A finished square bar online detection device and detection method

Abstract

The present invention provides an online inspection device for finished square bars and an inspection method thereof, wherein the device comprises: a modeling module for, when multiple robots perform quality inspection on single crystal finished square bars, if any robot reports an inspection situation to be inspected online, performing AR modeling on the inspection situation to obtain a situation AR model; and an auxiliary module for assisting a user in performing corresponding quality inspection and processing of the inspection situation online based on the situation AR model. The online inspection device for finished square bars of the present invention and an inspection method thereof, when a robot performing quality inspection on single crystal finished square bars reports an inspection situation to be inspected online, performing AR modeling on the inspection situation to obtain a situation AR model, and assisting a user in performing corresponding quality inspection and processing of the inspection situation online based on the situation AR model, eliminates the need for management personnel to go to the site for processing, thereby improving convenience and enabling the inspection situation to be resolved in a timely manner, thereby avoiding affecting the overall inspection progress of the single crystal finished square bars.

Description

Technical Field

[0001] The present invention relates to the technical field of detection of finished single crystal square bars, and in particular to an online detection device and a detection method for finished square bars. Background Art

[0002] Single crystal square ingots are a crucial raw material for high-tech industries like semiconductors and photovoltaics. Their quality directly impacts the performance and reliability of downstream products. Traditional methods for inspecting the quality of finished square ingots rely heavily on manual labor, often suffering from slow inspection speeds, low accuracy, and significant operator error. These methods fail to meet the efficiency and precision requirements of modern production.

[0003] With the advancement of industrial automation and intelligent technologies, the production process of finished single crystal square ingots is becoming increasingly efficient and precise. To improve the efficiency and accuracy of quality inspections, automated quality inspection systems have become an integral part of industrial production. In practical applications, the use of multiple robots working collaboratively to perform real-time inspections of finished single crystal square ingots effectively improves inspection efficiency and reduces manual operation costs.

[0004] However, when multiple robots work together to perform real-time inspection of single crystal finished square bars, they may encounter complex situations where they cannot perform inspections. When encountering complex situations, management personnel need to go to the site to handle them, which is less convenient and cannot be resolved in a timely manner, affecting the overall inspection progress of single crystal finished square bars.

[0005] Therefore, a solution is urgently needed. Summary of the Invention

[0006] One of the purposes of the present invention is to provide an online inspection device for finished square bars. When a robot that performs quality inspection on single crystal finished square bars reports the inspection situation to be performed online, AR modeling is performed on the inspection situation to obtain the situation AR model, and the user is assisted in performing corresponding quality inspection processing on the inspection situation online based on the situation AR model. There is no need for management personnel to go to the site for processing, which improves convenience and enables the inspection situation to be resolved in a timely manner to avoid affecting the overall inspection progress of single crystal finished square bars.

[0007] An embodiment of the present invention provides an online detection device for finished square bars, comprising:

[0008] A modeling module is used to perform AR modeling on the inspection situation when multiple robots perform quality inspection on finished single crystal square bars. If any robot reports an inspection situation to be performed online, the inspection situation is modeled to obtain an AR model of the situation.

[0009] The auxiliary module is used to assist users in performing corresponding quality inspection and processing on the detection situation online based on the situation AR model.

[0010] Optionally, the auxiliary module assists the user in performing corresponding quality inspection and processing on the inspection situation online based on the situation AR model, including:

[0011] Guide users into the situational AR model;

[0012] When the user enters, continuously identifying whether the user focuses on a first AR object in the situational AR model within a first period of time;

[0013] If the answer is yes, the second AR object other than the first AR model in the situation AR model is continuously controlled to be undisplayed within a second period of time, and a third AR object with display value is selected from the second AR objects based on the interaction history between the user and the first AR object, and the third AR object is controlled to be undisplayed within a third period of time;

[0014] When the identification result is negative, the user is prompted to focus.

[0015] Optionally, the auxiliary module continuously identifies whether the user focuses on the first AR object in the situational AR model within the first period, including:

[0016] Continuously identifying whether a focus condition is met between the user and the first AR object within a first period of time;

[0017] If the conditions are met, it is determined that the first AR object is in focus; otherwise, it is not.

