SMT-AI multi-device collaborative data interaction and re-judgment method and device based on intelligent interconnection

Abstract

The invention relates to an SMT-AI multi-device collaborative data interaction and re-judgment method and device based on intelligent interconnection. The method comprises the following steps: acquiring related detection data of a mounted PCB (Printed Circuit Board); the detection data comes from the AOI equipment used for STM production line detection and connected with the service rule management system; sending the detection data to an AI re-judgment server; receiving a re-judgment result given by the AI re-judgment server for the detection data, and making a decision instruction according to the re-judgment result; wherein the AI re-judgment server is connected with a plurality of service rule management systems in a parallel communication mode. The AI re-judgment server is applied to the SMT production line, the detection data collected by the AOI equipment is re-judged, the requirement for re-judgment of large-scale production line detection data can be met, and through parallel communication with the service rule management system, the expansibility of the system is improved, and the maintenance difficulty of the system is reduced.

Description

Technical Field

[0001] The present application relates to the field of printed circuit board surface mounting technology, and in particular to a method and apparatus for SMT-AI multi-device collaborative data interaction and re-judgment based on intelligent interconnection. Background Art

[0002] In the modern electronic manufacturing industry, SMT (Surface Mounted Technology) equipment is widely used to accurately mount electronic components on printed circuit boards (PCBs).

[0003] However, defects are inevitable during the production process, such as component position deviation, poor soldering, etc. In order to ensure product quality, AOI (Automated Optical Inspection) equipment is usually used to inspect the mounted circuit boards, and the inspection results are sent to operators for further manual verification and corresponding operations.

[0004] However, as the scale of production expands, the above-mentioned defect inspection method may be unable to cope with the data processing requirements of a large number of devices. Summary of the invention

[0005] Based on this, it is necessary to provide a SMT-AI multi-device collaborative data interaction and re-judgment method and device based on intelligent interconnection to address the above technical problems.

[0006] In the first aspect, the present application provides a SMT-AI multi-device collaborative data interaction and re-judgment method based on intelligent interconnection, which is applied to a business rule management system. The method includes:

[0007] Obtain relevant inspection data of the mounted PCB board; the inspection data comes from the AOI equipment used for STM production line inspection connected to the business rule management system;

[0008] Send the detection data to the AI ​​re-judgment server;

[0009] Receive the re-judgment results given by the AI ​​re-judgment server for the test data, and make decision instructions based on the re-judgment results;

[0010] Among them, the AI ​​re-judgment server is connected to multiple business rule management systems in parallel communication mode.

[0011] In one embodiment, sending the detection data to the AI ​​re-judgment server includes:

[0012] The test data is packaged into a JSON format data packet; the JSON format data packet includes the STM production line identification, the equipment identification in the STM production line, the timestamp, the PCB board information and the re-judgment result;

[0013] Send the JSON format data packet to the AI ​​review server via a POST request.

[0014] In one embodiment, the AI ​​re-judgment server uses a two-way communication mechanism to connect to the client;

[0015] Sending the detection data to the AI ​​re-judgment server includes:

[0016] Forward the detection data to the AI ​​re-judgment server through the client;

[0017] The re-judgment results given by the AI ​​re-judgment server for the detection data include:

[0018] Receive the re-judgment result given by the AI ​​re-judgment server and forwarded by the client.

[0019] In one embodiment, a data confirmation and retransmission mechanism is used between the AI ​​re-judgment server and the client for data transmission.

[0020] In one embodiment, sending the detection data to the AI ​​re-judgment server includes:

[0021] According to the real-time workload of the STM production line, the frequency of sending detection data and the connection status with the AI ​​re-judgment server are dynamically adjusted, and a load balancing algorithm is used to dynamically distribute detection data to the AI ​​re-judgment server.

[0022] In the second aspect, the present application also provides an SMT-AI multi-device collaborative data interaction and re-judgment method based on intelligent interconnection, which is applied to an AI re-judgment server, and the AI ​​re-judgment server is connected to multiple business rule management systems in a parallel communication manner, and the method includes:

[0023] Receiving the inspection data acquired by the business rule management system; wherein the inspection data comes from the AOI equipment for STM production line inspection connected to the business rule management system;

[0024] A re-judgment result is given in response to the detection data, and the re-judgment result is sent to the business rule management system so that the business rule management system can make a decision instruction based on the re-judgment result.

