental timing alignment signal, the system combines the environmental detection parameter information with the video frame images in the sub-transfer video information of the corresponding transfer node to determine whether there is an anomaly in the environment of the product under test. If there is an anomaly, the system outputs the environmental anomaly determination result and records the environmental anomaly information.

[0032] Preferably, the abnormal flow information and the abnormal environmental information are combined to form the product tracking abnormal information of the product under test;

[0033] Based on the video frame images in the sub-transfer video information of each product transfer node, the relevant transfer personnel of each product transfer node are statistically analyzed to obtain the relevant staff information of each product transfer node;

[0034] The real-time flow record information of the product under test, the sub-flow video information of each product flow node, the product tracking anomaly information of the product under test, and the relevant personnel information of each product flow node are time-series aligned. After the time-series alignment is completed, the data is fused to obtain the product flow data of each product flow node. The product flow data of each product flow node is recorded and stored in the corresponding product flow node of the feature traceability chain.

[0035] The system monitors in real time whether the feature traceability chain has changed. If a change is found, the updated feature traceability chain is synchronously uploaded to the blockchain system.

[0036] Preferably, dynamic feature codes are created based on the data in each node of the feature tracing chain and the timestamps of the process nodes. It should be noted that the dynamic feature codes in this application embodiment are unique and the dynamic code features at different times are inconsistent.

[0037] Generate time-series feature QR codes for the products under test based on dynamic feature encoding;

[0038] Based on the data in each node of the feature traceability chain, a product testing report is generated in real time, resulting in multiple versions of the product testing report for the product under test.

[0039] Based on the process node timestamp, the product test report of each version of the product under test is bound to the dynamic feature code under the corresponding time sequence. After the binding is completed, a report binding completion signal is output.

[0040] Upon receiving the report binding completion signal, the dynamic coding features of the product under test are encrypted using an encrypted hash algorithm. Scanning the time-series feature QR code can verify the authenticity of the product test report and trace the historical versions of the product test report.

[0041] Record user query traceability information and upload the user query traceability information to the blockchain system.

[0042] Preferably, a wireless communication module is acquired and a signal connection link is established between the wireless communication module and the product under test;

[0043] Obtain the feature tracing chain and the user query tracing information and cache them;

[0044] The feature tracing chain and the user query tracing information are sent to the background monitoring system based on the wireless communication module.

[0045] In summary, this application includes at least one of the following beneficial technical effects:

[0046] By generating and scanning a product QR code label for the product under test, initial product record information is obtained. A collection timestamp is created, and video information of the scanning process is captured. Based on the product QR code label, initial product record information, and video information, an initial node of the traceability chain is created. Multiple product flow nodes of the feature traceability chain are created based on the process flow information of the product under test. The real-time flow record information of the product under test is detected, and any flow anomalies are identified. If an anomaly is found, the flow anomaly information is recorded. Combined with video image analysis and environmental sensor detection, any environmental anomalies during the flow process are identified. If an anomaly is found, the environmental anomaly information is recorded. The flow anomaly information and environmental anomaly information are combined to form product tracking anomaly information. Information on relevant personnel at each product flow node is collected. The real-time flow record information and the full-process video information are integrated. Product tracking anomaly information and related personnel information are marked on the corresponding product flow nodes of the feature traceability chain. The feature traceability chain is updated in real time and synchronously uploaded to the blockchain system, improving the transparency of image recognition-based test report traceability and thus improving the efficiency of image recognition-based test report traceability. Dynamic feature codes are created for the products to be tested and time-series feature QR codes are generated. Multiple versions of product test reports are generated based on the feature traceability chain, and the product test reports are bound to the dynamic feature codes. The dynamic feature codes are encrypted, and the time-series feature QR codes are scanned to verify the authenticity of the product test reports and trace the historical versions of the product test reports. User query traceability information is recorded, further improving the transparency of image recognition-based test report traceability and thus further improving the efficiency of image recognition-based test report traceability. Attached Figure Description

[0047] Figure 1 This embodiment mainly illustrates the process of the detection report tracing method based on image recognition. Detailed Implementation

[0048] The present application will be further described in detail below with reference to the accompanying drawings.

[0049] This application discloses a method for tracing the source of detection reports based on image recognition.

