Intelligent monitoring system and method for automatic production line of ice making machine

Abstract

The present invention belongs to the technical field of ice making machines, and provides an intelligent monitoring system and method for an automatic production line of an ice making machine. The method includes: analyzing video stream data to determine the quality inspection type of the quality inspection link, the attribute information of the ice making machine, and the measured quality inspection information; determining a number of related quality inspection specification information according to the attribute information; screening out part of the quality inspection specification information according to the quality inspection type, and using it as the target quality inspection specification information; performing compliance detection on the measured quality inspection information based on the target quality inspection specification information, and outputting an alarm message if it does not comply with the rules. The present invention configures a specific monitoring strategy for the quality inspection link of the automatic production line of the ice making machine, which changes the existing monitoring system's function of only being able to perform image recording or conventional equipment abnormalities, human-machine contact hazards, etc., and can achieve a deeper level of compliance analysis of the quality inspection link, thereby ensuring the quality of the ice making machines produced by the automatic production line of the ice making machine.

Description

Technical Field

[0001] The present invention relates to the technical field of ice making machines, and in particular to an intelligent monitoring system and method for an automatic production line of an ice making machine. Background Art

[0002] At present, ice machines are produced quickly through automatic production lines, which play an important role in improving production efficiency and reducing costs. At the same time, a monitoring system needs to be deployed in the area around the automatic production line to monitor the automatic production line and detect abnormal situations in time.

[0003] However, the existing production line monitoring system focuses more on safety, such as monitoring of equipment abnormalities and human-machine contact hazards, but rarely involves monitoring of the subsequent quality inspection links of the automatic production line. The existing production line monitoring system can only record the quality inspection links, but lacks the formulation of more reasonable and proactive monitoring strategies. It can be seen that how to improve the proactive monitoring of the subsequent quality inspection links of the automatic production line is a technical problem that needs to be solved at present. Summary of the invention

[0004] In this regard, the present invention provides an intelligent monitoring method, system, electronic equipment, computer storage medium and computer program product for an automatic production line of ice making machines to solve the above technical problems.

[0005] The present invention provides an intelligent monitoring method for an automatic production line of an ice-making machine, the method comprising the following steps: determining from a monitoring system first video stream data, second video stream data, and third video stream data corresponding to a quality inspection link of the automatic production line of the ice-making machine; wherein the first video stream data is earlier than the second video stream data, and the second video stream data is earlier than the third video stream data; analyzing the first video stream data to determine the quality inspection type of the quality inspection link; wherein the quality inspection type includes manual quality inspection, machine quality inspection, and human-machine mixed quality inspection; analyzing the second video stream data to determine the attribute information of the ice-making machine, and determining and obtaining a plurality of associated quality inspection specification information according to the attribute information, each of the quality inspection specification information including a plurality of first quality inspection item information and corresponding first sequence information; filtering out a portion of the quality inspection specification information according to the quality inspection type, and using it as target quality inspection specification information; analyzing the third video stream data to determine the actual quality inspection information, and performing compliance detection on the actual quality inspection information based on the target quality inspection specification information, and outputting an alarm message if it does not conform to the rules; wherein the actual quality inspection information includes a plurality of second quality inspection item information and corresponding second sequence information.

[0006] Optionally, the determining of the first video stream data, the second video stream data, and the third video stream data corresponding to the quality inspection link of the ice-making machine automatic production line from the monitoring system includes: retrieving the fourth video stream data captured by each camera of the monitoring system, and analyzing the fourth video stream data to obtain the assembly completeness of the ice-making machine; if the assembly completeness of the ice-making machine in the fourth video stream data is higher than the target assembly completeness, determining the corresponding area of ​​the fourth video stream data as the quality inspection link; and obtaining the first video stream data, the second video stream data, and the third video stream data corresponding to the quality inspection link.

[0007] Optionally, analyzing the fourth video stream data to obtain the assembly completeness of the ice maker includes: extracting outer contour information and target component recognition information of the ice maker from the fourth video stream data; determining a first complete evaluation value based on the outer contour information, determining a second complete evaluation value based on the target component recognition information, and calculating the assembly completeness of the ice maker based on the first complete evaluation value and a first weight, and the second complete evaluation value and a second weight; wherein the first weight is higher than the second weight.