[0025] In the third aspect, the present application also provides an SMT-AI multi-device collaborative data interaction and re-judgment device based on intelligent interconnection. The device includes a business rule management system and an AI re-judgment server, and the AI ​​re-judgment server is connected to multiple business rule management systems in a parallel communication mode;

[0026] Among them, the business rule management system is used to obtain the relevant inspection data of the PCB board that has been mounted; the inspection data comes from the AOI equipment for STM production line inspection connected to the business rule management system; the inspection data is sent to the AI ​​re-judgment server; the re-judgment results given by the AI ​​re-judgment server for the inspection data are received, and decision instructions are made according to the re-judgment results;

[0027] The AI ​​re-judgment server is used to receive the detection data obtained by the business rule management system; give a re-judgment result in response to the detection data, and send the re-judgment result to the business rule management system so that the business rule management system can make decision instructions based on the re-judgment result.

[0028] In a fourth aspect, the present application also provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps in the above-mentioned SMT-AI multi-device collaborative data interaction and re-judgment method based on intelligent interconnection when executing the computer program.

[0029] In a fifth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned SMT-AI multi-device collaborative data interaction and re-judgment method based on intelligent interconnection are implemented.

[0030] In a sixth aspect, the present application also provides a computer program product. The computer program product includes a computer program, which, when executed by a processor, implements the steps in the above-mentioned SMT-AI multi-device collaborative data interaction and re-judgment method based on intelligent interconnection.

[0031] The above-mentioned SMT-AI multi-device collaborative data interaction and re-judgment method and device based on intelligent interconnection are applied to the business rule management system, and the method includes: obtaining the relevant detection data of the PCB board that has been mounted; the detection data comes from the AOI equipment for STM production line detection connected to the business rule management system; sending the detection data to the AI ​​re-judgment server; receiving the re-judgment results given by the AI ​​re-judgment server for the detection data, and making decision instructions based on the re-judgment results; wherein the AI ​​re-judgment server is connected to multiple business rule management systems in a parallel communication mode. The present invention applies the AI ​​re-judgment server on the SMT production line to re-judge the detection data collected by the AOI equipment, which can meet the needs of re-judgment of large-scale production line detection data, and through parallel communication with the business rule management system, it improves the scalability of the system and reduces the difficulty of system maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a flowchart of a SMT-AI multi-device collaborative data interaction and re-judgment method based on intelligent interconnection in one embodiment;

[0033] Figure 2 The present invention is a structural block diagram of an SMT-AI multi-device collaborative data interaction and re-judgment device based on intelligent interconnection in one embodiment. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0035] The embodiment of the present application provides an SMT-AI multi-device collaborative data interaction and re-judgment method based on intelligent interconnection, which is applied to a business rule management system, including the following steps:

[0036] Step 102, obtaining relevant inspection data of the mounted PCB board; the inspection data comes from the AOI equipment for STM production line inspection connected to the business rule management system;

[0037] Step 104, sending the detection data to the AI ​​re-judgment server;

[0038] Step 106, receiving the re-judgment result given by the AI ​​re-judgment server for the detection data, and making a decision instruction according to the re-judgment result.

[0039] Among them, the AI ​​re-judgment server is connected to multiple business rule management systems in parallel communication mode.

[0040] In this embodiment, the business rules management (BRM) system generally refers to a system used to manage and apply various business rules and logics in the inspection process. It mainly undertakes the following tasks: defining the standards and parameters for whether a product is qualified or not, such as dimensional tolerances, surface defects, etc.; managing the inspection process, including when to conduct inspections and how to handle inspection results; analyzing the inspection results, generating reports and statistical data for improving production processes and quality control; automating subsequent decisions based on the inspection results and preset business rules, such as whether to continue production or rework.

[0041] In step 102, each SMT device inspects the PCB board through the AOI device and collects production data in real time, including the specific location of the component, the number of the PCB board, the inspection results (such as whether the component is mounted normally and whether the solder joint is qualified), etc. After these data are preliminarily processed, a standardized data package containing the device ID, production line information and inspection results is generated.

[0042] In step 104, the AI ​​(Artificial Intelligence) review server refers to an artificial intelligence system used in the production and quality control process, whose main function is to review and verify the preliminary test results of automatic inspection equipment (such as automatic optical inspection equipment AOI, X-ray inspection equipment, etc.). These AI review servers usually combine technologies such as machine learning, deep learning, and computer vision to improve the accuracy and reliability of detection. The AI ​​review server is used to review the collected test data and summarize the review results.

[0043] In step 106, the business rule management system receives the re-judgment result returned by the AI ​​re-judgment server and makes a decision instruction based on the re-judgment result. Common decision instructions include triggering an alarm and notifying the operator to perform manual intervention when the re-judgment result determines that the PCB board is abnormal.

