Script-based detection method and device, equipment, medium and product

Abstract

The invention discloses a script-based detection method and device, equipment, a medium and a product. The method comprises the following steps: inputting a standard three-dimensional model and an actual three-dimensional model corresponding to a to-be-detected product and detection demand information into a pre-trained language analysis model to obtain detection search information; determining at least one to-be-detected task from a preset detection task library based on the detection search information; and detecting the standard three-dimensional model and the actual three-dimensional model based on a to-be-detected execution script corresponding to the at least one to-be-detected task to obtain a detection result corresponding to the to-be-detected product. The problem that in the prior art, existing three-dimensional detection software is used for product detection, and the detection cost is high is solved, and the detection efficiency and the detection result determination accuracy are improved while the detection task is efficiently and automatically generated.

Description

Technical Field

[0001] The present invention relates to the field of computer processing technologies, and in particular, to a script-based detection method, device, equipment, medium, and product. Background Art

[0002] In order to ensure the quality of a product, it is usually necessary to detect the reference model and the scanned model of the product. The current detection method usually uses existing 3D detection software to perform feature measurement and comparison on the reference model and the scanned model.

[0003] This detection method not only has relatively high requirements for the detection user, but also has the problem of relatively high software detection cost. Summary of the Invention

[0004] The present invention provides a script-based detection method, device, equipment, medium, and product to achieve efficient automatic generation of detection tasks while improving the detection efficiency and the accuracy of determining the detection result.

[0005] According to one aspect of the present invention, there is provided a script-based detection method, the method comprising:

[0006] Inputting a standard 3D model, an actual 3D model corresponding to the product to be detected, and detection requirement information into a pre-trained language parsing model to obtain detection search information;

[0007] Determining at least one detection task to be detected from a preset detection task library based on the detection search information;

[0008] Detecting the standard 3D model and the actual 3D model based on a detection execution script corresponding to at least one detection task to be detected to obtain a detection result corresponding to the product to be detected.

[0009] According to another aspect of the present invention, there is provided a script-based detection device, the device comprising:

[0010] A detection search information determination module, configured to input a standard 3D model, an actual 3D model corresponding to the product to be detected, and detection requirement information into a pre-trained language parsing model to obtain detection search information;

[0011] A detection task to be detected determination module, configured to determine at least one detection task to be detected from a preset detection task library based on the detection search information;

[0012] A detection result determination module, configured to detect the standard 3D model and the actual 3D model based on a detection execution script corresponding to at least one detection task to be detected to obtain a detection result corresponding to the product to be detected.

[0013] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0014] at least one processor; and a memory communicatively connected to the at least one processor; wherein,

[0015] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the script-based detection method according to any embodiment of the present invention.

[0016] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the script-based detection method according to any embodiment of the present invention when executed.

[0017] According to another aspect of the present invention, there is provided a computer program product including a computer program which, when executed by a processor, implements the script-based detection method according to any embodiment of the present invention.

[0018] The technical solution of the embodiment of the present invention inputs the standard three-dimensional model, the actual three-dimensional model corresponding to the product to be detected, and the detection requirement information into a pre-trained language parsing model to obtain detection search information. Furthermore, at least one task to be detected is determined from a preset detection task library based on the detection search information. Finally, the standard three-dimensional model and the actual three-dimensional model are detected based on the detection execution script corresponding to at least one task to be detected, and a detection result corresponding to the product to be detected is obtained, solving the problem of high detection cost in the prior art when using existing three-dimensional detection software for product detection. It realizes generating specific detection search information by inputting the standard three-dimensional model, the actual three-dimensional model, and the detection requirement information into a pre-trained language parsing model. Then, at least one task to be detected is matched from a preset detection condition library based on the detection search information, which can realize efficient automatic generation of detection tasks. Furthermore, the standard three-dimensional model and the actual three-dimensional model are detected based on the detection execution script corresponding to at least one task to be detected, improving the detection efficiency and the accuracy of determining the detection result, thereby ensuring the precision and quality of the product.

