Method, device and equipment for flexibly configuring and expanding quality inspection rule of point cloud labeling result and storage medium

Abstract

The invention discloses a method, a device, equipment and a storage method for flexibly configuring and expanding quality inspection rules of a point cloud labeling result, which are used for information processing of a point cloud labeling structure and comprise the following steps of: initializing and configuring all quality inspection rules, quality inspection rule codes and corresponding operation entity pools; obtaining an item selected by a user, and generating a quality inspection rule list of the item; the quality inspection rule list comprises bound quality inspection rules and / or unbound quality inspection rules; when an unbound quality inspection rule opened by the user is identified, converting the unbound quality inspection rule into a bound quality inspection rule, and binding the unbound quality inspection rule to the project; and when it is identified that the user completes the point cloud labeling operation of the question package of the project, running the bound quality inspection rules of the quality inspection rule list. According to the method, the quality inspection rules, the quality inspection rule codes and the operation entity pool are initialized and configured, and the quality inspection rule list is dynamically generated according to the items selected by the user, so that flexible binding and operation of the quality inspection rules are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of point cloud data processing, and particularly to a method, device, equipment and storage medium for flexible configuration and extension of quality inspection rules for point cloud annotation results. Background Art

[0002] In a point cloud fusion annotation system, quality inspection of annotation results is a key link to ensure data quality and smooth progress of projects. At present, traditional quality inspection methods mainly include two forms: manual inspection and script batch processing. Although manual quality inspection can conduct detailed inspections on annotation results, it is inefficient and relies on the subjective judgment of quality inspectors, resulting in uneven quality inspection. In addition, the manual quality inspection process is cumbersome and prone to omitting problems due to fatigue or negligence. While script batch processing can quickly process a large number of annotation results, it is separated from online project management, increasing the time cost of result feedback and processing. Both of these quality inspection methods have deficiencies in project management efficiency, and when quality inspection requirements change, they have poor scalability and are difficult to quickly adapt to new quality inspection needs.

[0003] With the continuous development of point cloud annotation technology, the complexity and diversity of annotation projects are increasing, posing higher requirements for the flexibility and efficiency of quality inspection. Therefore, there is a need for a method that can flexibly configure quality inspection rules and quickly adapt to project changes to improve the overall performance and user experience of the point cloud annotation system. Summary of the Invention

[0004] To overcome the above technical defects, the present invention provides a method, device, equipment and storage medium for flexible configuration and extension of quality inspection rules for point cloud annotation results.

[0005] To solve the above problems, the present invention is implemented according to the following technical solutions:

[0006] In a first aspect, the present invention provides a method for flexible configuration and extension of quality inspection rules for point cloud annotation results, for information processing of point cloud annotation structures. The method includes the following steps:

[0007] Initialize and configure all quality inspection rules, quality inspection rule codes, and corresponding running entity pools;

[0008] Obtain the project selected by the user and generate a quality inspection rule list for the project; the quality inspection rule list includes bound quality inspection rules and / or unbound quality inspection rules;

[0009] When an unbound quality inspection rule enabled by the user is recognized, the unbound quality inspection rule is converted into a bound quality inspection rule and bound to the project;

[0010] After the user finishes the point cloud annotation operation of the question package of the project, run the bound quality inspection rules in the quality inspection rule list.

[0011] Combined with the first aspect, the present invention also provides the first preferred implementation manner of the first aspect. Specifically, generating a quality inspection rule list for the project includes the following steps:

[0012] Identify whether the project is bound with quality inspection rules;

[0013] If the project has bound quality inspection rules, return the corresponding bound quality inspection rules and supplement all unbound quality inspection rules to generate the quality inspection rule list;

[0014] If the project does not have bound quality inspection rules, default to return all unbound quality inspection rules, the quality inspection rule table.

[0015] Combined with the first aspect, the present invention also provides the second preferred implementation manner of the first aspect. Specifically, running the bound quality inspection rules in the quality inspection rule list includes:

[0016] Generate an annotation number based on the project and generate a track record;

[0017] Bind the track record to the question package ID of the project to generate a track ID;

[0018] According to the quality inspection rule code of the bound quality inspection rules in the quality inspection rule list, obtain the quality inspection script in the running entity pool;

[0019] Run the quality inspection scripts one by one to perform quality inspection on the project and store a quality inspection method running record in the record table;

[0020] When the quality inspection is completed, output the corresponding quality inspection results, batch save these quality inspection results to the comment table, and record the information of the quality inspection results.

