A configuration method and device for detecting a model combination, electronic equipment and a storage medium

Abstract

Embodiments of the present application provide a configuration method and device for a detection model combination, electronic equipment and a storage medium, wherein the method comprises: obtaining a node processing file and a post-processing file required for constructing the detection model combination; processing the node processing file to obtain a processed node processing file; configuring combination parameters required for the detection model combination; selecting a plurality of detection models required from a model list according to the combination parameters; obtaining model paths corresponding to the plurality of detection models; and generating a configuration file of the detection model combination according to the model paths, the processed node processing file and the post-processing file. The embodiments of the present application can improve the detection function of the detection model combination, can timely locate when the detection model combination is wrong, and can effectively save version information to prevent being overwritten.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer model detection, in particular to a configuration method and device of a detection model combination, an electronic device and a computer readable storage medium. BACKGROUND

[0002] In daily life, some computer detection models are often applied for detection. For example, for the detection of kitchen specifications, multiple detection functions of different scenes may be needed, such as open fire detection, mouse detection, chef hat wearing detection, and mobile phone playing detection. At this time, multiple detection models are combined into a detection model combination with multiple functions through some rules, so as to realize the coordinated action of multiple functions.

[0003] However, the existing detection model combination has many problems. For example, when editing the execution file of the model combination, if the function to be implemented by the detection model combination is complex, the logic of processing will also become complex, errors are easy to occur, and it is not easy to locate the problem when the problem occurs. When testing the detection model combination, the same operation needs to be repeated, and after the test is completed, the version information needs to be saved in the local, and the situation that multiple versions are not correctly marked and are overwritten may occur. SUMMARY

[0004] The purpose of the embodiments of the present application is to provide a configuration method and device of a detection model combination, an electronic device and a computer readable storage medium, which can improve the detection function of the detection model combination, locate the error of the detection model combination in time, and effectively save the version information to prevent it from being overwritten.

[0005] In a first aspect, the embodiments of the present application provide a configuration method of a detection model combination, which comprises:

[0006] obtaining a node processing file and a post-processing file required for constructing the detection model combination;

[0007] processing the node processing file to obtain a processed node processing file;

[0008] configuring combination parameters required by the detection model combination;

[0009] selecting multiple detection models required in a model list according to the combination parameters;

[0010] obtaining model paths corresponding to the multiple detection models;

[0011] generating a configuration file of the detection model combination according to the model paths, the processed node processing file and the post-processing file.

[0012] In the implementation process, the plurality of detection models are selected according to the combination parameters, and the configuration file is generated according to the model paths of the plurality of detection models and the required files, so that the detection function of the detection model combination can be improved, the error of the detection model combination can be located in time, the version information can be effectively saved, and the version information is prevented from being covered.

[0013] Further, after the step of generating the configuration file of the detection model combination according to the model path, the processed node processing file and the post-processing file, the method further comprises:

[0014] Testing the configuration file of the detection model combination.

[0015] In the implementation process, the configuration file is further tested, so that the effectiveness of the configuration file can be ensured, the error probability in the use process can be reduced, and the repetitive operation in the use process can be reduced.

[0016] Further, the step of processing the node processing file to obtain the processed node processing file comprises:

[0017] Obtaining node function information and node parameters;

[0018] According to the function information and the node parameters, the node processing file is edited to obtain the processed node processing file.

[0019] In the implementation process, the node processing file is edited according to the node function information and the node parameters, so that the accuracy of the detection model combination in the function of each node can be ensured, and the repeated node process is avoided.

[0020] Further, the step of configuring the combination parameters required by the detection model combination further comprises:

[0021] Obtaining name information, version information and skill information of the detection model combination;

[0022] According to the name information, the version information and the skill information, the combination parameters are configured.

[0023] In the implementation process, the name information, the version information and the skill information are configured into the combination parameters, so that the version of the detection model combination is prevented from being covered, and the version information can be found in time when an error occurs.

[0024] Further, after the step of obtaining the model paths corresponding to the plurality of detection models, the method further comprises:

[0025] Obtaining node information corresponding to the plurality of detection models;

[0026] generate a node execution flowchart according to the node information, the node execution flowchart comprising the model path.