[0050] A method for tracing the source of detection reports based on image recognition includes the following steps:

[0051] Reference Figure 1 Step S1 involves generating a product QR code label for the product to be tested, scanning the product QR code label to collect and record initial product information, creating a collection timestamp, and capturing video footage of the scanning process in real time. Based on the product QR code label, initial product information, and video footage, product data is obtained, and an initial node for the traceability chain is created. The traceability chain is then uploaded to the blockchain system. Step S1 specifically includes the following sub-steps:

[0052] Step S11: Obtain the basic information of the product to be tested. The basic information of the product to be tested includes product type information and product ID information.

[0053] Step S12: Generate a product QR code label for the product to be tested based on the product type information and product ID information. The product ID information is unique, therefore the product QR code label for the product to be tested is also unique.

[0054] Step S13: The collector scans the product QR code label of the product to be tested using a mobile scanning device, and collects and records the relevant parameters of the scanning process to obtain the initial record information of the product to be tested. The initial record information includes the collector's information, the collection time information, and the collection location information.

[0055] Step S14: Create a timestamp for scanning the product QR code label of the product to be tested based on the collection time information, i.e., the collection timestamp.

[0056] Step S15: Acquire the camera and establish a signal connection link between the camera and the product under test. Based on the scanning and recording process of the product under test by the camera, capture video information of the product under test in real time.

[0057] Step S16: Time-series alignment of the product QR code label of the product under test, the initial record information of the product under test, and the collected video information of the product under test. After time-series alignment, data fusion is performed to obtain product collected data. Based on the product collected data, an initial node of the feature traceability chain is created, and the collection timestamp is marked and displayed at the initial node of the feature traceability chain.

[0058] Step S17: Upload the feature traceability chain to the blockchain system for storage.

[0059] Reference Figure 1 Step S2 involves determining the set flow information of the product under test based on its process flow information during the product's transfer process. Multiple product transfer nodes are created in the feature traceability chain. The real-time transfer record information of the product under test is detected, and compared with the set flow information to determine if any abnormal transfer occurs. If so, the abnormal transfer information is recorded. Step S2 specifically includes the following sub-steps:

[0060] Step S21: Obtain the process flow information of the product under test, determine the product flow nodes of the product under test based on the process flow information, and determine the set flow information of the product under test based on the process flow information. The set flow information of the product under test includes the product flow time range, product flow location area, and product flow set path at each product flow node.

[0061] Step S22: Based on the implementation priority of each process flow in the process flow information of the product under test, determine the occurrence priority of the product flow node of the product under test to obtain the node occurrence priority information.

[0062] Step S23: Based on the product flow nodes and node occurrence priority information of the product to be tested, create multiple product flow nodes of the feature traceability chain in sequence.

[0063] Step S24: Real-time positioning of the product under test is performed to obtain real-time location information of the product, and real-time positioning time is recorded to obtain product positioning time information. Based on the real-time location information of the product, the movement path of the product under test at each circulation node is identified to obtain product dynamic path information at each circulation node. The real-time location information of the product, the product positioning time information, and the product dynamic path information are combined to form the real-time circulation record information of the product under test.

[0064] Step S25: Compare the set flow information of the product under test with the real-time flow record information of the product under test to determine whether there is an abnormality. If there is an abnormality, output the flow abnormality judgment result and record the flow abnormality information.

[0065] Specifically, the first type of flow information comparison result is obtained by comparing the product flow location area of ​​each product flow node with the real-time product location information; the second type of flow information comparison result is obtained by comparing the product flow time range of each product flow node with the product positioning time information; and the third type of flow information comparison result is obtained by comparing the product flow set path of each product flow node with the product dynamic path information.

[0066] If the real-time location information of the product is not located within the product circulation location area in the first type of circulation information comparison results, then the first type of circulation anomaly result will be output.

[0067] If the product location time information is not within the product circulation time range in the comparison results of the second type of circulation information, then the second type of circulation abnormal result will be output.

[0068] If the product dynamic path information is inconsistent with the product flow setting path in the comparison results of the third type of flow information, the third type of flow abnormal result will be output.