[0021] Combined with the first aspect, the present invention also provides the third preferred implementation manner of the first aspect. Specifically, the method further includes a project question package query step:

[0022] Obtain the question package ID of the project;

[0023] Query the tracking track ID according to the question package ID, and use the track ID to query the track record;

[0024] According to the track record, query the quality inspection method running record stored in the record table;

[0025] According to the quality inspection method running record in the record table, query the information of the quality inspection results stored in the comment table.

[0026] In a second aspect, the present invention provides a device for flexibly configuring and expanding quality inspection rules for point cloud annotation results, which is used for information processing of point cloud annotation structures. The device includes:

[0027] An initialization configuration module, which is used to initialize and configure all quality inspection rules, quality inspection rule codes, and corresponding running entity pools;

[0028] A generation module, which is used to obtain the items selected by the user and generate a quality inspection rule list for the items; the quality inspection rule list includes bound quality inspection rules and / or unbound quality inspection rules;

[0029] A binding module, which is used to convert the unbound quality inspection rules into bound quality inspection rules when it identifies that the user has enabled unbound quality inspection rules, and bind the unbound quality inspection rules to the items;

[0030] A processing module, which is used to run the bound quality inspection rules in the quality inspection rule list when it identifies that the user has completed the point cloud annotation operation of the item package of the item.

[0031] Combined with the second aspect, the present invention also provides the first preferred implementation manner of the second aspect. Specifically, the generation module generates a quality inspection rule list for an item, which specifically includes the following steps:

[0032] Identify whether the item is bound with quality inspection rules;

[0033] If the item has bound quality inspection rules, return the corresponding bound quality inspection rules and supplement all unbound quality inspection rules to generate the quality inspection rule list;

[0034] If the item does not have bound quality inspection rules, by default, return all unbound quality inspection rules, the quality inspection rule table.

[0035] Combined with the second aspect, the present invention also provides the second preferred implementation manner of the second aspect. Specifically, the processing module runs the bound quality inspection rules in the quality inspection rule list, which specifically includes:

[0036] Generate an annotation number based on the item and generate a track record;

[0037] Bind the track record to the item package ID of the item to generate a track ID;

[0038] Obtain a quality inspection script from the running entity pool according to the quality inspection rule code of the bound quality inspection rules in the quality inspection rule list;

[0039] Run the quality inspection scripts one by one to perform quality inspection on the item, and store a quality inspection method running record in the record table;

[0040] After the quality inspection is completed, the corresponding quality inspection results are output, and these quality inspection results are saved in batches to the comment table to record the information of the quality inspection results.

[0041] Combined with the second aspect, the present invention also provides a third preferred implementation manner of the second aspect. Specifically, the device further includes:

[0042] A query module, which is used to obtain the question package ID of the project; query the tracking track ID according to the question package ID, and query the track record using the track ID; query the quality inspection method operation record stored in the record table according to the track record; query the information of the quality inspection results stored in the comment table according to the quality inspection method operation record in the record table.

[0043] In a third aspect, the present invention also provides an electronic device, which includes:

[0044] At least one processor; and a memory communicatively connected to the at least one processor;

[0045] Wherein, the memory stores a computer program executable by the at least one processor, and the computer program is

[0046] executed by the at least one processor so that the at least one processor can execute the method for flexible configuration and extension of the quality inspection rules for point cloud annotation results described in the first aspect.

[0047] In a fourth aspect, the present invention also provides a computer-readable storage medium, which stores a computer program,

[0048] The computer program is used to enable the processor to implement the method for flexible configuration and extension of the quality inspection rules for point cloud annotation results described in the first aspect when executed.

[0049] Compared with the prior art, the beneficial effects of the present invention are:

[0050] The present invention provides a method for flexible configuration and extension of quality inspection rules for point cloud annotation results, which is used for information processing of point cloud annotation structures. The method includes the following steps: Initialize and configure all quality inspection rules, quality inspection rule codes, and corresponding operation entity pools; Obtain the project selected by the user and generate a quality inspection rule list for the project; The quality inspection rule list includes bound quality inspection rules and / or unbound quality inspection rules; When it is recognized that the user enables an unbound quality inspection rule, the unbound quality inspection rule is converted into a bound quality inspection rule, and the unbound quality inspection rule is bound to the project; When it is recognized that the user completes the point cloud annotation operation of the question package of the project, run the bound quality inspection rules in the quality inspection rule list.