[0027] In the implementation process, the node execution flowchart is generated according to the node information, the detection efficiency of the detection model combination at each node is improved, and the error probability at each node is reduced.

[0028] In a second aspect, the embodiments of the present application further provide a configuration device of a detection model combination, the device comprising:

[0029] an acquisition module configured to acquire a node processing file and a post-processing file required for constructing the detection model combination;

[0030] a processing module configured to process the node processing file to obtain a processed node processing file;

[0031] a configuration module configured to configure combination parameters required for the detection model combination;

[0032] a selection module configured to select a plurality of detection models required in a model list according to the combination parameters;

[0033] a path obtaining module configured to obtain model paths corresponding to the plurality of detection models;

[0034] a generation module configured to generate a configuration file of the detection model combination according to the model paths, the processed node processing file and the post-processing file.

[0035] In the implementation process, the plurality of detection models are selected according to the combination parameters, and the configuration file is generated according to the model paths of the plurality of detection models and the required files, so that the detection function of the detection model combination can be improved, the version information can be effectively saved to prevent being overwritten, and the detection model combination can be positioned in time when an error occurs.

[0036] Further, the device further comprises a test module configured to:

[0037] test the configuration file of the detection model combination.

[0038] In the implementation process, the configuration file is further tested, so that the validity of the configuration file can be ensured, the error probability in the use process can be reduced, and repetitive operations in the use process can be reduced.

[0039] Further, the processing module is further configured to:

[0040] acquire node function information and node parameters;

[0041] According to the function information and the node parameter, the node processing file is edited to obtain the processed node processing file.

[0042] In the implementation process, the node processing file is edited according to the node function information and the node parameter, which can ensure the accuracy of the detection module combination in the function of each node and avoid repeated node processes.

[0043] In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor implements the steps of the method according to any one of the first aspect when executing the computer program.

[0044] In a fourth aspect, a computer readable storage medium is provided, which stores instructions. When the instructions are executed on a computer, the computer executes the method according to any one of the first aspect.

[0045] In a fifth aspect, a computer program product is provided, which, when executed on a computer, causes the computer to execute the method according to any one of the first aspect.

[0046] Other features and advantages of the present disclosure will be described in the following description, or can be learned from the description, or can be determined without doubt, or can be known by implementing the above-mentioned technologies of the present disclosure.

[0047] And can be implemented according to the content of the specification, the following will be described in detail with the preferred embodiments of the present application and the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0049] Figure 1 The flowchart of the configuration method of the detection model combination provided by the embodiments of the present application is shown in the figure.

[0050] Figure 2 The structural composition schematic diagram of the configuration device of the detection model combination provided by the embodiments of the present application is shown in the figure.

[0051] Figure 3 The structural composition schematic diagram of the electronic device provided by the embodiments of the present application is shown in the figure. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

[0053] It should be noted that similar reference numerals and letters refer to like items in the following drawings, and therefore, once an item is defined in one drawing, it need not be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", and the like are only used to distinguish description, and cannot be understood as indicating or implying relative importance.

[0054] The specific embodiments of the present application will be further described in detail below with reference to the drawings and embodiments. The following embodiments are used to illustrate the present application, but are not used to limit the scope of the present application.

[0055] Embodiment One

[0056] Figure 1 is a flowchart of a configuration method of a detection model combination provided by the embodiments of the present application, as shown in Figure 1 The method comprises the following steps:

[0057] S1, acquiring a node processing file and a post-processing file required for constructing a detection model combination;

[0058] S2, processing the node processing file to obtain a processed node processing file;

[0059] S3, configuring combination parameters required for the detection model combination;

[0060] S4, selecting a plurality of detection models required in a model list according to the combination parameters;

[0061] S5, obtaining model paths corresponding to the plurality of detection models;

[0062] S6, generating a configuration file of the detection model combination according to the model paths, the processed node processing file, and the post-processing file.

[0063] In the above implementation process, the plurality of detection models are selected according to the combination parameters, and the configuration file is generated according to the model paths of the plurality of detection models and the required files, which can improve the detection function of the detection model combination, can timely locate when the detection model combination is wrong, and can effectively save the version information to prevent being overwritten.