[0008] Optionally, the analysis of the first video stream data to determine the quality inspection type of the quality inspection link includes: extracting features of the quality inspector and the quality inspection machine on the first video stream data to obtain features of the quality inspector and features of the quality inspection machine, respectively, and extracting features of the operating state of the ice maker to obtain the operating state or non-operating state of the quality inspection link; if the quality inspection link is in an operating state and only features of the quality inspector exist, the quality inspection type is identified as manual quality inspection; if the quality inspection link is in an operating state and only features of the quality inspection machine exist, the quality inspection type is identified as machine quality inspection; if the quality inspection link is in an operating state and both features of the quality inspector and features of the quality inspection machine exist, the quality inspection type is identified as mixed quality inspection.

[0009] Optionally, part of the quality inspection specification information is filtered out according to the quality inspection type and used as the target quality inspection specification information, including: if the quality inspection type is manual quality inspection, the first quality inspection specification information corresponding to the manual quality inspection is determined as the target quality inspection specification information; if the quality inspection type is machine quality inspection or mixed quality inspection, the first quality inspection specification information corresponding to manual quality inspection, the second quality inspection specification information corresponding to machine quality inspection, and the third quality inspection specification information corresponding to mixed quality inspection are determined as the target quality inspection specification information.

[0010] Optionally, the compliance check of the measured quality inspection information based on the target quality inspection specification information includes: matching the second quality inspection item information in the measured quality inspection information and the first quality inspection item information in the target quality inspection specification information according to the second sequence information and the first sequence information; if any of the second quality inspection item information fails to match, or the match is successful but the second sequence information fails to match the first sequence information, the measured quality inspection information is determined to be non-compliant.

[0011] The present invention also provides an intelligent monitoring system for an automatic production line of an ice-making machine, the system comprising a first processing component, a second processing component, a third processing component, a fourth processing component, and a detection and alarm component; the first processing component is used to determine from the monitoring system first video stream data, second video stream data, and third video stream data corresponding to a quality inspection link of the automatic production line of the ice-making machine; wherein the first video stream data is earlier than the second video stream data, and the second video stream data is earlier than the third video stream data; the second processing component is used to analyze the first video stream data to determine the quality inspection type of the quality inspection link; wherein the quality inspection types include manual quality inspection, machine quality inspection, and human-machine mixed quality inspection; the third A processing component is used to analyze the second video stream data to determine the attribute information of the ice maker, and determine a number of associated quality inspection specification information based on the attribute information, each of the quality inspection specification information includes a number of first quality inspection item information and corresponding first sequence information; the fourth processing component is used to filter out part of the quality inspection specification information according to the quality inspection type and use it as target quality inspection specification information; the detection and alarm component is used to analyze the third video stream data to determine the measured quality inspection information, and perform compliance detection on the measured quality inspection information based on the target quality inspection specification information, and output an alarm message if it does not comply with the rules; wherein the measured quality inspection information includes a number of second quality inspection item information and corresponding second sequence information.

[0012] The present invention also provides an electronic device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program implements the method described in any of the preceding items when executed by the processor.

[0013] The present invention also provides a computer storage medium storing a computer program executable by a processor to implement any of the methods described above.

[0014] The present invention also provides a computer program product, which includes a computer program that can be executed by a processor to implement any of the methods described above.

[0015] The present invention configures a specific monitoring strategy for the quality inspection link of the ice-making machine automatic production line, which changes the existing monitoring system's function of only performing image recording or conventional detection of equipment abnormalities, human-machine contact hazards, etc., and can achieve a deeper compliance analysis of the quality inspection link, thereby ensuring the quality of the ice-making machines produced by the ice-making machine automatic production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 The present invention is a flowchart of an intelligent monitoring method for an automatic production line of ice machines disclosed in an embodiment of the present invention.

[0018] Figure 2 The invention discloses a structure diagram of an intelligent monitoring system for an automatic production line of ice machines.