[0069] When a first, second, or third type of abnormal flow result is received, it is determined that there is an abnormality in the flow of the product under test. The abnormal flow result is output, and the abnormal flow information of the product under test is recorded. The abnormal flow information of the product under test includes the abnormal flow node, the abnormal flow time information, and the abnormal flow location information.

[0070] Reference Figure 1Step S3 involves capturing the entire process of the product under test to obtain full-process video information. Environmental detection parameters are then created and obtained based on the environmental sensing integration module. Combining the full-process video information and the environmental detection parameters, it is determined whether there are any anomalies in the environment during the process. If an anomaly is found, the environmental anomaly information is recorded. Step S3 specifically includes the following sub-steps:

[0071] Step S31: Obtain full-process video information of the product under test by capturing the entire process of the product under test using a camera.

[0072] Step S32: Based on the occurrence time of the entire process of the product under test, create timestamps for different moments in each node to obtain process node timestamps.

[0073] Step S33: Based on the set flow information of the product under test, the full-process video information is segmented to obtain the sub-flow video information of each product flow node. The sub-flow video information includes multiple video frame images.

[0074] Step S34: Based on the product type of the product to be tested, determine the testing items for the environment in which the product to be tested is located to obtain the environmental testing items.

[0075] Step S35: Create an environmental sensing integration module based on the environmental monitoring project. Move the environmental sensing integration module based on the real-time location information of the product under test. The environmental sensing integration module tracks and detects the product under test to obtain environmental monitoring parameter information.

[0076] Step S36: Perform time-series alignment of the environmental detection parameter information and the video frame images in the sub-stream video information of the corresponding streaming node, and output the environmental time-series alignment signal after completion.

[0077] Step S37: Upon receiving the environmental timing alignment signal, the system combines the environmental detection parameter information and the video frame images in the sub-transfer video information of the corresponding transfer node to determine whether there is an anomaly in the environment of the product under test. If an anomaly is found, the system outputs the environmental anomaly determination result and records the environmental anomaly information. The environmental anomaly information includes the type and location of the environmental anomaly.

[0078] Reference Figure 1 Step S4 involves combining abnormal flow information and environmental abnormality information to form product tracking abnormality information. Information on relevant personnel at each product flow node is collected. Real-time flow records, full-process video information, product tracking abnormality information, and relevant personnel information are fused and marked in the corresponding product flow node of the feature traceability chain. The feature traceability chain is updated in real time and uploaded to the blockchain system. Step S4 specifically includes the following sub-steps:

[0079] Step S41: The abnormal flow information and the abnormal environment information are combined to form the product tracking abnormal information of the product under test.

[0080] Step S42: Based on the video frame images in the sub-transfer video information of each product transfer node, statistical analysis is performed on the relevant transfer personnel of each product transfer node to obtain the relevant staff information of each product transfer node.

[0081] Step S43: The real-time flow record information of the product under test, the sub-flow video information of each product flow node, the product tracking anomaly information of the product under test, and the relevant personnel information of each product flow node are time-series aligned. After the time-series alignment is completed, the data is fused to obtain the product flow data of each product flow node. The product flow data of each product flow node is recorded and stored in the corresponding product flow node of the feature traceability chain.

[0082] Step S44: Real-time detection of whether the feature traceability chain has changed. If it has changed, the updated feature traceability chain is synchronously uploaded to the blockchain system.

[0083] Reference Figure 1 Step S5 involves creating a dynamic feature code for the product under test based on the feature traceability chain and generating a time-series feature QR code. Multiple versions of the product testing report are generated based on the feature traceability chain. The product testing report is then bound to the dynamic feature code, which is encrypted. The time-series feature QR code is scanned to verify the authenticity of the product testing report and trace its historical versions. User query traceability information is recorded and uploaded to the blockchain system. Step S5 specifically includes the following sub-steps:

[0084] Step S51: Based on the data in each node of the feature traceability chain and the timestamp of the process node, a dynamic feature code is created. It should be noted that the dynamic feature code in this application embodiment is unique and the dynamic code features at different times are inconsistent.

[0085] Step S52: Generate a time-series feature QR code for the product under test based on dynamic feature encoding.

[0086] Step S53: Based on the data in each node of the feature traceability chain, generate product testing reports in real time to obtain multiple versions of product testing reports for the product under test.