[0051] The present invention initializes and configures quality inspection rules, quality inspection rule codes, and operation entity pools, and dynamically generates a quality inspection rule list according to the project selected by the user, realizing flexible binding and operation of quality inspection rules. This design not only improves the quality inspection efficiency and reduces errors caused by manual intervention, but also enhances the flexibility and scalability of the system through a dynamic binding mechanism, and can quickly adapt to changes in project requirements. At the same time, the close combination of quality inspection rules and project management reduces the time cost of result feedback and processing, and improves project management efficiency.

[0052] In addition, users can complete the configuration, binding, and operation of quality inspection rules in the same system, optimizing the user experience and reducing system maintenance costs. Finally, the present invention ensures the high quality of point cloud annotation results through a flexible and arbitrarily extensible and adjustable quality inspection rule configuration scheme, provides reliable data support for subsequent data processing and applications, and significantly improves the overall performance and user experience of the point cloud annotation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The following further details the specific embodiments of the present invention with reference to the accompanying drawings, wherein:

[0054] Figure 1 is a technical flow chart of a method for flexible configuration and extension of quality inspection rules for point cloud annotation results according to an embodiment of the present invention;

[0055] Figure 2 is an algorithm flow chart of a method for flexible configuration and extension of quality inspection rules for point cloud annotation results according to an embodiment of the present invention;

[0056] Figure 3 is an algorithm flow chart of the question package status query step of a method for flexible configuration and extension of quality inspection rules for point cloud annotation results according to an embodiment of the present invention;

[0057] Figure 4 is a module diagram of a device for flexible configuration and extension of quality inspection rules for point cloud annotation results according to an embodiment of the present invention;

[0058] Figure 5 It is a schematic structural diagram of an electronic device according to an embodiment of the present invention. Detailed implementation manners

[0059] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only for the purpose of illustrating and explaining the present invention, and are not intended to limit the present invention.

[0060] In the point cloud fusion annotation system, the quality inspection of the annotation results is a key link to ensure data quality and the smooth progress of the project. At present, the traditional quality inspection methods mainly include two forms: manual inspection and script batch processing. Although manual quality inspection can conduct a detailed inspection of the annotation results, its efficiency is low, and it depends on the subjective judgment of the quality inspectors, resulting in uneven quality inspection. In addition, the manual quality inspection process is cumbersome and prone to missing problems due to fatigue or negligence. While script batch processing can quickly process a large number of annotation results, it is separated from the online project management, increasing the time cost of result feedback and processing. Both of these quality inspection methods have deficiencies in project management efficiency, and when the quality inspection requirements change, their scalability is poor and it is difficult to quickly adapt to new quality inspection needs.

[0061] With the continuous development of point cloud annotation technology, the complexity and diversity of annotation projects are increasing, posing higher requirements for the flexibility and efficiency of quality inspection. Therefore, a method for flexibly configuring and expanding quality inspection rules for point cloud annotation results is needed to improve the overall performance and user experience of the point cloud annotation system.

[0062] The present invention provides a method for flexibly configuring and expanding quality inspection rules for point cloud annotation results for information processing of a point cloud annotation structure. The method includes the following steps: initializing and configuring all quality inspection rules, quality inspection rule codes, and corresponding running entity pools; obtaining a project selected by a user and generating a quality inspection rule list for the project; the quality inspection rule list includes bound quality inspection rules and / or unbound quality inspection rules; when an unbound quality inspection rule enabled by the user is identified, the unbound quality inspection rule is converted into a bound quality inspection rule and the unbound quality inspection rule is bound to the project; when it is identified that the user has completed the point cloud annotation operation of the question package of the project, the bound quality inspection rules in the quality inspection rule list are run.

[0063] The present invention realizes the flexible binding and operation of quality inspection rules by initializing and configuring quality inspection rules, quality inspection rule codes, and the operation entity pool, and dynamically generating a quality inspection rule list according to the project selected by the user. This design not only improves the quality inspection efficiency and reduces errors caused by manual intervention, but also enhances the flexibility and scalability of the system through the dynamic binding mechanism, enabling it to quickly adapt to changes in project requirements. At the same time, the close combination of quality inspection rules and project management reduces the time cost of result feedback and processing, and improves project management efficiency.