[0064] In the embodiments of the present application, the functions of the plurality of detection models are connected in series through nodes, and optionally, the node flow of the detection model combination can include a producer node, a processor node, a consumer node, etc. Different detection models in the detection model combination need to play a role in each node, and different functions or different application scenarios can be realized by editing and adjusting the nodes.

[0065] Further, the step of processing the node processing file to obtain the processed node processing file includes:

[0066] Obtaining node function information and node parameters;

[0067] According to the function information and the node parameters, the node processing file is edited to obtain the processed node processing file.

[0068] In the above implementation process, according to the node function information and the node parameters, the node processing file is edited, which can ensure the accuracy of the function of the detection model combination in each node and avoid repeated node flows.

[0069] The node processing file needs to be edited, that is, it needs to be improved what function each node needs to complete, the received parameters and the output results, so the processing file is edited according to the node function information and the node parameters to realize the improvement of the node function.

[0070] Optionally, the post-processing file can be edited, or some post-processing files required by the detection models can be placed in a specified folder for easy searching in the subsequent testing process.

[0071] Further, the step of configuring the combination parameters required by the detection model combination further includes:

[0072] Obtaining name information, version information and skill information of the detection model combination;

[0073] According to the name information, the version information and the skill information, the combination parameters are configured.

[0074] In the above implementation process, the name information, the version information and the skill information are configured into the combination parameters, which prevents the version of the detection model combination from being overwritten and facilitates timely finding of the version information when an error occurs.

[0075] According to the name information, the version information and the skill information, the skill parameters and the combination parameters are configured, and the edge box can be selected according to the combination parameters.

[0076] Further, after the step of obtaining the model paths corresponding to the plurality of detection models, further includes:

[0077] Obtaining node information corresponding to the plurality of detection models;

[0078] The node execution flowchart is generated according to the node information, and the node execution flowchart includes a model path.

[0079] In the implementation process, the node execution flowchart is generated according to the node information, the detection efficiency of the detection model combination at each node is improved, and the error probability at each node is reduced.

[0080] The detection model needed is selected from the model list, and then the node execution flowchart is generated, and the parameters needed are configured. If a detection model is needed during the node execution process, the model path used by the detection model is input, and a configuration file is generated.

[0081] The application embodiment displays the construction process and the component structure of the detection model combination through the node execution flowchart, that is, a graphical interface, is easy to understand, separates the post-processing operation and the model execution, is easier to locate when a problem occurs, and in combination with an operation log, is more convenient for an algorithm personnel to find a problem source and an optimization point.

[0082] All configuration information is checked, and after it is confirmed that there is no error, the configuration file is packaged to obtain a detection model combination.

[0083] Further, after the step of generating the configuration file of the detection model combination according to the model path, the processed node processing file and the post-processing file, the step further includes:

[0084] The configuration file of the detection model combination is tested.

[0085] In the implementation process, the configuration file is further tested, the effectiveness of the configuration file can be ensured, the error probability in the use process is reduced, and the repetitive operation in the use process is reduced.

[0086] In the application embodiment, if the configuration file of the detection model combination is to be tested, an algorithm personnel needs to select a target test set and submit a test request, and the detection model combination to be tested and the target test set are automatically pushed to an edge box of a specified target type according to the test request to perform testing. After the testing is completed, an algorithm personnel is notified by email and the result is returned.

[0087] If the algorithm personnel needs to compare with a previous version of a certain detection model combination, the system automatically loads the results of two times to perform comparison after the target version is selected. After the comparison is completed, the algorithm personnel is notified by email.

[0088] For the algorithm personnel, it is not necessary to maintain a test version and a historical test result on a local or an edge box, and for iteration of each version, the optimization and the effect of a new version are more clear.

[0089] Save the operation time of algorithm personnel, no need to go to the repetitive operation again, and when the edge box resource is limited, no need to pay attention to when the resource will release, at the same time can reduce the use of edge box, save the cost.