[0018] The focusing conditions include:

[0019] Condition 1: The similarity between the spatial movement trajectories of the user's two virtual operating bodies in the situation AR model exceeds a similarity threshold and the two virtual operating bodies operate the first AR object;

[0020] and / or,

[0021] Condition 2: The user operates a first AR object with a single virtual operating body in the contextual AR model, and the distance between the first AR object and the user's viewing starting position in the contextual AR model continuously does not exceed a distance threshold;

[0022] and / or,

[0023] Condition 3: The user's viewing angle in the situation AR model continuously includes only the first AR object.

[0024] Optionally, the auxiliary module selects a third AR object having display value from the second AR object based on the interaction history between the user and the first AR object, including:

[0025] Based on the first time period and the second time period, the interaction history is divided into a first history sequence and a second history sequence;

[0026] When there is at least one progressive relationship between a second history item in the second history sequence and a first history item in the first history sequence, generating a first object selection condition based on the corresponding second history item and other second history items within a preset range after the corresponding second history item in the second history sequence;

[0027] using the second AR object that meets the first object selection condition as the third AR object;

[0028] When the second history sequence is different from the first history sequence, generating a second object selection condition based on all second history items in the second history sequence;

[0029] using the second AR object that meets the second object selection condition as the third AR object;

[0030] When the second history sequence is partially identical to the first history sequence, generating a third object selection condition based on all second history items in the partially identical partial sequences in the second history sequence;

[0031] The second AR object that meets the third object selection condition is used as the third AR object.

[0032] Optionally, the first time period is any time period after the user enters the situation AR model, the time period being the preset first time period value;

[0033] The second time period is after the first time period and is adjacent to the first time period. The duration of the second time period is a second duration value. There is a first positive correlation between the second duration value and the proportion of the first AR object in the detection situation.

[0034] The third time period is during the second time period and is adjacent to the second time period. The duration of the third time period is a third duration value. There is a second positive correlation between the third duration value and the display value of the third AR object.

[0035] An embodiment of the present invention provides an online detection method for finished square bars, comprising:

[0036] When multiple robots perform quality inspection on finished single crystal square bars, if any robot reports a test situation to be tested online, AR modeling is performed on the test situation to obtain a situation AR model.

[0037] Assist users to perform corresponding quality inspection and processing on the detection situation online based on the situation AR model.

[0038] Optionally, the auxiliary user performs corresponding quality detection processing on the detection situation online based on the situation AR model, including:

[0039] Guide users into the situational AR model;

[0040] When the user enters, continuously identifying whether the user focuses on a first AR object in the situational AR model within a first period of time;

[0041] If the answer is yes, the second AR object other than the first AR model in the situation AR model is continuously controlled to be undisplayed within a second period of time, and a third AR object with display value is selected from the second AR objects based on the interaction history between the user and the first AR object, and the third AR object is controlled to be undisplayed within a third period of time;

[0042] When the identification result is negative, the user is prompted to focus.

[0043] Optionally, the continuously identifying whether the user focuses on the first AR object in the situational AR model within the first period includes:

[0044] Continuously identifying whether a focus condition is met between the user and the first AR object within a first period of time;

[0045] If the conditions are met, it is determined that the first AR object is in focus; otherwise, it is not.

[0046] The focusing conditions include:

[0047] Condition 1: The similarity between the spatial movement trajectories of the user's two virtual operating bodies in the situation AR model exceeds a similarity threshold and the two virtual operating bodies operate the first AR object;

[0048] and / or,

[0049] Condition 2: The user operates a first AR object with a single virtual operating body in the contextual AR model, and the distance between the first AR object and the user's viewing starting position in the contextual AR model continuously does not exceed a distance threshold;

[0050] and / or,

[0051] Condition 3: The user's viewing angle in the situation AR model continuously includes only the first AR object.