[0087] Step S54: Based on the process node timestamp, bind the product test report of each version of the product under test with the dynamic feature code under the corresponding time sequence, and output the report binding completion signal after the binding is completed.

[0088] Step S55: After receiving the report binding completion signal, the dynamic coding features of the product under test are encrypted using an encrypted hash algorithm. Scanning the time sequence feature QR code can verify the authenticity of the product test report and trace the historical versions of the product test report.

[0089] Step S56: Record the user's query traceability information and upload it to the blockchain system. The user's query traceability information includes the user's name, the authenticity of the query, and the version of the traceability report.

[0090] Reference Figure 1 Step S6 involves sending the feature tracing chain and user query tracing information to the backend monitoring system. Step S6 specifically includes the following sub-steps:

[0091] Step S61: Obtain the wireless communication module and establish a signal connection link between the wireless communication module and the product under test.

[0092] Step S62: Obtain the feature traceability chain and user query traceability information and perform caching processing.

[0093] Step S63: The feature traceability chain and user query traceability information are sent to the background monitoring system based on the wireless communication module. It should be noted that the wireless communication module in this embodiment can be a wireless communication module based on Bluetooth technology.

[0094] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A method for tracing the source of detection reports based on image recognition, characterized in that, Includes the following steps: Step S1: Generate a product QR code label for the product to be tested, scan the product QR code label to obtain the initial record information of the product, create a collection timestamp, record the scanning process to obtain the collection video information, and create the initial node of the traceability chain based on the product QR code label, the initial record information of the product, and the collection video information. Step S2: Determine the set flow information of the product under test based on the process flow information of the product under test, create multiple product flow nodes in the feature traceability chain, detect the real-time flow record information of the product under test, compare the real-time flow record information with the set flow information to determine whether there is an anomaly, and if there is an anomaly, record the flow anomaly information. Step S3: Capture the entire process of the product under test to obtain full-process video information, create and detect environmental detection parameter information based on the environmental sensing integration module, and combine the full-process video information and environmental detection parameter information to determine whether there is any abnormality in the environment during the flow process. If there is an abnormality, record the environmental abnormality information. Step S4: Combining abnormal flow information and abnormal environment information to form abnormal product tracking information, collecting relevant staff information at each product flow node, marking real-time flow record information, full-process video information, abnormal product tracking information and relevant staff information at the corresponding product flow node of the feature traceability chain, and updating the feature traceability chain in real time; Step S5: Create a dynamic feature code for the product to be tested and generate a time-series feature QR code. Generate multiple versions of the product test report based on the feature traceability chain. Bind the product test report to the dynamic feature code, encrypt the dynamic feature code, scan the time-series feature QR code to verify the authenticity of the product test report and trace the historical versions of the product test report, and record the user query traceability information. Step S6: Send the feature traceability chain and user query traceability information to the background monitoring system.

2. The method for tracing the source of detection reports based on image recognition according to claim 1, characterized in that, Step S1 specifically includes: Obtain basic information about the product to be tested, including product type information and product ID information; Generate a product QR code label for the product to be tested based on product type information and product ID information; The product QR code label of the product to be tested is scanned, and the relevant parameters of the scanning process are collected and recorded to obtain the initial record information of the product to be tested. The initial record information includes the information of the collector, the collection time, and the collection location. The timestamp for scanning the product QR code label of the product to be tested is created based on the collection time information; that is, the collection timestamp.

3. The method for tracing the source of detection reports based on image recognition according to claim 2, characterized in that, Step S1 also includes: The process of scanning and collecting data from the product under test is recorded in real time to obtain the collected video information of the product under test. The product QR code label, the initial record information, and the collected video information of the product under test are time-series aligned. After time-series alignment, the data is fused to obtain the product collection data. An initial node of the feature traceability chain is created based on the product collection data, and the collection timestamp is marked and displayed at the initial node of the feature traceability chain. The feature traceability chain is uploaded to the blockchain system for storage.