[0019] Figure 3 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0021] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0022] like Figure 1As shown, an embodiment of the present invention discloses an intelligent monitoring method for an automatic production line of an ice-making machine, the method comprising the following steps: determining from a monitoring system first video stream data, second video stream data, and third video stream data corresponding to a quality inspection link of the automatic production line of the ice-making machine; wherein the first video stream data is earlier than the second video stream data, and the second video stream data is earlier than the third video stream data; analyzing the first video stream data to determine a quality inspection type for the quality inspection link; wherein the quality inspection type includes manual quality inspection, machine quality inspection, and human-machine mixed quality inspection; analyzing the second video stream data An analysis is performed to determine the attribute information of the ice maker, and a number of associated quality inspection specification information is determined based on the attribute information, each of the quality inspection specification information includes a number of first quality inspection item information and corresponding first sequence information; part of the quality inspection specification information is screened out according to the quality inspection type, and is used as the target quality inspection specification information; the third video stream data is analyzed to determine the measured quality inspection information, and a compliance check is performed on the measured quality inspection information based on the target quality inspection specification information, and an alarm message is output if it does not comply with the rules; wherein the measured quality inspection information includes a number of second quality inspection item information and corresponding second sequence information.

[0023] In order to solve the technical problems mentioned in the background technology, the present invention sets a video monitoring system on the automatic production line of the ice maker. The video monitoring system is composed of a plurality of cameras, and each camera corresponds to each production link of the automatic production line of the ice maker.

[0024] First, retrieve the video stream data corresponding to the quality inspection link, where the collection time of the first video stream data, the second video stream data, and the third video stream data is arranged in order. The first video stream data may be the video stream before the quality inspection of a certain ice-making machine after production is completed. At this time, the quality inspection type adopted in the quality inspection link of the automatic production line is analyzed based on the first video stream data, that is, manual quality inspection, machine quality inspection, or human-machine mixed quality inspection. The machine quality inspection refers to the configuration of a quality inspection machine with automated quality inspection capabilities in the quality inspection link, which can perform quality inspection and analysis on multiple specified quality inspection items of the ice-making machine according to a preset program, and output the corresponding quality inspection conclusions.

[0025] When the produced ice machine is about to or has just arrived at the quality inspection stage, the second video stream data is shot, and the attribute information of the ice machine (such as the ice machine type number) is extracted from it. The attribute information corresponds to a number of quality inspection specification information, each of which includes a number of first quality inspection item information and corresponding first item sequence information. The first quality inspection item information includes, for example, appearance quality inspection (mainly checking whether there are appearance defects such as bumps, whether the identification information is printed completely, etc.), electrical component quality inspection (such as checking whether the touch screen is available, whether the power cable is powered normally, etc.), mechanical component quality inspection (such as whether the refrigerant pipeline is desoldered, whether the casters are installed, etc.). Each quality inspection item is preset with a corresponding quality inspection sequence.

[0026] Next, according to the quality inspection type of the quality inspection link of the automatic production line obtained above, some quality inspection specification information is selected from the quality inspection specification information corresponding to the attribute information of the ice maker, and it is used as the target quality inspection specification information. For example, if there are three quality inspection specification information corresponding to the attribute information of the ice maker, two of them are selected as the target quality inspection specification information.

[0027] Finally, when the formal quality inspection of the ice maker begins, the third video stream data is retrieved and the specific quality inspection behavior of the ice maker is extracted from it and used as the measured quality inspection information. The measured quality inspection information is then checked for compliance based on the target quality inspection specification information obtained above. If it does not comply with the rules, an alarm message is output.

[0028] Therefore, the present invention configures a specific monitoring strategy for the quality inspection link of the ice-making machine automatic production line, which changes the existing monitoring system's function of only performing image recording or detecting conventional equipment abnormalities, human-machine contact hazards, etc., and can achieve a deeper compliance analysis of the quality inspection link, thereby ensuring the quality of the ice-making machines produced by the ice-making machine automatic production line.

[0029] Optionally, the determining of the first video stream data, the second video stream data, and the third video stream data corresponding to the quality inspection link of the ice-making machine automatic production line from the monitoring system includes: retrieving the fourth video stream data captured by each camera of the monitoring system, and analyzing the fourth video stream data to obtain the assembly completeness of the ice-making machine; if the assembly completeness of the ice-making machine in the fourth video stream data is higher than the target assembly completeness, determining the corresponding area of ​​the fourth video stream data as the quality inspection link; and obtaining the first video stream data, the second video stream data, and the third video stream data corresponding to the quality inspection link.