[0052] Optionally, selecting a third AR object having display value from the second AR object based on the interaction history between the user and the first AR object includes:

[0053] Based on the first time period and the second time period, the interaction history is divided into a first history sequence and a second history sequence;

[0054] When there is at least one progressive relationship between a second history item in the second history sequence and a first history item in the first history sequence, generating a first object selection condition based on the corresponding second history item and other second history items within a preset range after the corresponding second history item in the second history sequence;

[0055] using the second AR object that meets the first object selection condition as the third AR object;

[0056] When the second history sequence is different from the first history sequence, generating a second object selection condition based on all second history items in the second history sequence;

[0057] using the second AR object that meets the second object selection condition as the third AR object;

[0058] When the second history sequence is partially identical to the first history sequence, generating a third object selection condition based on all second history items in the partially identical partial sequences in the second history sequence;

[0059] The second AR object that meets the third object selection condition is used as the third AR object.

[0060] Optionally, the first time period is any time period after the user enters the situation AR model, the time period being the preset first time period value;

[0061] The second time period is after the first time period and is adjacent to the first time period. The duration of the second time period is a second duration value. There is a first positive correlation between the second duration value and the proportion of the first AR object in the detection situation.

[0062] The third time period is during the second time period and is adjacent to the second time period. The duration of the third time period is a third duration value. There is a second positive correlation between the third duration value and the display value of the third AR object.

[0063] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0064] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0066] Figure 1Schematic diagram of an online detection device for finished square bars according to an embodiment of the present invention;

[0067] Figure 2 The figure is a flow chart of a method for online detection of finished square bars in an embodiment of the present invention. DETAILED DESCRIPTION

[0068] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0069] The embodiment of the present invention provides an online detection device for finished square bars, such as Figure 1 As shown, including:

[0070] Modeling module 1 is used to perform AR modeling on the inspection situation when multiple robots perform quality inspection on finished single crystal square bars, and obtain an AR model of the inspection situation if any robot reports an inspection situation to be performed online;

[0071] Auxiliary module 2 is used to assist the user in performing corresponding quality detection processing on the detection situation online based on the situation AR model.

[0072] The robot can be a visual inspection robot, which detects whether the size and surface of the single crystal finished square rod meet the requirements when performing quality inspection; if it encounters a complex situation where the inspection cannot be carried out, it will report it, that is, report the inspection situation to be carried out online quality inspection, which can be cracks on the surface of the single crystal finished square rod that the robot cannot classify, or quality problems of a large number of single crystal finished square rods at the same time; AR modeling is performed on the inspection situation. During modeling, based on the inspection information related to the inspection situation detected by the robot, the inspection situation is three-dimensionally restored and AR configuration is performed to obtain an AR model. In the AR model, the three-dimensional model of the single crystal finished square rod involved in the inspection situation can be operated, and the quality problems can be directly seen in the three-dimensional model of the single crystal finished square rod involved; finally, the user is assisted to perform corresponding quality inspection and processing on the inspection situation online based on the situation AR model; the user can be the relevant personnel assisting the inspection management of the single crystal finished square rod.

[0073] When the robot performing quality inspection on the finished single crystal square rods reports the inspection situation to be performed online for quality inspection, the present invention performs AR modeling on the inspection situation to obtain the situation AR model, and assists the user to perform corresponding quality inspection processing on the inspection situation online based on the situation AR model. There is no need for management personnel to go to the site for processing, which improves convenience and enables the inspection situation to be resolved in a timely manner, avoiding affecting the overall inspection progress of the finished single crystal square rods.

[0074] In one embodiment, the auxiliary module assists the user in performing corresponding quality inspection processing on the detection situation online based on the situation AR model, including:

[0075] S21, guiding the user into the situation AR model;

[0076] In S21, during guidance, an invitation message requiring the user to intervene in solving the detection situation through AR may be pushed to the user. After the user confirms the invitation, an AR model of the situation is pushed to the user. When the user chooses to enter the AR model of the situation, the user enters the AR model of the situation.