[0044] Traditional re-judgment usually relies on manual inspection, which is not only time-consuming but also easily affected by human fatigue and subjective factors. This embodiment uses an AI re-judgment server to automatically review the preliminary inspection results, reduce reliance on manual labor, and improve production efficiency. At the same time, the AI ​​re-judgment server can learn and identify some complex defect patterns by analyzing large amounts of data and samples. These patterns may exceed the recognition capabilities of traditional detection methods. Through continuous learning and optimization of algorithms, the AI ​​re-judgment server can continuously improve the accuracy of detection. At the same time, this embodiment supports parallel communication between multiple production lines and equipment and the AI ​​re-judgment server, thereby improving the scalability of the system.

[0045] In one embodiment, step 104 includes:

[0046] The detection data is packaged into a JSON format data packet; the JSON format data packet includes the STM production line identification, the equipment identification in the STM production line, the timestamp, the PCB board information and the re-judgment result; the JSON format data packet is sent to the AI ​​re-judgment server through a POST request.

[0047] Using the POST method for data transmission can ensure the safe and complete transmission of large-capacity data, while reducing the probability of errors during data transmission.

[0048] In one embodiment, the AI ​​re-judgment server uses a two-way communication mechanism to connect to the client. The corresponding step 104 includes: forwarding the detection data to the AI ​​re-judgment server through the client; the corresponding step 106 receiving the re-judgment result given by the AI ​​re-judgment server for the detection data includes: receiving the re-judgment result given by the AI ​​re-judgment server and forwarded by the client.

[0049] In step 104, the BRM sends a JSON format data packet to the client via a POST request. After receiving the POST request from the BRM, the client automatically forwards the data to the AI ​​re-judgment server.

[0050] After processing the received data, the AI ​​re-judgment server returns the re-judgment result to the client via HTTP response. The client sends relevant instructions to BRM based on the returned result.

[0051] In one embodiment, a data confirmation and retransmission mechanism is used between the AI ​​re-judgment server and the client for data transmission.

[0052] In this embodiment, the client is used as a data packet forwarding transfer station. On the one hand, it communicates bidirectionally with the AI ​​re-judgment server, and on the other hand, it communicates bidirectionally with multiple BRMs to achieve bidirectional communication between the AI ​​re-judgment server and the BRM.

[0053] In one embodiment, step 104 includes: dynamically adjusting the sending frequency of the detection data and the connection status with the AI ​​re-judgment server according to the real-time workload of the STM production line, and dynamically allocating the detection data to the AI ​​re-judgment server using a load balancing algorithm.

[0054] According to the real-time workload of the production line, the client will dynamically adjust the frequency of POST requests and the number of production lines, AOI equipment or BRMs connected to the AI ​​review server. During peak production periods, the client will give priority to abnormal or important data and reduce the transmission frequency of non-critical data to ensure the timeliness of critical data. If a production line stops production, the system will automatically disconnect it from the server to reduce the server load. When a new production line or equipment starts, the client will immediately re-establish the connection and start data interaction to ensure the continuity of production. At the same time, based on the working status of each production line and data transmission delay, the system can adjust the frequency of POST requests in real time.

[0055] To achieve load balancing, the AI ​​re-judgment server in this embodiment is composed of multiple servers, and adopts a weighted polling load balancing algorithm to dynamically allocate POST requests according to the real-time processing capabilities and network delays of each server to ensure that all servers can work under a balanced load.

[0056] In one embodiment, to ensure the integrity of data transmission, after receiving the re-judgment result of the AI ​​re-judgment server, the client will perform an integrity check on the detection data corresponding to the re-judgment result. If the detection data is found to be incomplete or the transmission is erroneous, the client will resend the POST request until it is confirmed that the detection data has been completely transmitted successfully. In addition, the client uses a message queue mechanism to receive, transmit and store detection data. Specifically, after receiving the re-judgment result response from the AI ​​re-judgment server, the client stores it in the message queue and waits for the ACK (AcknowledgeCharacter, confirmation character) confirmation from the AI ​​re-judgment server. When the confirmation is successful, the message will be deleted from the queue; otherwise, it will be retransmitted.

[0057] In one embodiment, all data transmission, re-judgment results, and operation records are stored in a database for production tracking and traceability management. By querying the database, the production and inspection records of each PCB board can be tracked according to time, product batch and other conditions for subsequent quality management and production optimization. Using a distributed database, it supports high-concurrency data reading and writing, and has a powerful data retrieval function, which can perform traceability queries based on various conditions such as PCB board information and production time.