[0030] In this embodiment, cameras are arranged in multiple areas of the automatic production line to monitor each link of the automatic production line. The existing method is to associate and number each camera with the corresponding arrangement position in advance, so that the area corresponding to each video stream data can be determined according to the number. However, the camera may also be non-fixed, or the shooting angle of the camera may also change, resulting in the video stream data captured by it not matching the original area.

[0031] In view of the above technical problems, the present invention retrieves the fourth video stream data captured by each camera of the monitoring system, analyzes each segment of the fourth video stream data to obtain the assembly completeness of the ice maker, and if the assembly completeness of the ice maker in the fourth video stream data is higher than the target assembly completeness, then the area corresponding to the fourth video stream data is determined to be the area where the quality inspection link is located, because only the ice maker in the quality inspection link is assembled and has the highest assembly completeness. Then, the first video stream data, the second video stream data, and the third video stream data corresponding to the quality inspection link can be obtained.

[0032] Optionally, analyzing the fourth video stream data to obtain the assembly completeness of the ice maker includes: extracting outer contour information and target component recognition information of the ice maker from the fourth video stream data; determining a first complete evaluation value based on the outer contour information, determining a second complete evaluation value based on the target component recognition information, and calculating the assembly completeness of the ice maker based on the first complete evaluation value and a first weight, and the second complete evaluation value and a second weight; wherein the first weight is higher than the second weight.

[0033] In this embodiment, the assembly completeness of the ice maker at different links of the automatic production line is different. At the front end of the automatic production line, the assembly completeness of the ice maker is the lowest, mainly in the form of parts; the ice maker at the middle end of the automatic production line has been partially assembled, and its assembly completeness is medium; at the back end of the automatic production line, such as the quality inspection link, the ice maker is already a finished product, and its assembly completeness is the highest. The present invention comprehensively evaluates the assembly completeness of the ice maker based on the outer contour information of the ice maker and the target component recognition information.

[0034] Among them, the outer contour information refers to the outer contour lines of the ice maker in each link of the automatic production line. The less the fluctuation of the outer contour lines and the lower the fluctuation amplitude, that is, the closer to a straight line, the greater the probability that the ice maker is covered by the outer cover shell. Correspondingly, the closer to the rear end of the automatic production line, the higher the corresponding assembly completeness of the ice maker, and the larger the first complete evaluation value is set; otherwise, the smaller the first complete evaluation value is set.

[0035] The target component recognition information refers to the situation where several target components (mainly the compressor, evaporator, condenser, etc. located inside the cover) are identified in the fourth video stream data. For example, if the target component is not identified, or if it is identified but only a part of the target component is identified, then the probability that the ice maker is closer to the rear end of the automatic production line is higher, and the corresponding setting second complete evaluation value is larger; and if the target component is identified and most of the target component is identified, then the probability that the ice maker is closer to the front end of the automatic production line is higher, and the corresponding setting second complete evaluation value is smaller.

[0036] At the same time, the identification of the target component does not completely correspond to the production process, and various factors will also affect the identification of the target component, but the presence or absence of the outer cover can basically be used to determine the assembly integrity of the ice maker. Therefore, the present invention sets the first weight corresponding to the outer contour information to be higher than the second weight corresponding to the target component recognition information.

[0037] Optionally, the analysis of the first video stream data to determine the quality inspection type of the quality inspection link includes: extracting features of the quality inspector and the quality inspection machine on the first video stream data to obtain features of the quality inspector and features of the quality inspection machine, respectively, and extracting features of the operating state of the ice maker to obtain the operating state or non-operating state of the quality inspection link; if the quality inspection link is in an operating state and only features of the quality inspector exist, the quality inspection type is identified as manual quality inspection; if the quality inspection link is in an operating state and only features of the quality inspection machine exist, the quality inspection type is identified as machine quality inspection; if the quality inspection link is in an operating state and both features of the quality inspector and features of the quality inspection machine exist, the quality inspection type is identified as mixed quality inspection.