[0077] S22. When the user enters, continuously identifying whether the user focuses on a first AR object in the situational AR model within a first period of time;

[0078] In S22, the user can view the three-dimensional model of the single crystal finished square bar that requires online quality inspection in the situation AR model, and can also perform realistic operations on the model, such as moving, rotating, and enlarging the model. Each three-dimensional model of the single crystal finished square bar that requires online quality inspection in the situation AR model is an AR object. Therefore, it can be identified whether the user is focused on one or more AR objects. If so, the focused AR object is used as the first AR object. Focusing means that the user may be paying attention to the first AR object and / or the user may want to perform inspection on the first AR object.

[0079] S23: If the answer is yes, continue to control the second AR objects other than the first AR model in the situation AR model to cancel their display within a second period, select a third AR object with display value from the second AR objects based on the interaction history between the user and the first AR object, and then control the third AR object to cancel its display within a third period;

[0080] In S23, when it is recognized that the user is focusing on the first AR object, the second AR object is canceled to allow the user to immersively process the first AR object according to their needs in the situation AR model. At this time, the user can only view or move the first AR object. The user will have an interaction history with the first AR object during the first and second time periods. The interaction history includes at least: the part of the first AR object viewed by the user and the corresponding viewing time, and the AR operations performed by the user while viewing the first AR object. In this way, the interaction history reflects the user's current intention to perform online quality inspection. Based on this, a third AR object with display value can be selected from the second AR object based on the user's intention. Display value means that it meets the intention and display can improve the efficiency of the user's online quality inspection. For example, if the interaction history shows that the user wants to analyze abnormal cracks on the surface, the third AR object with display value is the second AR object that also has abnormal cracks on the surface. After the third AR object is determined, the display of the third AR object is controlled to be canceled. At this time, after the user immersively analyzes the first AR object, he can analyze the third AR object and compare and analyze the first and third AR objects to improve the efficiency of online quality inspection.

[0081] S24: When the identification result is negative, the user is prompted to focus.

[0082] In S24 , the user has not focused on the first AR object and needs to be prompted to focus to avoid delaying the detection progress. When prompting, relevant prompt text can be displayed in the situation AR model.

[0083] The embodiments of the present invention achieve the following beneficial effects:

[0084] By identifying the user's focus, it provides them with an immersive online quality inspection environment for the object they are focused on, effectively reducing visual interference, ensuring that users can concentrate on complex inspection tasks, and significantly improving the accuracy and efficiency of quality inspection; by real-time analysis of the user's interaction history with AR objects, the system can accurately identify user needs, intelligently filter and present AR objects with display value, thereby optimizing the inspection process and improving the user's decision-making quality and work efficiency; by dynamically adjusting the display content of the AR model, it provides a seamless operating experience and enhances the flexibility and response speed of operation.

[0085] In one embodiment, the auxiliary module continuously identifies whether the user focuses on the first AR object in the situation AR model within a first period of time, including:

[0086] Continuously identifying whether a focus condition is met between the user and the first AR object within a first period of time;

[0087] If the conditions are met, it is determined that the first AR object is in focus; otherwise, it is not.

[0088] The focusing conditions include:

[0089] Condition 1: The similarity between the spatial movement trajectories of the user's two virtual operating bodies in the situation AR model exceeds a similarity threshold and the two virtual operating bodies operate the first AR object;

[0090] and / or,

[0091] Condition 2: The user operates a first AR object with a single virtual operating body in the contextual AR model, and the distance between the first AR object and the user's viewing starting position in the contextual AR model continuously does not exceed a distance threshold;

[0092] and / or,

[0093] Condition 3: The user's viewing angle in the situation AR model continuously includes only the first AR object.