[0064] Reference Figure 1 , the embodiment of the present invention provides a schematic flowchart of a method for flexible configuration and extension of quality inspection rules for point cloud annotation results. This method can be executed by a device for flexible configuration and extension of quality inspection rules for point cloud annotation results, and this device can be implemented in the form of hardware and / or software, and this device can be configured in a computer. As Figure 1 shown, this method includes:

[0065] S100: Initialize and configure all quality inspection rules, quality inspection rule codes, and the corresponding operation entity pool.

[0066] In a specific implementation, the initialization stage is the basic setting link of the algorithm. By pre-configuring all possible quality inspection rules and their unique identifiers (codes), and establishing an operation entity pool (a resource pool for executing rules), it provides basic support for the subsequent quality inspection process. Ensure the flexibility and scalability of quality inspection rules, and at the same time, through the configuration of the operation entity pool, improve resource utilization efficiency and provide a stable operation environment for subsequent quality inspection operations.

[0067] In a specific implementation, use a database management system (such as MySQL) to create a quality inspection rule table to store quality inspection rules and their codes. Build an operation entity pool on the server, and integrate existing point cloud annotation tools (such as PointLabeler) and quality inspection algorithms (such as a deep learning-based annotation accuracy detection algorithm).

[0068] S200: Obtain the project selected by the user and generate a quality inspection rule list for the project; the quality inspection rule list includes bound quality inspection rules and / or unbound quality inspection rules.

[0069] In a specific implementation, the user selects the point cloud annotation project to be quality inspected through the system interface. According to the project requirements, screen out the rules applicable to the project from the initialized quality inspection rules to form a quality inspection rule list. The content of the quality inspection rule list includes bound quality inspection rules (rules default or previously bound for the project) and unbound quality inspection rules (optional but not yet bound rules).

[0070] For example, on the system front-end design project selection interface, the user can enter the project name or select a project through a drop-down menu. The back-end queries the database based on the project information, extracts the corresponding quality inspection rules, and generates a list of quality inspection rules to be displayed on the user interface.

[0071] In a specific implementation, generating a list of quality inspection rules for a project specifically includes the following steps:

[0072] S210: Identify whether the project is bound to quality inspection rules.

[0073] Check in the system whether the current project has been associated with any quality inspection rules. This step is to determine whether the project already has bound quality inspection rules by querying the database or configuration file.

[0074] In one example, look up the quality inspection rule association information of the current project in the project table. For example, there can be a field bound_quality_rules in the project table to store the list of codes of the bound quality inspection rules. If this field is empty or does not exist, it is considered that the project has no bound quality inspection rules; otherwise, it is considered that the project has bound quality inspection rules.

[0075] S220: If the project has bound quality inspection rules, return the corresponding bound quality inspection rules and complete all unbound quality inspection rules to generate the list of quality inspection rules.

[0076] In one example, if a project has already bound some quality inspection rules, these bound rules need to be merged with the unbound rules to generate a complete list of quality inspection rules. In this way, the user can clearly see which rules have been enabled and which rules can still be selected for enabling.

[0077] S230: If the project does not have bound quality inspection rules, by default, return all unbound quality inspection rules, the quality inspection rule table.

[0078] In one example, if a project has not bound any quality inspection rules, directly return all quality inspection rules supported by the system and mark them as in the "unbound" state. In this way, the user can select the rules that need to be enabled from them.

[0079] Through the above steps, the system can dynamically generate a list of quality inspection rules including bound and unbound rules according to whether the project is bound to quality inspection rules. The user can enable or disable rules as needed, thus realizing the flexible configuration and extension of quality inspection rules.

[0080] S300: When identifying the unbound quality inspection rules enabled by the user, convert the unbound quality inspection rules into bound quality inspection rules and bind the unbound quality inspection rules to the project.

[0081] It is understandable that the system monitors the user's operations on unbound quality inspection rules, such as clicking the "Enable" button. Update the status of the unbound quality inspection rule to bound and associate it with the current project to ensure that the rule takes effect in subsequent quality inspections.

[0082] In a specific implementation, an "Enable" button is added to each unbound quality inspection rule in the quality inspection rule list interface. After the user clicks the button, the system sends a request from the front end to the back end, and the back end updates the rule status in the database and binds the rule to the project.

[0083] S400: When it is recognized that the user has completed the point cloud annotation operation of the question package of the project, run the bound quality inspection rules in the quality inspection rule list.