[0038] In this embodiment, the quality inspection link can be designed as manual quality inspection, machine quality inspection and mixed quality inspection according to needs, and the features of the quality inspection personnel and the quality inspection machine can be extracted from the first video stream data, and the type of the quality inspection link can be analyzed based on the extracted quality inspection personnel features and quality inspection machine features. In addition, since the quality inspection personnel features and quality inspection machine features may not be detected in the running state, and even if they are detected, they may not be consistent with the actual situation, the analysis of the quality inspection type set by the present invention is performed when the quality inspection link is in the running state. It should be noted that the quality inspection personnel features in the present invention refer to features that can be used to determine that the quality inspection executor is a "person", such as human shape features, clothing features, etc.; in contrast, the quality inspection machine features refer to features that can be used to determine that the quality inspection executor is a "machine", such as robotic arm features, camera features, etc.

[0039] In addition, the operating state or non-operating state of the quality inspection link is determined according to the operating state of the ice maker. The operating state of the ice maker refers to the moving transmission state and the static state of the ice maker on the conveyor belt. When the operating state of the ice maker is the moving transmission state, it means that the conveyor belt is working, and the quality inspection link is in the operating state; when the operating state of the ice maker is the static state, it means that the conveyor belt is not working, and the quality inspection link is in the non-operating state.

[0040] Optionally, part of the quality inspection specification information is filtered out according to the quality inspection type and used as the target quality inspection specification information, including: if the quality inspection type is manual quality inspection, the first quality inspection specification information corresponding to the manual quality inspection is determined as the target quality inspection specification information; if the quality inspection type is machine quality inspection or mixed quality inspection, the first quality inspection specification information corresponding to manual quality inspection, the second quality inspection specification information corresponding to machine quality inspection, and the third quality inspection specification information corresponding to mixed quality inspection are determined as the target quality inspection specification information.

[0041] In this embodiment, when the quality inspection type is manual quality inspection, since the installation and deployment of the automatic quality inspection machine takes a long time, the probability of changing to machine quality inspection or mixed quality inspection in the short term is very low, so at this time, only the first quality inspection specification information corresponding to manual quality inspection is set as the target quality inspection specification information. When the quality inspection type is machine quality inspection or mixed quality inspection, there is a certain probability that the quality inspection link will be changed to manual quality inspection or mixed quality inspection in the short term (or, the quality inspection link itself is mixed quality inspection, but the characteristics of the quality inspection personnel are not detected in the first video stream data). At this time, the first quality inspection specification information corresponding to manual quality inspection, the second quality inspection specification information corresponding to machine quality inspection, and the third quality inspection specification information corresponding to mixed quality inspection are all determined as target quality inspection specification information.

[0042] It should be noted that although the monitoring system can be configured with quality inspection specification information for various quality inspection types, this will cause the storage space of the monitoring system to be excessively occupied on the one hand, and on the other hand, if the corresponding quality inspection specification information is not pre-stored in the monitoring system, it needs to be temporarily obtained, which may cause the quality inspection link to have to pause and other jams. For example, when only the second quality inspection specification information corresponding to the machine quality inspection is cached in the monitoring system, and the actual quality inspection type becomes a mixed type, the monitoring system needs to temporarily obtain the third quality inspection specification information from the server, and the acquisition of the third quality inspection specification information takes a certain amount of time, which will cause the quality inspection link to pause and other jams. Therefore, the present invention is arranged to pre-store the first quality inspection specification information, the second quality inspection specification information, and the third quality inspection specification information in the monitoring system at the same time when the quality inspection type is machine quality inspection or mixed quality inspection, thereby avoiding the problem of quality inspection jams caused by time-consuming calls.

[0043] Among them, based on the types of different types of ice makers, different quality inspection specification information needs to be configured for them, that is, at least one of the first quality inspection specification information, the second quality inspection specification information, and the third quality inspection specification information mentioned above, and the configured quality inspection specification information is associated with the attribute information of the ice maker and stored in the monitoring system or server.

[0044] Optionally, the compliance check of the measured quality inspection information based on the target quality inspection specification information includes: matching the second quality inspection item information in the measured quality inspection information and the first quality inspection item information in the target quality inspection specification information according to the second sequence information and the first sequence information; if any of the second quality inspection item information fails to match, or the match is successful but the second sequence information fails to match the first sequence information, the measured quality inspection information is determined to be non-compliant.