[0094] When the focus condition is met between the user and the first AR object, they are in focus, otherwise not; specifically, in the set condition one, the dual virtual operating bodies refer to the dual virtual operating hands corresponding to the user's hands, which include two virtual operating hands. If the similarity between their respective spatial movement trajectories exceeds the similarity threshold and the dual virtual operating bodies operate the first AR object, it means that the user is moving at least the first AR object continuously for comparative analysis, and then focusing is achieved. For example: the initial posture of the first AR object is the same, and if you want to view the same part of it at the same time, you need to perform the same movement, flipping, or zooming operation, and the similarity between the spatial movement trajectories of the dual virtual operating bodies will be relatively large; the similarity threshold can be set to 80%; in addition, in the set condition two, the single virtual operating body is the same as the first AR object. The virtual operator is a virtual operator corresponding to one of the user's hands. The viewing angle starting position refers to the position of the virtual camera in the situation AR model. The virtual camera shoots the picture in the situation AR model at its position and transmits it to the AR device. The user can view the corresponding picture when wearing the AR device. When a single virtual operator operates the first AR object and the distance between the first AR object and the user's viewing angle starting position in the situation AR model continues to not exceed the distance threshold, it means that the user has been operating to achieve continuous close viewing of the first AR object, and focus is also achieved. The distance threshold can be set to 1.8 meters. Secondly, in the set condition three, the viewing angle range refers to the user's visible range in the situation AR model. If the viewing angle range continuously contains only the first AR object, focus is also achieved.

[0095] The embodiments of the present invention achieve the following beneficial effects:

[0096] By comprehensively evaluating the similarity of the trajectories of the two virtual operators, the interaction distance and viewing angle range of a single virtual operator, the system can accurately capture the user's focusing behavior, effectively distinguish between the user's active attention and unintentional interaction, and significantly improve the intelligence and responsiveness of the interaction; by dynamically monitoring the user's operations and viewing angle changes, the system can seamlessly adapt to the user's diverse behavior patterns and optimize the focus locking process, thereby providing a smooth and intuitive immersive experience in complex AR scenes; multiple focusing conditions ensure that whether in different interaction modes such as two-handed collaborative operation, one-handed control, or automatic focus based on the viewing angle range, the system can accurately identify and respond to user needs, greatly improving the system's adaptability and intelligence.

[0097] In one embodiment, the auxiliary module selects a third AR object having display value from the second AR object based on the interaction history between the user and the first AR object, including:

[0098] S231. Divide the interaction history into a first history sequence and a second history sequence based on the first time period and the second time period;

[0099] In S231, the first history sequence includes interaction history items generated sequentially in a first time period, and correspondingly, the second history sequence includes interaction history items generated sequentially in a second time period;

[0100] S232: When there is at least one progressive relationship between a second history item in the second history sequence and a first history item in the first history sequence, generating a first object selection condition based on the corresponding second history item and other second history items within a preset range after the corresponding second history item in the second history sequence;

[0101] In S232, the progressive relationship refers to the second history item and the first history item reflecting that the user has performed a corresponding depth interaction in the second time period based on the basic interaction in the first time period. For example, the first history item is viewing a crack on the first AR object, and the second history item is viewing the coverage area of ​​the crack on the first AR object, etc., and there is a progressive relationship between the two. When there is a progressive relationship, the corresponding second history item and other second history items within a preset range after the corresponding second history item in the second history sequence (the corresponding second history item is a depth interaction, and a series of related depth interactions will be performed after this) fully reflect the user's current intention to perform online quality inspection, and the first object selection condition is generated based on it. For example, the second history item is viewing the coverage area of ​​the crack on the first AR object, and the other second history items after it are viewing the crack depth of the crack on the first AR object, then the first object selection condition is generated to select a second AR object with a surface crack coverage area close to the coverage area and a crack depth close to the crack depth; the preset range can be within three second history items.

[0102] S233: select the second AR object that meets the first object selection condition as the third AR object;

[0103] S234. When the second history sequence is different from the first history sequence, generate a second object selection condition based on all second history items in the second history sequence;

[0104] In S234, when the second historical sequence is different from the first historical sequence, it indicates that the first historical sequence does not reflect the actual user's intention to perform online quality inspection, while the second historical sequence does reflect (immersion quality inspection analysis assistance was performed during the second period, and the second historical sequence generated during the second period is different from the first historical sequence generated during the first period, indicating that the user actually intended to perform online quality inspection). Based on all second historical items in the second historical sequence, a second object selection condition is generated. For example, if each second historical item in the second historical sequence is a history of successively checking surface cracks of single crystal finished square bars of the same size, the second object selection condition generated is to select other single crystal finished square bars of the same size that have surface cracks.