4. The method for tracing the source of detection reports based on image recognition according to claim 3, characterized in that, Step S2 specifically includes: Obtain the process flow information of the product under test, determine the product flow nodes of the product under test based on the process flow information of the product under test, and determine the set flow information of the product under test based on the process flow information of the product under test. Based on the implementation priority of each process in the process flow information of the product under test, the occurrence priority of the product flow node of the product under test is determined to obtain the node occurrence priority information. Based on the product flow nodes and node occurrence priority information of the product under test, multiple product flow nodes of the feature traceability chain are created sequentially. The product under test is located in real time to obtain real-time location information. The real-time location time is recorded to obtain product location time information. Based on the real-time location information, the movement path of the product under test at each circulation node is identified to obtain product dynamic path information at each circulation node. The real-time location information, product location time information, and product dynamic path information are combined to form real-time circulation record information of the product under test. The set flow information of the product under test is compared with the real-time flow record information of the product under test to determine whether there is an anomaly. If there is an anomaly, the flow anomaly determination result is output and the flow anomaly information is recorded.

5. The method for tracing the source of detection reports based on image recognition according to claim 4, characterized in that, Step S3 specifically includes: The entire process of the product under test is captured to obtain full-process video information of the product under test; Based on the occurrence time of the entire process of the product under test, timestamps at different times in each node are created to obtain the process node timestamps; Based on the set flow information of the product under test, the full-process video information is segmented to obtain the sub-flow video information of each product flow node. The sub-flow video information includes multiple video frame images. Based on the product type of the product to be tested, the testing items for the environment in which the product to be tested is located are determined to obtain the environmental testing items; An environmental sensing integration module is created based on the environmental monitoring project. The environmental sensing integration module is moved based on the real-time location information of the product under test. The environmental sensing integration module tracks and detects the product under test to obtain environmental monitoring parameter information. The environmental detection parameter information and the video frame images in the sub-stream video information of the corresponding streaming node are time-aligned, and the environmental timing alignment signal is output after completion. Upon receiving the environmental timing alignment signal, the system combines the environmental detection parameter information and the video frame images in the sub-transfer video information of the corresponding transfer node to determine whether there is an anomaly in the environment of the product under test. If there is an anomaly, the system outputs the environmental anomaly determination result and records the environmental anomaly information.

6. The method for tracing the source of detection reports based on image recognition according to claim 5, characterized in that, Step S4 specifically includes: The combination of abnormal flow information and abnormal environmental information forms the product tracking abnormality information of the product under test. Based on the video frame images in the sub-transfer video information of each product transfer node, the relevant transfer personnel of each product transfer node are statistically analyzed to obtain the relevant staff information of each product transfer node; The real-time flow record information of the product under test, the sub-flow video information of each product flow node, the product tracking anomaly information of the product under test, and the relevant personnel information of each product flow node are aligned in time sequence. After completion, the data is fused to obtain the product flow data of each product flow node. The product flow data of each product flow node is recorded and stored at the corresponding product flow node in the feature traceability chain. The system monitors in real time whether the feature traceability chain has changed. If a change is found, the updated feature traceability chain is synchronously uploaded to the blockchain system.

7. The method for tracing the source of detection reports based on image recognition according to claim 6, characterized in that, Step S5 specifically includes: Based on the data and process node timestamps in each node of the feature traceability chain, dynamic feature codes are created. It should be noted that the dynamic feature codes in this application embodiment are unique and the dynamic code features at different times are inconsistent. Generate time-series feature QR codes for the products under test based on dynamic feature encoding; Based on the data in each node of the feature traceability chain, a product testing report is generated in real time, resulting in multiple versions of the product testing report for the product under test. Based on the process node timestamp, the product test report of each version of the product under test is bound to the dynamic feature code under the corresponding time sequence. After the binding is completed, a report binding completion signal is output. Upon receiving the report binding completion signal, the dynamic coding features of the product under test are encrypted using an encrypted hash algorithm. Scanning the time-series feature QR code can verify the authenticity of the product test report and trace the historical versions of the product test report. Record user query traceability information and upload the user query traceability information to the blockchain system.

8. The method for tracing the source of detection reports based on image recognition according to claim 7, characterized in that, Step S6 specifically includes: Acquire the wireless communication module and establish a signal connection link between the wireless communication module and the product under test; Obtain the feature tracing chain and the user query tracing information and cache them; The feature tracing chain and the user query tracing information are sent to the background monitoring system based on the wireless communication module.

Images