[0045] In this embodiment, the target quality inspection specification information obtained above is used to limit the quality inspection items that should be carried out on the ice maker and the standard order of each quality inspection item. If the actual quality inspection items of the ice maker are missing by the quality inspection personnel and / or quality inspection machine (that is, some of the first item information is not implemented) or the quality inspection order is incorrect, the actual quality inspection information is judged to be non-compliant, and an alarm message can be output at this time.

[0046] like Figure 2 As shown, an embodiment of the present invention further discloses an intelligent monitoring system for an automatic production line of an ice-making machine, the system comprising a first processing component, a second processing component, a third processing component, a fourth processing component, and a detection alarm component; the first processing component is used to determine from the monitoring system first video stream data, second video stream data, and third video stream data corresponding to a quality inspection link of the automatic production line of the ice-making machine; wherein the first video stream data is earlier than the second video stream data, and the second video stream data is earlier than the third video stream data; the second processing component is used to analyze the first video stream data to determine a quality inspection type of the quality inspection link; wherein the quality inspection type includes manual quality inspection, machine quality inspection, and human-machine mixed quality inspection; The third processing component is used to analyze the second video stream data to determine the attribute information of the ice maker, and determine a number of associated quality inspection specification information based on the attribute information, each of the quality inspection specification information includes a number of first quality inspection item information and corresponding first sequence information; the fourth processing component is used to filter out part of the quality inspection specification information according to the quality inspection type and use it as target quality inspection specification information; the detection and alarm component is used to analyze the third video stream data to determine the measured quality inspection information, and perform compliance detection on the measured quality inspection information based on the target quality inspection specification information, and output an alarm message if it does not comply with the rules; wherein the measured quality inspection information includes a number of second quality inspection item information and corresponding second sequence information.

[0047] like Figure 3 As shown, an embodiment of the present invention further discloses an electronic device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program implements the method described in any of the preceding items when executed by the processor.

[0048] The present invention also discloses a computer storage medium, which stores a computer program that can be executed by a processor to implement any of the methods described in the preceding items.

[0049] The present invention also discloses a computer program product, which includes a computer program that can be executed by a processor to implement any of the methods described in the preceding items.

[0050] In addition, the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk and other media that can store program codes.

[0051] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An intelligent monitoring method for an automatic production line of an ice machine, characterized in that: The method comprises the following steps: determining from the monitoring system the first video stream data, the second video stream data, and the third video stream data corresponding to the quality inspection link of the ice-making machine automatic production line; wherein the first video stream data is earlier than the second video stream data, and the second video stream data is earlier than the third video stream data; analyzing the first video stream data to determine the quality inspection type of the quality inspection link; wherein the quality inspection type includes manual quality inspection, machine quality inspection, and human-machine mixed quality inspection; analyzing the second video stream data to determine the attribute information of the ice-making machine, and determining the associated several quality inspection specification information according to the attribute information, each of the quality inspection specification information includes several first quality inspection item information and corresponding first sequence information; filtering out part of the quality inspection specification information according to the quality inspection type, and using it as the target quality inspection specification information; analyzing the third video stream data to determine the measured quality inspection information, and performing compliance detection on the measured quality inspection information based on the target quality inspection specification information, and outputting an alarm message if it does not conform to the rules; wherein the measured quality inspection information includes several second quality inspection item information and corresponding second sequence information; Among them, the first video stream data is a video stream before the quality inspection of a completed ice-making machine, the second video stream data is a video stream shot when the produced ice-making machine is about to or has just arrived at the quality inspection stage, and the third video stream data is a video stream shot when the formal quality inspection of the ice-making machine begins.

2. The intelligent monitoring method for an automatic production line of an ice machine according to claim 1, characterized in that: Determine from the monitoring system the first video stream data, the second video stream data, and the third video stream data corresponding to the quality inspection link of the ice-making machine automatic production line, including: retrieve the fourth video stream data captured by each camera of the monitoring system, analyze the fourth video stream data to obtain the assembly completeness of the ice-making machine; if the assembly completeness of the ice-making machine in the fourth video stream data is higher than the target assembly completeness, determine the corresponding area of ​​the fourth video stream data as the quality inspection link; obtain the first video stream data, the second video stream data, and the third video stream data corresponding to the quality inspection link.