[0105] S235: Use the second AR object that meets the second object selection condition as the third AR object;

[0106] S236: When the second history sequence is partially identical to the first history sequence, generate a third object selection condition based on all second history items in the partially identical partial sequences in the second history sequence;

[0107] In S236, if the second historical sequence is partially identical to the first historical sequence, it indicates that the second historical sequence and the first historical sequence jointly reflect the user's current intention to perform online quality inspection. Therefore, a third object selection condition is generated based on all second historical items in the partially identical local sequences in the second historical sequence. The generation of the third object selection condition based on the second historical items is similar to the generation of the first object selection condition and the second object condition, and no retrospective analysis is performed.

[0108] S237 : Use the second AR object that meets the third object selection condition as the third AR object.

[0109] The embodiments of the present invention achieve the following beneficial effects:

[0110] By accurately identifying the progressive relationship in the user's interaction history, the system can recommend AR objects that are highly relevant to the user's current needs, enhancing the intelligence and personalization of the interaction and improving the efficiency and accuracy of quality inspection; by accurately determining the corresponding object selection conditions through the situation where the first historical sequence and the second historical sequence are different from each other but partially the same, the applicability of the system is improved; by intelligently screening AR objects that meet the selection conditions, it ensures that users only receive the information most relevant to their current online quality inspection intentions during in-depth interaction, reducing information redundancy and improving the effectiveness of information processing.

[0111] In one embodiment, the first time period is any time period after the user enters the situation AR model, the time period being the preset first time period value;

[0112] The second time period is after the first time period and is adjacent to the first time period. The duration of the second time period is a second duration value. There is a first positive correlation between the second duration value and the proportion of the first AR object in the detection situation.

[0113] The third time period is during the second time period and is adjacent to the second time period. The duration of the third time period is a third duration value. There is a second positive correlation between the third duration value and the display value of the third AR object.

[0114] The first duration value can be 100 seconds; the situation ratio refers to the ratio of the relevant situation elements of the first AR object in the detection situation to all the situation elements of the detection situation; the larger the situation ratio, the more time the user needs to spend on online quality detection and analysis of the first AR object, and the larger the second duration value. Therefore, there is a first positive correlation between the two. The specific conversion ratio of the first positive correlation can be set in advance by technical personnel according to actual needs; the display value of the third AR object refers to the number of the above-mentioned conditions one, two, and three that it meets. The larger the number, the more conditions it meets, the greater the local display value, and the more time the user needs to spend on analyzing and comparing the first AR object and the third AR object separately. Therefore, there is a second positive correlation between the two. Similarly, the specific conversion ratio of the second positive correlation can be set in advance by technical personnel according to actual needs.

[0115] The embodiments of the present invention achieve the following beneficial effects:

[0116] According to the complexity of the detection situation and the display value of the AR object, the duration of each time period is automatically adjusted, so that the user's operation time in different situations is more reasonable, avoiding information overload or too little, improving the rationality of system resource allocation, and enhancing the user experience.

[0117] The embodiment of the present invention provides a method for online detection of finished square bars. Figure 2 As shown, including:

[0118] S1. When multiple robots perform quality inspection on finished single crystal square bars, if any robot reports a test situation to be tested online, AR modeling is performed on the test situation to obtain a situation AR model.

[0119] S2. Assist the user to perform corresponding quality inspection and processing on the inspection situation online based on the situation AR model.

[0120] The auxiliary user performs corresponding quality detection processing on the detection situation online based on the situation AR model, including:

[0121] Guide users into the situational AR model;

[0122] When the user enters, continuously identifying whether the user focuses on a first AR object in the situational AR model within a first period of time;

[0123] If the answer is yes, the second AR object other than the first AR model in the situation AR model is continuously controlled to be undisplayed within a second period of time, and a third AR object with display value is selected from the second AR objects based on the interaction history between the user and the first AR object, and the third AR object is controlled to be undisplayed within a third period of time;

[0124] When the identification result is negative, the user is prompted to focus.