[0084] In a specific implementation, the system determines whether the point cloud annotation is completed by monitoring the status of the annotation tool or the user's submission operation. Sequentially execute the bound quality inspection rules in the quality inspection rule list to perform quality detection on the annotation results. Set a submission button for completing the annotation in the point cloud annotation tool (such as PointLabeler), and after the user clicks it, the quality inspection process is triggered. The system back end calls the corresponding running entity (such as a quality inspection script) according to the quality inspection rules bound to the project to detect the annotation results and feedback the results to the user.

[0085] In a specific implementation, running the bound quality inspection rules in the quality inspection rule list specifically includes:

[0086] S410: Generate an annotation number based on the project and generate a track record.

[0087] It should be noted that the annotation number is the unique number used to identify the current quality inspection batch, and the track record is used to track the entire quality inspection process. Generating an annotation number can help with subsequent traceability and management of quality inspection tasks.

[0088] In a specific implementation, generate the annotation number: Generate a unique number according to the project information and timestamp, for example, using the combination of the project ID and the timestamp. Create a track record: Create a record in the database to store information such as the annotation number, project ID, and quality inspection start time.

[0089] S420: Bind the track record to the question package ID of the project to generate a track ID.

[0090] Associate the track record with the question package ID of the project to ensure that the quality inspection process is bound to the specific data packet, facilitating subsequent query and management.

[0091] S430: Obtain the quality inspection script from the running entity pool according to the quality inspection rule code of the bound quality inspection rules in the quality inspection rule list.

[0092] Find the corresponding quality inspection script from the running entity pool according to the bound quality inspection rule code. The running entity pool can be a resource library storing scripts or algorithms. Obtain the corresponding script path or algorithm from the database or file system according to the quality inspection rule code. Load the script into memory and prepare to run.

[0093] S440: Run the quality inspection scripts one by one, conduct quality inspection on the project, and store a record of the quality inspection method run in the record table.

[0094] It can be understood that each quality inspection script is run in sequence to conduct quality inspection on the project, and the running status and results of each script are recorded. The running results of the script are stored in the record table, including the quality inspection rule code, running time, result status, etc.

[0095] S450: When the quality inspection is completed, output the corresponding quality inspection results, save this batch of quality inspection results in batches to the comment table, and record the information of the quality inspection results.

[0096] Summarize the running results of all quality inspection scripts and save them in batches to the comment table for subsequent viewing and analysis.

[0097] Through the above steps, the system can efficiently run the bound quality inspection rules, record the quality inspection process and results, and save the results in batches to the database. This process not only ensures the automation and traceability of quality inspection, but also improves the flexibility and scalability of quality inspection.

[0098] In a preferred implementation, the method further includes a project question package query step:

[0099] S10: Obtain the question package ID of the project.

[0100] S20: Query the tracking track ID according to the question package ID, and use the track ID to query the track record.

[0101] S30: Query the quality inspection method running record stored in the record table according to the track record.

[0102] S40: Query the information of the quality inspection results stored in the comment table according to the quality inspection method running record in the record table.

[0103] By adding the project question package query step, the system can achieve a complete traceability from the question package ID to the quality inspection results. This implementation method not only improves the transparency of the quality inspection process, but also facilitates users to quickly locate problems, enhancing the usability and user experience of the system.

[0104] Specifically, the present invention provides the following specific implementation manners:

[0105] S1. When the program starts, it initializes and configures all quality inspection rules, and initializes and configures the quality inspection rule code and the corresponding operation entity pool.

[0106] S2. The user selects a project and obtains the quality inspection rule list. If the project has bound quality inspection rules, the corresponding bound quality inspection rules are returned and the unbound quality inspection rules are supplemented. If the project has no quality inspection rules, all unbound quality inspection rules are returned by default.

[0107] S3. The user configures to enable Quality Inspection Rule A and Quality Inspection Rule B, triggering the program to bind the quality inspection rules to the project.

[0108] S4. After the user completes the point cloud annotation operation of the question package, click to run the quality inspection rules.

[0109] S5. Save a track record in the track table, bind the question package ID, generate a track ID, and find the bound quality inspection rule code according to the project. Then, according to the corresponding code, find the corresponding entity class in the quality inspection entity pool and run the quality inspection method of the entity class. For example, there are two quality inspection rules in the quality inspection entity pool: "Annotation box size consistency detection" and "Annotation box attribute integrity detection". If the project binds the code boxSizeConsistence, then the "Annotation box size consistency detection" entity class is matched and the quality inspection method of the entity class is run.

