Data resource management method, system and storage medium

Abstract

The present application relates to the technical field of data resource management, and in particular to a data resource management method, system, and storage medium. The method comprises: obtaining data resources to be stored and data resource scenarios relatively bound to the data resources to be stored, determining category scenario information of different categories and category scenario data corresponding to the category scenario information according to the data resource scenarios, creating a scenario category model, performing secondary association construction on the scenario category model based on the category scenario information and the category scenario data to obtain the constructed scenario category model, inputting the data resources to be stored into the scenario category model for data verification, determining whether there is abnormal resource data in the data resources to be stored, and if so, generating a data anomaly prompt based on the abnormal resource data, the data anomaly prompt including an abnormal data resource node storing the data resource and a data modification plan. The present application improves the quality and accuracy of specific data in data resources.

Description

Technical Field

[0001] The present application relates to the technical field of data resource management, and in particular to a data resource management method, system, and storage medium. Background Art

[0002] Data resource management refers to the effective organization, coordination, planning, and control of data resources. These activities aim to ensure the proper utilization and protection of data resources throughout their lifecycle to meet the organization's needs for business operations, decision support, and innovative development. Data resource management encompasses data collection, storage, processing, analysis, and sharing, as well as the management of related policies, standards, technologies, and personnel.

[0003] To effectively manage data resources, organizations need to establish a comprehensive data resource management system. This includes clarifying data resource management goals and strategies, formulating data resource management policies and standards, establishing an organizational structure and processes for data resource management, and adopting advanced data resource management technologies and tools. Through these measures, organizations can better utilize and protect data resources, improve their quality and value, and promote business development and innovation.

[0004] Before managing data resources, it is necessary to ensure the quality and accuracy of the data. In existing technologies, data visualization technology is generally used to identify and adjust data anomalies. Data visualization technology converts large amounts of complex data into graphics, charts or other easy-to-understand visual forms, thereby helping data monitoring personnel to more quickly identify patterns, trends and outliers in the data.

[0005] However, with the advent of the big data era, the amount of data resources has increased by leaps and bounds. If data resources are still processed and analyzed according to data visualization technology, it will not only aggravate the system's data processing tasks, but also make it difficult for data monitoring personnel to more quickly identify patterns, trends and outliers in the data, and thus it will be difficult to ensure the quality and accuracy of specific data in the data resources. Summary of the Invention

[0006] In order to solve at least one of the above technical problems, the present application provides a data resource management method, apparatus, device and medium.

[0007] In a first aspect, the present application provides a data resource management method, which adopts the following technical solutions:

[0008] Acquire a data resource to be stored and a data resource scenario relatively bound to the data resource to be stored, wherein the data resource scenario is a data resource generation scenario corresponding to different resource data in the data resource to be stored;

[0009] Determining different categories of category scenario information and category scenario data corresponding to the category scenario information according to the data resource scenario;

[0010] Creating a scene category model, where the scene category model is a model created based on an image captured of a real scene corresponding to the data resource scene;

[0011] Performing secondary association construction on the scene category model based on the category scene information and the category scene data to obtain a constructed scene category model;

[0012] The data resources to be stored are input into the scenario category model for data verification to determine whether there is abnormal resource data in the data resources to be stored. If so, a data anomaly prompt is generated based on the abnormal resource data, and the data anomaly prompt includes the abnormal data resource node of the stored data resource and a data modification plan.

[0013] In a possible implementation, determining different categories of category scenario information and category scenario data corresponding to the category scenario information according to the data resource scenario includes:

[0014] Determine, based on a preset correspondence between the data resource scenario and the at least one influencing factor corresponding to the data resource scenario and the weight of each influencing factor, wherein the correspondence includes: a correspondence between the data resource scenario and the influencing factor, and the weight of the influencing factor, and the influencing factor includes: scenario type, influencing data value, scenario data, number of parameters, filtering parameters, and scenario data variation range;

[0015] Determining evaluation values ​​corresponding to different scenario information in the data resource scenario based on at least one influencing factor corresponding to the data resource scenario and the weights of the influencing factors;

[0016] It is determined whether the evaluation value meets the preset evaluation value. If so, the evaluation value is determined to be category scene information and category scene data according to the scene information corresponding to the evaluation value and the influencing factors corresponding to the evaluation value.