[0019] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0021] Figure 1 is a flowchart of a script-based detection method provided in Embodiment 1 of the present invention;

[0022] Figure 2 is a schematic flowchart of a script-based detection method provided in Embodiment 2 of the present invention;

[0023] Figure 3 is a schematic structural diagram of a script-based detection device provided in Embodiment 3 of the present invention;

[0024] Figure 4 is a schematic structural diagram of an electronic device for implementing the script-based detection method of the embodiments of the present invention. Detailed implementation manners

[0025] In order to enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above accompanying drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0027] Embodiment 1

[0028] Figure 1FIG. 0 is a flowchart of a script-based detection method according to Embodiment 1 of the present invention. This embodiment is applicable to the situation of detecting 3D model products based on scripts. This method can be executed by a script-based detection device, which can be implemented in the form of hardware and / or software, and can be configured in a computing device. As Figure 1 shown, the method includes:

[0029] S110. Input a standard 3D model, an actual 3D model corresponding to the product to be detected, and detection requirement information into a pre-trained language parsing model to obtain detection search information.

[0030] Among them, the product to be detected can refer to those products that have completed production and processing but have not been subjected to relevant detections. Although these products have completed all production processes, they still need to undergo relevant detections to determine whether they meet relevant quality standards and set requirements. The standard 3D model can refer to the standard design model of the product to be detected, which reflects the ideal state of the product to be detected in the design stage. That is, the standard 3D model is the benchmark for product production, and all production processes refer to this model. The standard 3D model has the characteristics of accuracy and integrity, and it contains all geometric features and dimension information of the product, etc. The actual 3D model can be the 3D representation of the product to be detected after actual production and manufacturing, which reflects the real state of the product to be detected in actual production. In practical applications, the actual 3D model of the product to be detected can be obtained through 3D scanners, laser scanners, CT scans, or other measurement technologies. The detection requirement information can be the detection requirements described in natural language, such as requirements for detection range, accuracy, or standards. For example, the detection requirement information can be "detect the dimensional deviation of the product" or "check whether there are cracks on the surface", etc. The language parsing model is used to determine specific detection search information. The detection search information is generated by the language parsing model and can refer to relevant input data or conditions for guiding and screening detection tasks. For example, the detection search information includes, but is not limited to, user requirements, detection targets, detection items, detection keywords, detailed semantic descriptions of detection requirements, relevant context information, detection methods, detection tools, preset rules or standards, preset thresholds or conditions, and so on.

[0031] In this embodiment, the standard 3D model and the actual 3D model corresponding to the product to be detected can be obtained, and the standard 3D model, the actual 3D model, and the detection requirement information are used as the input data of the language parsing model, and the detection search information is obtained based on the output data of the language parsing model.

[0032] Exemplarily, a detection requirement input control can be developed in advance, and the user can input the detection requirement information for the product to be detected in the detection requirement input control. Synchronously, the standard 3D model and the actual 3D model corresponding to the product to be detected can be imported into the system. After receiving this information, the system integrates these input information and inputs them into a pre-trained language parsing model to obtain detection search information, so as to adapt to and enrich the detection requirement description and improve the detection effect.

[0033] S120. Determine at least one task to be detected from a preset detection task library based on the detection search information.

[0034] Among them, the preset detection task library is a preset set of detection tasks, and each detection task can be one or more detection rules or detection items. The task to be detected refers to a specific detection task description.

[0035] In this embodiment, keywords (such as "dimension deviation") can be extracted from the detection search information, and a matching algorithm is used to find the detection task most relevant to the detection search information in the preset detection task library as the task to be detected. Optionally, the matching algorithm can include, but is not limited to, string matching algorithms (such as Brute Force Matching Algorithm, Knuth-Morris-Pratt Matching Algorithm, Boyer-Moore matching algorithm (a matching algorithm based on the position law of character occurrences), Rabin-Karp algorithm (a string matching algorithm based on a hash function)), matching algorithms based on machine learning models (such as SVM, Random Forest, XGBoost), semantic similarity, Jaccard similarity coefficient, best fit alignment (combining keywords and semantic matching), etc.