[0110] S6. During the operation of each quality inspection method, first save a quality inspection method operation record in the record table and bind the track ID. Then, after the quality inspection rule method runs, output the corresponding quality inspection rule result, and batch save this batch of quality inspection rule results to the comment table to record the detailed information of the quality inspection result.

[0111] S7. The system automatically triggers the echo of the annotation result

[0112] S8. Query the tracking number track ID according to the question package ID. Then, according to the tracking number track ID, query how many quality inspection rules are run under this tracking number. For example, if it is queried that Quality Inspection Rule A and Quality Inspection Rule B are run according to the tracking number, then query the quality inspection results of the runs of Quality Inspection Rule A and Quality Inspection Rule B, and return the detailed information of the quality inspection results. If no quality inspection rule is run this time, return an empty quality inspection result to avoid querying old quality inspection result information.

[0113] The present invention has the following advantages:

[0114] 1. The use of the quality inspection rule entity class pool enables different quality inspection rule codes to match the quality inspection rule entity classes in the pool and run the quality inspection rule methods. Adding quality inspection rule entity classes can achieve the effect of expanding new quality inspection rules. By adding quality inspection codes and the corresponding entity classes, the system can be quickly expanded without being noticed.

[0115] 2. The design of the tracking number. By introducing the tracking number into the quality inspection, a new tracking number is generated every time the quality inspection rule is run, and the result of this run can be queried using the new tracking number. Through the design of the tracking number, the system retains the result records of each run of the quality inspection rule, enhancing the traceability of the system.

[0116] Such as Figure 4 As shown, the present invention provides a device for flexible configuration and expansion of quality inspection rules for point cloud annotation results, for information processing of point cloud annotation structures. The device includes:

[0117] An initialization configuration module, which is used to initialize and configure all quality inspection rules, quality inspection rule codes, and the corresponding running entity pool;

[0118] A generation module, which is used to obtain the project selected by the user and generate a list of quality inspection rules for the project; the list of quality inspection rules includes bound quality inspection rules and / or unbound quality inspection rules;

[0119] A binding module, which is used to convert unbound quality inspection rules into bound quality inspection rules and bind the unbound quality inspection rules to the project when it identifies that the user has enabled the unbound quality inspection rules;

[0120] A processing module, which is used to run the bound quality inspection rules in the list of quality inspection rules when it identifies that the user has completed the point cloud annotation operation of the question package for the project.

[0121] Figure 5 FIG. shows a schematic structural diagram of an electronic device 10 that can be used to implement an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, 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 herein and / or claimed.

[0122] Such as Figure 5As 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 read-only memory (ROM) 12, random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor. 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, ROM 12, and 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.

[0123] 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 through a computer network such as the Internet and / or various telecommunication networks.

[0124] The processor 11 can be various general and / or special 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 appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as solving a method for flexible configuration and extension of quality inspection rules for point cloud annotation results.

[0125] In some embodiments, a method for flexible configuration and extension of quality inspection rules for point cloud annotation results 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 method for flexible configuration and extension of quality inspection rules for point cloud annotation results described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute a method for flexible configuration and extension of quality inspection rules for point cloud annotation results in any other appropriate way (e.g., by means of firmware).

[0126] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a 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 are executable and / or interpretable on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0127] The computer programs for implementing the methods 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 apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0128] 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.

[0129] 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, speech input, or tactile input).

[0130] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including 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.

[0131] The computing system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having 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 and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0132] An embodiment of the present invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements a method for flexible configuration and extension of quality inspection rules for point cloud annotation results as provided in the embodiment of the present invention.

[0133] 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 an independent 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 kind of network - including a local area network (LAN) or a wide area network (WAN) - or, alternatively, can be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0134] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited 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 no limitation is imposed herein.

[0135] The above specific embodiments do not constitute a limitation on 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 principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for flexibly configuring and extending quality inspection rules for point cloud annotation results, characterized in that: The method for information processing of point cloud annotation structure comprises the following steps: Initialize and configure all quality inspection rules, quality inspection rule codes and corresponding running entity pools; Obtaining the project selected by the user and generating a quality inspection rule list for the project; the quality inspection rule list includes bound quality inspection rules and / or unbound quality inspection rules; When an unbound quality inspection rule enabled by a user is identified, the unbound quality inspection rule is converted into a bound quality inspection rule, and the unbound quality inspection rule is bound to the project; After it is identified that the user has completed the point cloud annotation operation of the question package of the project, the bound quality inspection rules in the quality inspection rule list are run.