[0058] In one embodiment, a SMT-AI multi-device collaborative data interaction and re-judgment method based on intelligent interconnection is applied to an AI re-judgment server, and the AI ​​re-judgment server is connected to multiple business rule management systems in a parallel communication manner. The method includes:

[0059] Receiving the inspection data acquired by the business rule management system; wherein the inspection data comes from the AOI equipment for STM production line inspection connected to the business rule management system;

[0060] A re-judgment result is given in response to the detection data, and the re-judgment result is sent to the business rule management system so that the business rule management system can make a decision instruction based on the re-judgment result.

[0061] In one embodiment, Figure 1 The figure shows a flow chart of the SMT-AI multi-device collaborative data interaction and re-judgment method based on intelligent interconnection. The method includes:

[0062] S1. Data Collection

[0063] The NG (Not Go) data collected by AOI equipment on multiple SMT production lines is the inspection data.

[0064] S2. Data packaging and communication request

[0065] The BRM corresponding to the AOI device is packaged in JSON data format and sent to the client via a POST request.

[0066] S3, intelligent data routing and load balancing

[0067] Dynamically adjust the frequency of POST requests and the number of device connections according to the real-time situation of the SMT production line, prioritize and send important abnormal data, and adaptively connect and disconnect communications and interactions with devices. Use a weighted polling load balancing algorithm to dynamically allocate POST requests based on the real-time processing capabilities and network latency of each server to ensure that all servers can work under a balanced load.

[0068] S4. Two-way communication mechanism

[0069] After processing the data, the AI ​​re-judgment server returns the re-judgment result to the client through HTTP response. According to the returned result, the client sends relevant instructions to BRM. The specific instruction is that if an abnormality is detected on the PCB board, BRM will trigger an alarm and notify the operator to intervene manually.

[0070] S5. Data confirmation and retransmission mechanism

[0071] After receiving the re-verification result from the AI ​​re-verification server, the client confirms the data integrity. If the data is found to be incomplete or the transmission is wrong, the client will resend the POST request until it is confirmed that the data has been completely transmitted successfully.

[0072] S6. Decision Execution

[0073] The re-judgment result is returned to the corresponding production line BRM end via POST for the next step.

[0074] Compared with the traditional technology, the present invention has the following advantages:

[0075] 1. Strong scalability: It supports parallel communication between multiple production lines and devices and the AI ​​re-judgment server, and can automatically adapt to changes in the number of devices and production lines.

[0076] 2. Load balancing and intelligent routing: Dynamically adjust the communication load to ensure priority processing of key data and improve the real-time performance of data transmission.

[0077] 3. Two-way communication mechanism: It not only transmits detection data, but also makes real-time operational adjustments through the results returned by the AI ​​review server, thus improving the intelligence of the production line.

[0078] 4. Data confirmation and retransmission mechanism: ensure the accuracy of data transmission and reduce misjudgment caused by data loss or transmission errors.

[0079] 5. Strong traceability capability: Through the storage and management functions of the database, the complete production records of each PCB can be tracked, providing reliable data support for quality control.

[0080] In summary, the purpose of the present invention is to provide an intelligent data transmission and re-judgment method based on HTTP protocol and implemented by POST method in response to the data interaction needs of multiple devices in the existing SMT production environment. Through this method, one-to-many intelligent communication and efficient data interaction between the AI ​​re-judgment server and multiple SMT devices can be realized, solving the problems of poor scalability, difficult data synchronization, transmission delay and load imbalance in traditional systems, and improving the coordination and production efficiency of the entire production system.

[0081] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0082] Based on the same inventive concept, the embodiment of the present application also provides a SMT-AI multi-device collaborative data interaction and re-judgment device based on intelligent interconnection for implementing the above-mentioned SMT-AI multi-device collaborative data interaction and re-judgment method based on intelligent interconnection. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the SMT-AI multi-device collaborative data interaction and re-judgment device based on intelligent interconnection provided below can be referred to the limitations of the SMT-AI multi-device collaborative data interaction and re-judgment method based on intelligent interconnection in the above text, and will not be repeated here.

[0083] In one embodiment, Figure 2 As shown, a SMT-AI multi-device collaborative data interaction and re-judgment device based on intelligent interconnection is provided. The device includes a business rule management system and an AI re-judgment server. The AI ​​re-judgment server is connected to multiple business rule management systems in a parallel communication manner.