[0036] Exemplarily, the task to be detected can be: using method A to compare the dimension differences between the standard 3D model and the actual 3D model, with an allowable error range of ±0.1 mm; using method B to detect surface cracks on the model, with a crack width threshold < 0.05 mm.

[0037] In this embodiment, determining at least one task to be detected from a preset detection task library based on the detection search information includes: determining at least one detection task to be selected that matches the detection search information from the preset detection task library; processing the at least one detection task to be selected to obtain at least one task to be detected.

[0038] Specifically, a preset matching method can be used to screen out the to-be-selected detection tasks related to the detection search information from the preset detection task library. The preset matching method can be a keyword matching method (such as extracting keywords in the detection search information and matching them with the detection task keywords in the detection condition library); or, a semantic matching method (such as using the semantic understanding ability of a language model to calculate the semantic similarity between the detection search information and the detection task description in the detection condition library)); or, a context matching method (such as screening detection tasks according to the context information in the detection search information (such as product type, detection environment, etc.)). Further, the to-be-selected detection tasks can be further processed, such as integrated processing and secondary screening processing, and the processed detection tasks are used as the to-be-detected tasks.

[0039] In this embodiment, processing at least one to-be-selected detection task to obtain at least one to-be-detected task includes: filtering at least one to-be-selected detection task to obtain at least one to-be-detected task.

[0040] Specifically, filtering at least one to-be-selected detection task to obtain at least one to-be-detected task can be: sorting all to-be-selected detection tasks according to keyword matching degree, semantic similarity, and context information, arranging the detection tasks with the highest matching degree with the detection search information in the front, and taking the front preset number of detection tasks as the to-be-detected tasks. Or, further screening the to-be-selected detection tasks according to preset filtering rules (such as the priority of the detection task, detection cost, detection time, etc.) to obtain the to-be-detected tasks. Or, if there are multiple to-be-selected detection tasks, they can be provided to the detection user to select the to-be-detected tasks, or the most suitable to-be-detected tasks can be automatically selected according to the user's historical preferences.

[0041] The technical solution provided in this embodiment screens out the to-be-selected detection tasks from the preset detection task library, processes these detection tasks further, and finally determines the to-be-detected tasks. It can improve the detection accuracy and detection efficiency at the same time. Meanwhile, it can better meet the complex detection needs of users.

[0042] In this embodiment, at least one custom detection task can also be determined; analyzing at least one custom detection task and at least one general detection task in the preset detection task library to obtain extended detection tasks; storing the custom detection tasks and / or extended detection tasks in the preset detection task library to determine at least one to-be-detected task from the preset detection task library based on the detection search information.

[0043] Among them, the general detection tasks can refer to common, necessary, or standardized detection tasks, which are initially stored in a preset detection task library. The custom detection tasks can be detection tasks dynamically defined according to specific requirements or user inputs, and support adjustment or optimization. The extended detection tasks can refer to new optimized detection tasks obtained based on the analysis of existing detection tasks.

[0044] In this embodiment, a detection task configuration page can be developed in advance, and users can customize and configure custom detection tasks on the detection task configuration page. At the same time, the general detection tasks and custom detection tasks can be analyzed for relevance through a rule engine or machine learning algorithm to obtain extended detection tasks. For example, both the general detection task A and the defined detection task A belong to the same type of defect detection, and these two tasks can be combined into one extended detection task. Or, according to the descriptions of the general detection task and the custom detection task, relevant detection content can be supplemented to obtain an extended detection task. Or, further, according to the natural language description input by the user, the general detection task or the custom detection task can be further refined to be extended into at least one extended detection task. Further, the custom detection tasks and / or extended detection tasks can be stored in the preset detection task library so that at least one task to be detected can be determined from these detection tasks in the preset detection task library based on the detection search information.

[0045] The technical solution provided in this embodiment can not only dynamically adjust the detection tasks according to user inputs and dynamically expand the detection condition library by determining the general detection tasks and custom detection tasks, generating extended detection tasks, and storing these detection tasks in the preset detection task library, but also improve the flexibility and adaptability of detection.