3. The intelligent monitoring method for an automatic production line of an ice making machine according to claim 2, characterized in that: The fourth video stream data is analyzed to obtain the assembly completeness of the ice maker, including: extracting the outer contour information and the target component recognition information of the ice maker from the fourth video stream data; determining a first complete evaluation value according to the outer contour information, determining a second complete evaluation value according to the target component recognition information, and calculating the assembly completeness of the ice maker according to the first complete evaluation value and a first weight, and the second complete evaluation value and a second weight; wherein the first weight is higher than the second weight.

4. The intelligent monitoring method for an automatic production line of an ice making machine according to claim 3 is characterized in that: The first video stream data is analyzed to determine the quality inspection type of the quality inspection link, including: extracting features of the quality inspector and the quality inspection machine on the first video stream data to obtain features of the quality inspector and features of the quality inspection machine respectively, and extracting features of the operating state of the ice maker to obtain the operating state or non-operating state of the quality inspection link; if the quality inspection link is in an operating state and only features of the quality inspector exist, the quality inspection type is identified as manual quality inspection; if the quality inspection link is in an operating state and only features of the quality inspection machine exist, the quality inspection type is identified as machine quality inspection; if the quality inspection link is in an operating state and both features of the quality inspector and features of the quality inspection machine exist, the quality inspection type is identified as mixed quality inspection.

5. The intelligent monitoring method for an automatic production line of an ice making machine according to claim 4, characterized in that: According to the quality inspection type, part of the quality inspection specification information is filtered out and used as the target quality inspection specification information, including: if the quality inspection type is manual quality inspection, the first quality inspection specification information corresponding to the manual quality inspection is determined as the target quality inspection specification information; if the quality inspection type is machine quality inspection or mixed quality inspection, the first quality inspection specification information corresponding to the manual quality inspection, the second quality inspection specification information corresponding to the machine quality inspection, and the third quality inspection specification information corresponding to the mixed quality inspection are determined as the target quality inspection specification information.

6. The intelligent monitoring method for an automatic production line of an ice machine according to claim 5, characterized in that: The measured quality inspection information is subjected to compliance check based on the target quality inspection specification information, including: matching the second quality inspection item information in the measured quality inspection information with the first quality inspection item information in the target quality inspection specification information according to the second sequence information and the first sequence information; if any of the second quality inspection item information fails to match, or if the match succeeds but the second sequence information fails to match the first sequence information, the measured quality inspection information is determined to be non-compliant.

7. An intelligent monitoring system for an automatic production line of an ice machine, the system comprising a first processing component, a second processing component, a third processing component, a fourth processing component, and a detection alarm component; characterized in that: The first processing component is used to determine from the monitoring system the first video stream data, the second video stream data, and the third video stream data corresponding to the quality inspection link of the ice-making machine automatic production line; wherein the first video stream data is earlier than the second video stream data, and the second video stream data is earlier than the third video stream data; the second processing component is used to analyze the first video stream data to determine the quality inspection type of the quality inspection link; wherein the quality inspection type includes manual quality inspection, machine quality inspection, and human-machine mixed quality inspection; the third processing component is used to analyze the second video stream data to determine the attribute information of the ice-making machine, Determine the associated several quality inspection specification information according to the attribute information, each of the quality inspection specification information includes several first quality inspection item information and corresponding first sequence information; the fourth processing component is used to filter out part of the quality inspection specification information according to the quality inspection type and use it as the target quality inspection specification information; the detection alarm component is used to analyze the third video stream data to determine the measured quality inspection information, perform compliance detection on the measured quality inspection information based on the target quality inspection specification information, and output an alarm message if it does not comply with the rules; wherein the measured quality inspection information includes several second quality inspection item information and corresponding second sequence information; Among them, the first video stream data is a video stream before the quality inspection of a completed ice-making machine, the second video stream data is a video stream shot when the produced ice-making machine is about to or has just arrived at the quality inspection stage, and the third video stream data is a video stream shot when the formal quality inspection of the ice-making machine begins.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program implements the method according to any one of claims 1 to 6 when executed by the processor.

9. A computer storage medium, characterized in that: The computer storage medium stores a computer program that can be executed by a processor to implement the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that: The computer program product comprises a computer program executable by a processor to implement the method according to any one of claims 1 to 6.

Images