[0090] Embodiment two

[0091] In order to execute the method corresponding to the above embodiment one, in order to realize the corresponding function and technical effect, the following provides a kind of configuration device of detection model combination, as shown in Figure 2 The device comprises:

[0092] Acquisition module 1 is used to acquire the node processing file and post-processing file required for constructing detection model combination;

[0093] Processing module 2 is used to process node processing file, to obtain processed node processing file;

[0094] Configuration module 3 is used to configure the combination parameters required for detection model combination;

[0095] Selection module 4 is used to select the multiple detection models required in model list according to combination parameters;

[0096] Path obtaining module 5 is used to obtain the model path corresponding to multiple detection models;

[0097] Generation module 6 is used to generate the configuration file of detection model combination according to model path, processed node processing file and post-processing file.

[0098] In the above implementation process, according to the model path of multiple detection models, the required file is generated according to the combination parameters to select multiple detection models, which can improve the detection function of detection model combination, and can be positioned in time when detection model combination is wrong, and version information can be effectively saved to prevent being covered.

[0099] Further, the device further comprises test module, for:

[0100] Test the configuration file of detection model combination.

[0101] In the above implementation process, further test the configuration file, which can ensure the validity of the configuration file, reduce the error probability in use process, and reduce the repetitive operation in use process.

[0102] Further, processing module 2 is further used for:

[0103] Obtain node function information and node parameters;

[0104] According to the function information and the node parameter, the node processing file is edited to obtain a processed node processing file.

[0105] In the implementation process, the node processing file is edited according to the node function information and the node parameter, which can ensure the accuracy of the detection module combination in the function of each node and avoid repeated node processes.

[0106] Further, the configuration module 3 is further configured to:

[0107] Obtain name information, version information and skill information of the detection model combination;

[0108] According to the name information, the version information and the skill information, the combination parameter is configured.

[0109] Further, the generation module 6 is further configured to:

[0110] Obtain node information corresponding to a plurality of detection models;

[0111] According to the node information, a node execution flowchart is generated, and the node execution flowchart includes a model path.

[0112] The configuration device of the detection model combination described above can implement the method of the first embodiment described above. The options in the first embodiment described above are also applicable to this embodiment, which will not be described in detail here.

[0113] The rest of the content of the embodiment of the application can refer to the content of the first embodiment described above. In this embodiment, it will not be described in detail.

[0114] Embodiment three

[0115] The embodiment of the application provides an electronic device, which comprises a memory and a processor. The memory is used to store a computer program, and the processor runs the computer program to make the electronic device execute the detection model combination configuration method of the first embodiment.

[0116] Optionally, the electronic device described above can be a server.

[0117] See Figure 3 , Figure 3 The electronic device provided by the embodiment of the application is a structural composition schematic diagram. The electronic device can include a processor 31, a communication interface 32, a memory 33 and at least one communication bus 34. Wherein, the communication bus 34 is used to realize the direct connection communication of these components. Wherein, the communication interface 32 of the device in the embodiment of the application is used to communicate with other node devices. The processor 31 can be an integrated circuit chip with signal processing capability.

[0118] The processor 31 can be a general processor, including a central processing unit (CPU), a network processor (NP), etc. It can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The disclosed methods, steps and logic block diagrams in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor 31 can also be any conventional processor.

[0119] The memory 33 can be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read only memory (PROM), an erasable programmable read only memory (EPROM), an electrically erasable programmable read only memory (EEPROM), etc. The memory 33 stores computer readable instructions, which, when executed by the processor 31, enable the device to perform the above Figure 1 The method embodiments involve various steps.

[0120] Optionally, the electronic device can further include a storage controller, an input / output unit. The memory 33, the storage controller, the processor 31, the peripheral interface, the input / output unit are directly or indirectly electrically connected to each other to realize data transmission or interaction. For example, these elements can be electrically connected to each other through one or more communication buses 34. The processor 31 is configured to execute executable modules stored in the memory 33, such as software function modules or computer programs included in the device.

[0121] The input / output unit is configured to provide a user with a creation task and create a selectable time period or a preset execution time for the task to realize user interaction with a server. The input / output unit can be, but is not limited to, a mouse and a keyboard, etc.