[0046] S130: Based on the detection execution script corresponding to at least one task to be detected, detect the standard 3D model and the actual 3D model to obtain the detection result corresponding to the product to be detected.

[0047] Among them, the detection execution script can be a code file used to implement the task to be detected that needs to be executed. The detection result can refer to the result obtained after detecting the model of the product to be detected, such as dimensional deviation, defect location, etc.

[0048] In this embodiment, the detection execution script corresponding to each task to be detected can be retrieved from a preset script library. Or, each task to be detected can also be compiled separately to obtain the detection execution script corresponding to each task to be detected. Further, run the detection execution script to detect the standard 3D model and the actual 3D model, and the running result of the detection execution script is the detection result corresponding to the product to be detected.

[0049] In this embodiment, based on the to-be-detected execution scripts corresponding to at least one to-be-detected task, the standard 3D model and the actual 3D model are detected to obtain the detection results corresponding to the to-be-detected product, including: for each to-be-detected task, determining the to-be-detected execution script mapped to the to-be-detected task from at least one to-be-executed script; detecting the standard 3D model and the actual 3D model based on each to-be-detected execution script to obtain the detection results corresponding to the to-be-detected product.

[0050] Among them, the to-be-executed script can be a code file for implementing the detection task.

[0051] Specifically, the script mapped to each to-be-detected task can be determined from at least one to-be-executed script as the to-be-detected execution script. Further, the standard 3D model and the actual 3D model are respectively detected using each to-be-detected execution script, so as to obtain the detection results corresponding to the to-be-detected product.

[0052] In this embodiment, at least one detection task in the preset detection task library can also be loaded into the script editor; each detection task is respectively compiled based on the script editor to obtain the to-be-executed script corresponding to each detection task; a mapping relationship is established between each detection task and its corresponding to-be-executed script, so as to determine the to-be-detected execution script mapped to the to-be-detected task from at least one to-be-executed script based on the mapping relationship.

[0053] Among them, the script editor is used to load the detection task information and convert it into executable script code.

[0054] Specifically, at least one detection task can be read from the preset detection task library and the read at least one detection task is passed to the script editor. Furthermore, the script editor performs lexical analysis and syntax analysis on the received detection task, and compiles the detection task in combination with the analysis results to generate the specific to-be-executed script corresponding to the detection task. Further, a mapping relationship is established between the detection task and the to-be-executed script corresponding to the detection task, and the mapping relationship is stored in a configuration file or a database. So that when determining the to-be-detected execution script mapped to the to-be-detected task from at least one to-be-executed script, the corresponding to-be-executed script can be found according to the mapping relationship as the to-be-detected execution script to execute the corresponding detection task.

[0055] Exemplarily, the detection task cluster can be loaded into the script editor, and the script editor performs immediate compilation through lexical analysis and syntax analysis, converts the detection task into machine code in bytecode form to generate the to-be-executed script, and stores the to-be-executed script in the database for subsequent calling.

[0056] The technical solution provided in this embodiment loads a detection task from a preset detection task library, generates a script to be executed, and establishes a mapping relationship between the detection task and the script, which facilitates quickly adjusting the detection logic according to the detection task. At the same time, it can realize the automatic execution of the detection task based on the script, improving the speed and flexibility of the detection task execution.

[0057] It should be noted that after obtaining the detection result corresponding to the product to be detected, one or more of the standard three-dimensional model and the actual three-dimensional model corresponding to the product to be detected, the detection requirement information, the detection result corresponding to the product to be detected, the detection search information, and the detection task to be detected can also be stored in the historical database. These data can be stored as structured data (such as in tabular form) or unstructured data (such as model files, text descriptions, etc.). Furthermore, based on these stored data in the historical database, an updated language parsing model can be trained. For example, based on the detection result corresponding to the product to be detected, the corresponding detection search information can be corrected. The standard three-dimensional model and the actual three-dimensional model corresponding to the product to be detected, as well as the detection requirement information, are used as input data in the training sample, and the corrected detection search information is used as the theoretical label of the input data in the training sample. The language parsing model is trained based on the training sample, and the model parameters of the language parsing model are corrected to improve the model accuracy, thereby improving the accuracy of product detection.