[0084] Among them, the business rule management system is used to obtain the relevant inspection data of the PCB board that has been mounted; the inspection data comes from the AOI equipment for STM production line inspection connected to the business rule management system; the inspection data is sent to the AI ​​re-judgment server; the re-judgment results given by the AI ​​re-judgment server for the inspection data are received, and decision instructions are made according to the re-judgment results;

[0085] The AI ​​re-judgment server is used to receive the detection data obtained by the business rule management system; give a re-judgment result in response to the detection data, and send the re-judgment result to the business rule management system so that the business rule management system can make decision instructions based on the re-judgment result.

[0086] In addition, the device also includes a client, which communicates bidirectionally with the business rule management system and the AI ​​re-judgment server respectively, to realize data forwarding between the AI ​​re-judgment server and the business rule management system.

[0087] In addition, the business rule management system, AI re-judgment server and client also execute the corresponding method steps in the above method embodiments.

[0088] Each module in the above-mentioned SMT-AI multi-device collaborative data interaction and re-judgment device based on intelligent interconnection can be implemented in whole or in part through software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0089] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in all the above method embodiments when executing the computer program.

[0090] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in all the above method embodiments are implemented.

[0091] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in all the above method embodiments when executed by a processor.

[0092] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0093] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited thereto. The processors involved in each embodiment provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, data processing logic devices based on quantum computing, etc., but are not limited thereto.

[0094] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0095] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A SMT-AI multi-device collaborative data interaction and re-judgment method based on intelligent interconnection, characterized in that: Applied to a business rule management system, the method comprises: Obtain relevant inspection data of the mounted PCB board; the inspection data is derived from the AOI equipment for STM production line inspection connected to the business rule management system; Sending the detection data to the AI ​​re-judgment server; Receive the re-judgment result given by the AI ​​re-judgment server for the detection data, and make a decision instruction according to the re-judgment result; Wherein, the AI ​​re-judgment server is connected with a plurality of the business rule management systems in a parallel communication manner.

2. The method according to claim 1, characterized in that The sending of the detection data to the AI ​​re-judgment server includes: Packing the detection data into a JSON format data packet; the JSON format data packet includes the STM production line identification, the equipment identification in the STM production line, the timestamp, the PCB board information and the re-judgment result; The JSON format data packet is sent to the AI ​​review server via a POST request.

3. The method according to claim 1, characterized in that The AI ​​re-judgment server uses a two-way communication mechanism to connect to the client; The sending of the detection data to the AI ​​re-judgment server includes: Forwarding the detection data to the AI ​​re-judgment server through the client; The receiving the re-judgment result given by the AI ​​re-judgment server for the detection data includes: Receive the re-judgment result given by the AI ​​re-judgment server and forwarded by the client.

4. The method according to claim 3, characterized in that The AI ​​re-judgment server and the client use a data confirmation and retransmission mechanism for data transmission.

5. The method according to claim 1, characterized in that The sending of the detection data to the AI ​​re-judgment server includes: According to the real-time workload of the STM production line, the sending frequency of the detection data and the connection status with the AI ​​re-judgment server are dynamically adjusted, and the detection data is dynamically distributed to the AI ​​re-judgment server using a load balancing algorithm.

6. A SMT-AI multi-device collaborative data interaction and re-judgment method based on intelligent interconnection, characterized in that: Applied to an AI re-judgment server, the AI ​​re-judgment server is connected to a plurality of the business rule management systems in a parallel communication manner, the method comprising: Receiving the detection data acquired by the business rule management system; wherein the detection data comes from the AOI equipment for STM production line detection connected to the business rule management system; A re-judgment result is given in response to the detection data, and the re-judgment result is sent to the business rule management system so that the business rule management system can make a decision instruction according to the re-judgment result.

7. A SMT-AI multi-device collaborative data interaction and re-judgment device based on intelligent interconnection, characterized in that: The device includes a business rule management system and an AI re-judgment server, wherein the AI ​​re-judgment server is connected to a plurality of the business rule management systems in a parallel communication manner; The business rule management system is used to obtain the relevant detection data of the PCB board that has been mounted; the detection data comes from the AOI equipment for STM production line detection connected to the business rule management system; the detection data is sent to the AI ​​re-judgment server; the re-judgment result given by the AI ​​re-judgment server for the detection data is received, and a decision instruction is made according to the re-judgment result; The AI ​​re-judgment server is used to receive the detection data acquired by the business rule management system; give a re-judgment result in response to the detection data, and send the re-judgment result to the business rule management system so that the business rule management system can make a decision instruction based on the re-judgment result.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images