[0125] The continuously identifying whether the user focuses on the first AR object in the situation AR model within the first period includes:

[0126] Continuously identifying whether a focus condition is met between the user and the first AR object within a first period of time;

[0127] If the conditions are met, it is determined that the first AR object is in focus; otherwise, it is not.

[0128] The focusing conditions include:

[0129] Condition 1: The similarity between the spatial movement trajectories of the user's two virtual operating bodies in the situation AR model exceeds a similarity threshold and the two virtual operating bodies operate the first AR object;

[0130] and / or,

[0131] Condition 2: The user operates a first AR object with a single virtual operating body in the contextual AR model, and the distance between the first AR object and the user's viewing starting position in the contextual AR model continuously does not exceed a distance threshold;

[0132] and / or,

[0133] Condition 3: The user's viewing angle in the situation AR model continuously includes only the first AR object.

[0134] The selecting, from the second AR object, a third AR object having display value based on the interaction history between the user and the first AR object includes:

[0135] Based on the first time period and the second time period, the interaction history is divided into a first history sequence and a second history sequence;

[0136] When there is at least one progressive relationship between a second history item in the second history sequence and a first history item in the first history sequence, generating a first object selection condition based on the corresponding second history item and other second history items within a preset range after the corresponding second history item in the second history sequence;

[0137] using the second AR object that meets the first object selection condition as the third AR object;

[0138] When the second history sequence is different from the first history sequence, generating a second object selection condition based on all second history items in the second history sequence;

[0139] using the second AR object that meets the second object selection condition as the third AR object;

[0140] When the second history sequence is partially identical to the first history sequence, generating a third object selection condition based on all second history items in the partially identical partial sequences in the second history sequence;

[0141] The second AR object that meets the third object selection condition is used as the third AR object.

[0142] The first time period is any time period after the user enters the situation AR model, which is equal to the preset first time period;

[0143] The second time period is after the first time period and is adjacent to the first time period. The duration of the second time period is a second duration value. There is a first positive correlation between the second duration value and the proportion of the first AR object in the detection situation.

[0144] The third time period is during the second time period and is adjacent to the second time period. The duration of the third time period is a third duration value. There is a second positive correlation between the third duration value and the display value of the third AR object.

[0145] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A finished square bar online detection device, characterized in that: include: A modeling module is used to perform AR modeling on the inspection situation when multiple robots perform quality inspection on finished single crystal square bars. If any robot reports an inspection situation to be performed online, the inspection situation is modeled to obtain an AR model of the situation. Auxiliary module, used to assist users in performing corresponding quality inspection and processing of the inspection situation online based on the situation AR model; The auxiliary module assists the user in performing corresponding quality inspection and processing of the inspection situation online based on the situation AR model, including: Guide users into the situational AR model; When the user enters, continuously identifying whether the user focuses on a first AR object in the situational AR model within a first period of time; If the answer is yes, the second AR object other than the first AR model in the situation AR model is continuously controlled to be undisplayed within a second period of time, and a third AR object with display value is selected from the second AR objects based on the interaction history between the user and the first AR object, and the third AR object is controlled to be undisplayed within a third period of time; When the recognition result is negative, the user is prompted to focus; The auxiliary module selects a third AR object having display value from the second AR object based on the interaction history between the user and the first AR object, including: Based on the first time period and the second time period, the interaction history is divided into a first history sequence and a second history sequence; When there is at least one progressive relationship between a second history item in the second history sequence and a first history item in the first history sequence, generating a first object selection condition based on the corresponding second history item and other second history items within a preset range after the corresponding second history item in the second history sequence; using the second AR object that meets the first object selection condition as the third AR object; When the second history sequence is different from the first history sequence, generating a second object selection condition based on all second history items in the second history sequence; using the second AR object that meets the second object selection condition as the third AR object; When the second history sequence is partially identical to the first history sequence, generating a third object selection condition based on all second history items in the partially identical partial sequences in the second history sequence; using the second AR object that meets the third object selection condition as the third AR object; The first time period is any time period after the user enters the situation AR model, which is equal to the preset first time period; The second time period is after the first time period and is adjacent to the first time period. The duration of the second time period is a second duration value. There is a first positive correlation between the second duration value and the proportion of the first AR object in the detection situation. The third time period is after the second time period and is adjacent to the second time period. The duration of the third time period is a third duration value. There is a second positive correlation between the third duration value and the display value of the third AR object.