[0058] Data mining can also be performed on these stored data in the historical database to obtain extended detection tasks, thereby updating the preset detection task library. For example, according to the detection result or detection task of the product to be detected, it is compared with the detection requirement information to extract new detection requirements, that is, the detection requirements not covered by the detection task, and a detection task corresponding to the new detection requirement is generated as an extended detection task; or, according to the new detection requirement, the existing detection task is adjusted to obtain an extended detection task. It is also possible to analyze the detection error of the detection result of the product to be detected. If the detection error does not meet the preset requirements, an extended detection task with higher accuracy can be generated. By processing the stored data in the historical database through data mining technology, new detection requirements can be effectively detected, more types of extended detection tasks can be generated, and the extended detection tasks are updated to the preset detection task library, improving the convenience of generating detection tasks while continuously improving the detection accuracy and comprehensiveness.

[0059] The technical solution provided by the embodiments of the present invention is to input the standard three-dimensional model, the actual three-dimensional model corresponding to the product to be detected, and the detection requirement information into a pre-trained language parsing model to obtain detection search information. Furthermore, at least one detection task to be detected is determined from a preset detection task library based on the detection search information. Finally, the standard three-dimensional model and the actual three-dimensional model are detected based on the detection execution script corresponding to at least one detection task to be detected, and the detection result corresponding to the product to be detected is obtained, which solves the problem of high detection cost in the prior art when using existing three-dimensional detection software for product detection. It realizes that by inputting the standard three-dimensional model, the actual three-dimensional model, and the detection requirement information into the pre-trained language parsing model to generate specific detection search information. Then, at least one detection task to be detected is matched from the preset detection condition library based on the detection search information, which can realize efficient automatic generation of detection tasks. Furthermore, the standard three-dimensional model and the actual three-dimensional model are detected based on the detection execution script corresponding to at least one detection task to be detected, improving the detection efficiency and the accuracy of determining the detection result, thus ensuring the precision and quality of the product.

[0060] Embodiment 2

[0061] As an optional embodiment of the above embodiment, in order to make those skilled in the art further understand the technical solution of the embodiments of the present invention, a specific application scenario example is given. Specifically, the following specific content can be referred to.

[0062] See Figure 2 , the detection requirement information in natural language can be transmitted to the language parsing model for parsing to obtain the refined user requirement content (i.e., the detection search information); the user requirement content is transmitted to the detection task parser for detection task parsing and aggregation to obtain at least one detection task to be detected. The detection tasks to be detected include but are not limited to general detection tasks (basic detection tasks formulated by the software system for guiding important core detections, initially stored in the database), custom detection tasks (detection tasks open to users for custom settings to help users add custom detection task clusters, and these detection tasks will be stored in the data warehouse), and extended detection tasks (including new detection tasks obtained by mining and analyzing historical data based on the historical database). Further, the detection tasks to be detected are loaded into the script editor, and the script editor performs immediate compilation through lexical analysis and syntax analysis, converting the bytecode into machine code, that is, converting the detection tasks to be detected into detection execution scripts. Finally, the detection execution scripts are executed, and the detection data is stored in the real-time database and the historical database in the data warehouse. The detection result is generated according to the data of the running detection execution script, and the detection report is output to complete this detection. It is also possible to perform the next detection cycle in combination with an automated detection process.

[0063] The technical solution provided in this embodiment converts the detection requirements from natural language into detection search information for searching the detection task set by combining a language parsing model, enabling the parsing of the user's detection requirements like an intelligent AI, and then generating detection tasks recognizable by a computer, thereby improving the convenience and accuracy of detection. At the same time, it supports users to participate in the formulation of detection tasks. While meeting the complex detection requirements of users, it can also mine and analyze data based on the historical database to form a new detection task set to assist in detection decision-making, optimize detection tasks, and improve detection efficiency and quality.