[0017] In one possible implementation, creating a scene category model includes:

[0018] Determine each frame of a real scene image captured during the process of creating the scene category model, wherein each frame of the real scene image carries a timestamp;

[0019] Classifying each frame of the real scene image using a pre-trained scene classification model to obtain a scene category and a scene matching degree of each frame of the real scene image;

[0020] Dividing the first preset time period into a plurality of second preset time periods according to the timestamp of each frame of the real scene image, determining the number of frames of images within the second preset time period whose scene matching degree is greater than / equal to a preset matching degree threshold, and if the determined number of frames is greater than the first frame number threshold, retaining the real scene images within the second preset time period as images whose scene matching degree satisfies the preset matching degree condition;

[0021] According to the scene categories of all real scene images, a target image of the target scene category is determined from the retained real scene images;

[0022] For target images in the target scene category whose scene matching degree meets a preset matching degree condition, sorting the target images according to video timestamps;

[0023] The score of each frame of the target image is obtained through the trained clarity evaluation model, and a scene category model is created based on the continuous frame target images that meet the preset scoring conditions.

[0024] In one possible implementation, inputting the data resources to be stored into a scene category model for data verification to determine whether abnormal resource data exists in the data resources to be stored includes:

[0025] Performing timestamp calibration on the data resource to be stored to determine the timestamp generated by the data resource to be stored;

[0026] Performing time matching based on the generated timestamp and the timestamp carried by each frame of the real scene image to obtain a data real scene image corresponding to the data resource to be stored;

[0027] Determine, according to the data real scene image, a dynamic scene model corresponding to the data real scene image in the scene category model;

[0028] Generating verification data resources according to the motion rules of the dynamic scene model;

[0029] The data resource to be stored is compared with the verification data resource to determine whether there is abnormal resource data in the data resource to be stored.

[0030] In a possible implementation, the step of generating a data anomaly prompt based on the abnormal resource data further includes:

[0031] Verify whether the abnormal resource data is processed within a preset time period after the data abnormality prompt is generated. If not, the data resource data segment to be stored containing the abnormal resource data is cut, and the data segment adjacent to the abnormal resource data and unprocessed after the cut is processed first.

[0032] In one possible implementation, obtaining a score for each frame of the target image using a trained clarity assessment model further includes:

[0033] The score means of multiple groups of continuous frame target images are calculated respectively, and the continuous frame target images that meet the preset scoring conditions are determined according to the score means.

[0034] In one possible implementation, obtaining a score for each frame of the target image using a trained clarity assessment model may also include:

[0035] A clarity evaluation model is created and trained based on the real scene image indicators of different clarity for each frame shot during the scene category model process.

[0036] In a second aspect, the present application provides a data resource management device, which adopts the following technical solution:

[0037] A data resource management device, comprising:

[0038] A resource acquisition module, configured to acquire data resources to be stored and data resource scenarios bound to the data resources to be stored, wherein the data resource scenarios are data resource generation scenarios corresponding to different resource data in the data resources to be stored;

[0039] A category determination module, configured to determine category scenario information of different categories and category scenario data corresponding to the category scenario information according to the data resource scenario;

[0040] A model creation module, configured to create a scene category model, wherein the scene category model is a model created based on an image captured of a real scene corresponding to the data resource scene;

[0041] an association construction module, configured to perform secondary association construction on the scene category model based on the category scene information and the category scene data to obtain a constructed scene category model;

[0042] A data verification module is used to input the data resources to be stored into the scene category model for data verification, determine whether there is abnormal resource data in the data resources to be stored, and if so, generate a data anomaly prompt based on the abnormal resource data. The data anomaly prompt includes the abnormal data resource node of the stored data resource and the data modification plan.