2. The online detection device for finished square bars according to claim 1, characterized in that: The auxiliary module continuously identifies whether the user focuses on the first AR object in the situation AR model within a first period of time, including: Continuously identifying whether a focus condition is met between the user and the first AR object within a first period of time; If the conditions are met, it is determined that the first AR object is in focus; otherwise, it is not. The focusing conditions include: Condition 1: The similarity between the spatial movement trajectories of the user's two virtual operating bodies in the situation AR model exceeds a similarity threshold and the two virtual operating bodies operate the first AR object; and / or, Condition 2: The user operates a first AR object with a single virtual operating body in the contextual AR model, and the distance between the first AR object and the user's viewing starting position in the contextual AR model continuously does not exceed a distance threshold; and / or, Condition 3: The user's viewing angle in the situation AR model continuously includes only the first AR object.

3. A method for online detection of finished square bars, characterized in that: include: When multiple robots perform quality inspection on finished single crystal square bars, if any robot reports a test situation to be tested online, AR modeling is performed on the test situation to obtain a situation AR model. Assist users to conduct corresponding quality inspection and processing of the inspection situation online based on the situation AR model; The auxiliary user performs corresponding quality detection processing on the detection situation online based on the situation AR model, including: Guide users into the situational AR model; When the user enters, continuously identifying whether the user focuses on a first AR object in the situational AR model within a first period of time; If the answer is yes, the second AR object other than the first AR model in the situation AR model is continuously controlled to be undisplayed within a second period of time, and a third AR object with display value is selected from the second AR objects based on the interaction history between the user and the first AR object, and the third AR object is controlled to be undisplayed within a third period of time; When the recognition result is negative, the user is prompted to focus; The selecting, from the second AR object, a third AR object having display value based on the interaction history between the user and the first AR object includes: Based on the first time period and the second time period, the interaction history is divided into a first history sequence and a second history sequence; When there is at least one progressive relationship between a second history item in the second history sequence and a first history item in the first history sequence, generating a first object selection condition based on the corresponding second history item and other second history items within a preset range after the corresponding second history item in the second history sequence; using the second AR object that meets the first object selection condition as the third AR object; When the second history sequence is different from the first history sequence, generating a second object selection condition based on all second history items in the second history sequence; using the second AR object that meets the second object selection condition as the third AR object; When the second history sequence is partially identical to the first history sequence, generating a third object selection condition based on all second history items in the partially identical partial sequences in the second history sequence; using the second AR object that meets the third object selection condition as the third AR object; The first time period is any time period after the user enters the situation AR model, which is equal to the preset first time period; The second time period is after the first time period and is adjacent to the first time period. The duration of the second time period is a second duration value. There is a first positive correlation between the second duration value and the proportion of the first AR object in the detection situation. The third time period is after the second time period and is adjacent to the second time period. The duration of the third time period is a third duration value. There is a second positive correlation between the third duration value and the display value of the third AR object.

4. The online detection method for finished square bars according to claim 3, characterized in that: The continuously identifying whether the user focuses on the first AR object in the situation AR model within the first period includes: Continuously identifying whether a focus condition is met between the user and the first AR object within a first period of time; If the conditions are met, it is determined that the first AR object is in focus; otherwise, it is not. The focusing conditions include: Condition 1: The similarity between the spatial movement trajectories of the user's two virtual operating bodies in the situation AR model exceeds a similarity threshold and the two virtual operating bodies operate the first AR object; and / or, Condition 2: The user operates a first AR object with a single virtual operating body in the contextual AR model, and the distance between the first AR object and the user's viewing starting position in the contextual AR model continuously does not exceed a distance threshold; and / or, Condition 3: The user's viewing angle in the situation AR model continuously includes only the first AR object.

Images