[0064] Embodiment III

[0065] Figure 3 is a schematic structural diagram of a script-based detection device provided according to Embodiment III of the present invention. As Figure 3 shown, the device includes: a detection search information determination module 210, a to-be-detected task determination module 220, and a detection result determination module 230.

[0066] Among them, the detection search information determination module 210 is configured to input the standard three-dimensional model, the actual three-dimensional model, and the detection requirement information corresponding to the product to be detected into a pre-trained language parsing model to obtain detection search information; the to-be-detected task determination module 220 is configured to determine at least one to-be-detected task from a preset detection task library based on the detection search information; the detection result determination module 230 is configured to detect the standard three-dimensional model and the actual three-dimensional model based on the to-be-detected execution script corresponding to at least one to-be-detected task to obtain a detection result corresponding to the product to be detected.

[0067] The technical solution of this embodiment inputs the standard three-dimensional model, the actual three-dimensional model, and the detection requirement information corresponding to the product to be detected into a pre-trained language parsing model to obtain detection search information. Furthermore, based on the detection search information, at least one to-be-detected task is determined from a preset detection task library. Finally, based on the to-be-detected execution script corresponding to at least one to-be-detected task, the standard three-dimensional model and the actual three-dimensional model are detected to obtain a detection result corresponding to the product to be detected, solving the problem of high detection cost in the prior art when using existing three-dimensional detection software for product detection. It realizes generating specific detection search information by inputting the standard three-dimensional model, the actual three-dimensional model, and the detection requirement information into a pre-trained language parsing model. Then, based on the detection search information, at least one to-be-detected task is matched from a preset detection condition library, which can achieve efficient automatic generation of detection tasks. Furthermore, based on the to-be-detected execution script corresponding to at least one to-be-detected task, the standard three-dimensional model and the actual three-dimensional model are detected, improving the detection efficiency and the accuracy of determining the detection result, thereby ensuring the precision and quality of the product.

[0068] Based on the above device, optionally, the to-be-detected task determination module 220 includes:

[0069] A to-be-selected detection task determination unit, configured to determine at least one to-be-selected detection task that matches the detection search information from a preset detection task library;

[0070] A to-be-detected task determination unit, configured to process at least one of the to-be-selected detection tasks to obtain at least one to-be-detected task.

[0071] Based on the above device, optionally, the to-be-detected task determination unit includes:

[0072] A to-be-detected task determination subunit, configured to filter at least one of the to-be-selected detection tasks to obtain at least one to-be-detected task.

[0073] Based on the above device, optionally, the device further includes:

[0074] A custom detection task determination unit, configured to determine at least one custom detection task;

[0075] An extended detection task determination unit, configured to analyze at least one of the custom detection tasks and at least one general detection task in the preset detection task library to obtain extended detection tasks;

[0076] A storage unit, configured to store the custom detection task and / or the extended detection task into the preset detection task library, so as to determine at least one to-be-detected task from the preset detection task library based on the detection search information.

[0077] Based on the above device, optionally, the detection result determination module 230 includes:

[0078] A to-be-detected execution script determination unit, configured to determine, for each of the to-be-detected tasks, a to-be-detected execution script that maps to the to-be-detected task from at least one to-be-executed script;

[0079] A detection result determination unit, configured to perform detection on the standard 3D model and the actual 3D model based on each of the to-be-detected execution scripts to obtain a detection result corresponding to the to-be-detected product.

[0080] Based on the above device, optionally, the device further includes:

[0081] A task loading unit, configured to load at least one detection task in the preset detection task library into a script editor;

[0082] A to-be-executed script determination unit, configured to compile each of the detection tasks respectively based on the script editor to obtain a to-be-executed script corresponding to each detection task;

[0083] A mapping relationship determination unit, configured to establish a mapping relationship between each of the detection tasks and its corresponding to-be-executed script, so as to determine a to-be-detected execution script mapped to the to-be-detected task from at least one to-be-executed script based on the mapping relationship.

[0084] The script-based detection device provided by the embodiment of the present invention can execute the script-based detection method provided by any embodiment of the present invention, and has function modules and beneficial effects corresponding to the execution method.