[0043] In a possible implementation, when the category determination module determines the category scenario information of different categories and the category scenario data corresponding to the category scenario information according to the data resource scenario, it is specifically configured to:

[0044] Determine, based on a preset correspondence between the data resource scenario and the at least one influencing factor corresponding to the data resource scenario and the weight of each influencing factor, wherein the correspondence includes: a correspondence between the data resource scenario and the influencing factor, and the weight of the influencing factor, and the influencing factor includes: scenario type, influencing data value, scenario data, number of parameters, filtering parameters, and scenario data variation range;

[0045] Determining evaluation values ​​corresponding to different scenario information in the data resource scenario based on at least one influencing factor corresponding to the data resource scenario and the weights of the influencing factors;

[0046] It is determined whether the evaluation value meets the preset evaluation value. If so, the evaluation value is determined to be category scene information and category scene data according to the scene information corresponding to the evaluation value and the influencing factors corresponding to the evaluation value.

[0047] In another possible implementation, when creating the scene category model, the model creation module is specifically configured to:

[0048] Determine each frame of a real scene image captured during the process of creating the scene category model, wherein each frame of the real scene image carries a timestamp;

[0049] Classifying each frame of the real scene image using a pre-trained scene classification model to obtain a scene category and a scene matching degree of each frame of the real scene image;

[0050] Dividing the first preset time period into a plurality of second preset time periods according to the timestamp of each frame of the real scene image, determining the number of frames of images within the second preset time period whose scene matching degree is greater than / equal to a preset matching degree threshold, and if the determined number of frames is greater than the first frame number threshold, retaining the real scene images within the second preset time period as images whose scene matching degree satisfies the preset matching degree condition;

[0051] According to the scene categories of all real scene images, a target image of the target scene category is determined from the retained real scene images;

[0052] For target images in the target scene category whose scene matching degree meets a preset matching degree condition, sorting the target images according to video timestamps;

[0053] The score of each frame of the target image is obtained through the trained clarity evaluation model, and a scene category model is created based on the continuous frame target images that meet the preset scoring conditions.

[0054] In another possible implementation, when the data resource to be stored is input into the scene category model for data verification to determine whether there is abnormal resource data in the data resource to be stored, the data verification module is specifically configured to:

[0055] Performing timestamp calibration on the data resource to be stored to determine the timestamp generated by the data resource to be stored;

[0056] Performing time matching based on the generated timestamp and the timestamp carried by each frame of the real scene image to obtain a data real scene image corresponding to the data resource to be stored;

[0057] Determine, according to the data real scene image, a dynamic scene model corresponding to the data real scene image in the scene category model;

[0058] Generating verification data resources according to the motion rules of the dynamic scene model;

[0059] The data resource to be stored is compared with the verification data resource to determine whether there is abnormal resource data in the data resource to be stored.

[0060] In another possible implementation, the device further includes: a data processing module, wherein:

[0061] The data processing module is used to verify whether the abnormal resource data is processed within a preset time period after the data abnormality prompt is generated. If not, the data resource data segment to be stored containing the abnormal resource data is cut, and the data segment adjacent to the abnormal resource data and unprocessed after the cut is processed first.

[0062] In another possible implementation, the device further includes: a mean value calculation module, wherein:

[0063] The mean value calculation module is used to respectively calculate the mean values ​​of the scores of multiple groups of continuous frame target images, and determine the continuous frame target images that meet the preset scoring conditions based on the mean values ​​of the scores.

[0064] In another possible implementation, the apparatus further includes: an evaluation creation module, wherein:

[0065] The evaluation creation module is used to create a clarity evaluation model and train the clarity evaluation model according to the real scene image indicators of each frame with different clarity taken in the scene classification model process to obtain a trained clarity evaluation model.

[0066] On the third side, this application provides an electronic device, which adopts the following technical solution:

[0067] at least one processor;

[0068] Memory;

[0069] At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute a data resource management method as described in any one of the first aspects.

[0070] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0071] A computer-readable storage medium stores a computer program thereon, which, when executed in a computer, causes the computer to execute the data resource management method as described in any one of the first aspects.

[0072] In summary, this application includes at least one of the following beneficial technical effects:

[0073] When verifying and managing data resources, the data resources to be stored and the data resource scenes relatively bound to the data resources to be stored are obtained, and then the category scene information of different categories and the category scene data corresponding to the category scene information are determined according to the data resource scenes, and then a scene category model is created. The scene category model is a model created according to the image captured according to the real scene corresponding to the data resource scene, and then the scene category model is secondary associated and constructed based on the category scene information and the category scene data to obtain the constructed scene category model, and then the data resources to be stored are input into the scene category model for data verification to determine whether there is abnormal resource data in the data resources to be stored. If so, a data anomaly prompt is generated based on the abnormal resource data. The data anomaly prompt includes the abnormal data resource node of the stored data resource and the data modification plan. The staff can independently select the data modification plan to modify the abnormal resource data of the abnormal data resource node, which not only saves the staff's data verification time, but also improves the quality and accuracy of data verification. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 A flowchart of a data resource management method provided in an embodiment of the present application.