2. The method for flexibly configuring and extending quality inspection rules for point cloud annotation results according to claim 1, characterized in that: Generate a list of quality inspection rules for the project, including the following steps: Identify whether the project is bound to a quality inspection rule; If the project has bound quality inspection rules, the corresponding bound quality inspection rules are returned and all unbound quality inspection rules are completed to generate the quality inspection rule list; If the project does not have any bound quality inspection rules, all unbound quality inspection rules and the quality inspection rule table are returned by default.

3. The method for flexible configuration and extension of quality inspection rules for point cloud annotation results according to claim 1, characterized in that: Run the bound quality inspection rules in the quality inspection rule list, including: Generate an annotation number based on the project and generate a track record; Bind the track record to the question package ID of the project to generate a trackID; Obtaining a quality inspection script from the running entity pool according to the quality inspection rule code of the bound quality inspection rule in the quality inspection rule list; Run the quality inspection scripts one by one to perform quality inspection on the project, and store a quality inspection method running record in the record table; When the quality inspection is completed, the corresponding quality inspection results are output and saved in batches into the comment table to record the quality inspection results information.

4. The method for flexible configuration and extension of quality inspection rules for point cloud annotation results according to claim 3, characterized in that: The method further comprises the step of querying the project question package: Get the question package ID of the project; Query the trackID according to the question package ID, and use the trackID to query the track record; According to the track record, query the quality inspection method operation record stored in the record table; According to the quality inspection method running record in the record table, query the quality inspection result information stored in the comment table.

5. A device for flexibly configuring and extending quality inspection rules for point cloud annotation results, characterized in that: For information processing of point cloud annotation structure, the device comprises: Initialization configuration module, which is used to initialize and configure all quality inspection rules, quality inspection rule codes and corresponding running entity pools; A generation module, which is used to obtain the project selected by the user and generate a quality inspection rule list for the project; the quality inspection rule list includes bound quality inspection rules and / or unbound quality inspection rules; A binding module, which is used to identify unbound quality inspection rules enabled by a user, convert the unbound quality inspection rules into bound quality inspection rules, and bind the unbound quality inspection rules to the project; A processing module is used to run the bound quality inspection rules in the quality inspection rule list after recognizing that the user has completed the point cloud annotation operation of the question package of the project.

6. The device for flexibly configuring and extending quality inspection rules for point cloud annotation results according to claim 5, characterized in that: The generation module generates a quality inspection rule list for the project, specifically including the following steps: Identify whether the project is bound to a quality inspection rule; If the project has bound quality inspection rules, the corresponding bound quality inspection rules are returned and all unbound quality inspection rules are completed to generate the quality inspection rule list; If the project does not have any bound quality inspection rules, all unbound quality inspection rules and the quality inspection rule table are returned by default.

7. The device for flexibly configuring and extending quality inspection rules for point cloud annotation results according to claim 6, characterized in that: The processing module runs the bound quality inspection rules in the quality inspection rule list, specifically including: Generate an annotation number based on the project and generate a track record; Bind the track record to the question package ID of the project to generate a trackID; Obtaining a quality inspection script from the running entity pool according to the quality inspection rule code of the bound quality inspection rule in the quality inspection rule list; Run the quality inspection scripts one by one to perform quality inspection on the project, and store a quality inspection method running record in the record table; When the quality inspection is completed, the corresponding quality inspection results are output and saved in batches into the comment table to record the quality inspection results information.

8. The device for flexibly configuring and extending quality inspection rules for point cloud annotation results according to claim 7, characterized in that: The device also includes: The query module is used to obtain the question package ID of the project; query the tracking trackID based on the question package ID, and use the trackID to query the track record; query the quality inspection method operation record stored in the record table based on the track record; query the quality inspection result information stored in the comment table based on the quality inspection method operation record in the record table.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; In which, the memory stores a computer program that can be executed 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 a method for flexibly configuring and extending quality inspection rules for point cloud annotation results as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The computer readable storage medium stores a computer program, The computer program is used to enable a processor to implement a method for flexibly configuring and extending quality inspection rules for point cloud annotation results as described in any one of claims 1 to 4 when executed.

Images