[0085] Embodiment 4

[0086] Figure 4 It is a schematic structural diagram of an electronic device for implementing the script-based detection method of the embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0087] As Figure 4 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor, and the processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0088] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0089] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the script-based detection method.

[0090] In some embodiments, the script-based detection method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the script-based detection method described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the script-based detection method by any other suitable means (e.g., by means of firmware).

[0091] The various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0092] A computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0093] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0094] In order to provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0095] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0096] A computing system can include a client and a server. The client and the server are generally far from each other and typically interact through a communication network. The client-server relationship is created by computer programs that run on respective computers and have a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0097] An embodiment of the present invention also provides a computer program product, including a computer program, which when executed by a processor, implements the script-based detection method provided in any embodiment of the present invention.

[0098] In the process of implementing the computer program product, computer program code for performing the operations of the present invention can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or can be connected to an external computer (e.g., connected through the Internet using an Internet service provider).

[0099] It should be understood that the various forms of processes shown above can be used, with steps reordered, added or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and this is not limited herein.

[0100] The above specific embodiments do not constitute a limitation to the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub - combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A script-based detection method, characterized in that, Including: Inputting a standard 3D model, an actual 3D model corresponding to the product to be detected, and detection requirement information into a pre-trained language parsing model to obtain detection search information; Determining at least one detection task to be performed from a preset detection task library based on the detection search information; Detecting the standard 3D model and the actual 3D model based on a detection execution script corresponding to at least one detection task to be performed, and obtaining a detection result corresponding to the product to be detected.

2. The method according to claim 1, wherein The determining at least one detection task to be performed from a preset detection task library based on the detection search information includes: Determining at least one detection task to be selected that matches the detection search information from a preset detection task library; Processing at least one of the detection tasks to be selected to obtain at least one detection task to be performed.

3. The method according to claim 2, wherein The processing at least one of the detection tasks to be selected to obtain at least one detection task to be performed includes: Filtering at least one of the detection tasks to be selected to obtain at least one detection task to be performed.

4. The method according to claim 1, wherein The method further includes: Determining at least one custom detection task; Analyzing at least one of the custom detection tasks and at least one general detection task in a preset detection task library to obtain an extended detection task; Storing the custom detection task and / or the extended detection task into the preset detection task library, so as to determine at least one detection task to be performed from the preset detection task library based on the detection search information.

5. The method according to claim 1, wherein The detecting the standard 3D model and the actual 3D model based on a detection execution script corresponding to at least one detection task to be performed, and obtaining a detection result corresponding to the product to be detected includes: For each of the detection tasks to be performed, determining a detection execution script that maps to the detection task to be performed from at least one execution script; Detecting the standard 3D model and the actual 3D model based on each of the detection execution scripts, and obtaining a detection result corresponding to the product to be detected.

6. The method according to claim 5, wherein The method further includes: Loading at least one detection task in a preset detection task library into a script editor; Compiling each of the detection tasks respectively based on the script editor to obtain an execution script corresponding to each of the detection tasks; Establishing a mapping relationship between each of the detection tasks and its corresponding execution script, so as to determine a detection execution script that maps to the detection task to be performed from at least one execution script based on the mapping relationship.

7. A script-based detection device, characterized in that, Including: A detection search information determination module, configured to input a standard 3D model, an actual 3D model corresponding to the product to be detected, and detection requirement information into a pre-trained language parsing model to obtain detection search information; A detection task to be performed determination module, configured to determine at least one detection task to be performed from a preset detection task library based on the detection search information; A detection result determination module, configured to detect the standard 3D model and the actual 3D model based on a detection execution script corresponding to at least one detection task to be performed, and obtain a detection result corresponding to the product to be detected.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the script-based detection method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for implementing the script-based detection method according to any one of claims 1-6 when the computer instructions are executed by a processor.

10. A computer program product, comprising a computer program, characterized in that, The computer program, when executed by a processor, implements the script-based detection method according to any one of claims 1-6.

Images