[0122] It can be understood that Figure 3 The structure shown is only schematic, and the electronic device can include more or fewer components than Figure 3 shown or have a different configuration than Figure 3 shown. Figure 3The components shown in the figures can be implemented in hardware, software, or a combination thereof.

[0123] In addition, the embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the configuration method of the detection model combination of the embodiment one.

[0124] The embodiment of the present application further provides a computer program product, which, when running on a computer, causes the computer to execute the method described in the method embodiment.

[0125] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are only schematic. For example, the flowcharts and block diagrams in the drawings show the possible implementation architectures, functions and operations of the devices, methods and computer program products according to the embodiments of the present application. In this regard, each block in the flowcharts or block diagrams can represent a module, a program segment or a part of code, which contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different orders from those described in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and the combination of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based device that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0126] In addition, each functional module in the embodiments of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0127] If the functions are realized in the form of software function modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The aforementioned storage medium includes various media that can store program codes, such as U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc.

[0128] The above merely provides an example of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, and thus, once an item is defined in one drawing, it need not be further defined and explained in subsequent drawings.

[0129] The above merely provides an example of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, and thus, once an item is defined in one drawing, it need not be further defined and explained in subsequent drawings.

[0130] It should be noted that the relational terms herein such as first and second and the like are used solely to distinguish one from another entity or action without necessarily requiring or implying any actual relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

Claims

1. A configuration method of a detection model combination, characterized by, The method comprises: obtaining a node processing file and a post-processing file required for constructing the detection model combination; processing the node processing file to obtain a processed node processing file; configuring combination parameters required for the detection model combination; selecting a plurality of detection models required in a model list according to the combination parameters; obtaining model paths corresponding to the plurality of detection models; generating a configuration file of the detection model combination according to the model paths, the processed node processing file and the post-processing file; after the step of obtaining the model paths corresponding to the plurality of detection models, further comprising: obtaining node information corresponding to the plurality of detection models; generating a node execution flowchart according to the node information, the node execution flowchart comprising the model paths.

2. The method of claim 1, wherein, after the step of generating the configuration file of the detection model combination according to the model paths, the processed node processing file and the post-processing file, further comprising: testing the configuration file of the detection model combination.

3. The method of claim 1, wherein, The step of processing the node processing file to obtain a processed node processing file comprises: obtaining node function information and node parameters; editing the node processing file according to the function information and the node parameters to obtain the processed node processing file.

4. The method of claim 1, wherein, The step of configuring combination parameters required for the detection model combination comprises: obtaining name information, version information and skill information of the detection model combination; configuring the combination parameters according to the name information, the version information and the skill information.

5. A configuration apparatus of a detection model combination, characterized by, The apparatus comprises: an obtaining module configured to obtain a node processing file and a post-processing file required for constructing the detection model combination; a processing module configured to process the node processing file to obtain a processed node processing file; a configuration module configured to configure combination parameters required for the detection model combination; a selecting module configured to select a plurality of detection models required in a model list according to the combination parameters; a path obtaining module configured to obtain model paths corresponding to the plurality of detection models; a generating module configured to generate a configuration file of the detection model combination according to the model paths, the processed node processing file and the post-processing file; the generating module is further configured to: obtain node information corresponding to the plurality of detection models; generate a node execution flowchart according to the node information, the node execution flowchart comprising the model paths.

6. The configuration apparatus of the detection model combination according to claim 5, wherein The apparatus further comprises a testing module configured to: test the configuration file of the detection model combination.

7. The configuration apparatus of the detection model combination according to claim 5, wherein The processing module is further configured to: obtain node function information and node parameters; edit the node processing file according to the function information and the node parameters to obtain the processed node processing file.

8. An electronic device, comprising: An electronic device comprising a memory and a processor, the memory being configured to store a computer program, and the processor being configured to execute the computer program to enable the electronic device to perform the configuration method of the detection model combination according to any one of claims 1 to 4.

9. A computer-readable storage medium, characterized in that, The computer program is stored in the computer storage and is executed by the processor to realize the configuration method of the detection model combination according to any one of claims 1 to 4.

Images