[0075] Figure 2 A schematic diagram of the structure of a data resource management device provided in an embodiment of the present application.

[0076] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0077] The following is combined with Figure 1-3This application is described in further detail.

[0078] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed, but as long as they are within the scope of the present application, they are protected by patent law.

[0079] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0080] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document, unless otherwise specified, generally indicates an "or" relationship between the related objects.

[0081] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0082] The embodiment of the present application provides a method for data resource management, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The terminal device and the server can be directly or indirectly connected through wired or wireless communication. The embodiment of the present application does not limit this. Figure 1 As shown, the method includes:

[0083] Step S10: Acquire the data resource to be stored and the data resource scenario bound to the data resource to be stored.

[0084] Among them, the data resource scenario is the data resource generation scenario corresponding to different resource data in the data resources to be stored.

[0085] For the embodiments of the present application, the data resources to be stored are data resources generated by different data resource scenarios and have not been stored. For example, in a production factory, the data generated by equipment in different production links are different. Therefore, it is necessary to determine the equipment production data in combination with the production scenarios of the equipment in the production links, and determine the data resource scenario based on the data resource generation scenario.

[0086] Step S11: Determine different categories of category scenario information and category scenario data corresponding to the category scenario information according to the data resource scenario.

[0087] Specifically, the category scenario information refers to each production equipment of a production line, the category scenario data and the production data generated by each production equipment.

[0088] Specifically, based on the correspondence between the data resource scenario and the preset, at least one influencing factor corresponding to the data resource scenario and the weight of each influencing factor are determined. The correspondence includes: the correspondence between the data resource scenario and the influencing factors, and the weight of the influencing factors. The influencing factors include: scenario type, influencing data value, scenario data, number of parameters, filtering parameters and scenario data variation range. Based on at least one influencing factor corresponding to the data resource scenario and the weight of each influencing factor, the evaluation value corresponding to different scenario information in the data resource scenario is determined, and it is judged whether the evaluation value meets the preset evaluation value. If so, it is determined as category scenario information and category scenario data based on the scenario information corresponding to the evaluation value and the influencing factor corresponding to the evaluation value.

[0089] Among them, the preset evaluation value is the evaluation value output by the staff through the work terminal.

[0090] Step S12: Create a scene category model.

[0091] Among them, the scene category model is a model created based on images captured from real scenes corresponding to the data resource scene.

[0092] In an embodiment of the present application, the scene category model is a 3D model. When creating it, the image of the real scene corresponding to the data resource scene is first collected. The specific collection method can be through drone flight shooting. Multiple drones are used to perform multi-dimensional and different visual shooting of the real scene, and then the objects in the real scene image are modeled using image modeling to obtain the scene category model.

[0093] Specifically, each frame of real scene image taken in the process of creating the scene category model is determined, and each frame of real scene image carries a timestamp. Each frame of real scene image is classified by a pre-trained scene classification model to obtain the scene category and scene matching degree of each frame of real scene image. The first preset time period is divided into multiple second preset time periods according to the timestamp of each frame of real scene image, and the number of frames of images with scene matching degrees greater than / equal to a preset matching degree threshold in the second preset time period is determined. If the determined number of frames is greater than the first frame number threshold, the real scene images in the second preset time period are retained as images whose scene matching degrees meet the preset matching degree conditions. According to the scene categories of all real scene images, target images of the target scene category are determined from the retained real scene images. For target images in the target scene category whose scene matching degrees meet the preset matching degree conditions, the target images are sorted according to the video timestamps. The score of each frame of target image is obtained by the trained clarity evaluation model, and a scene category model is created based on the continuous frame target images that meet the preset scoring conditions.

[0094] Step S13: Perform secondary association construction on the scene category model based on the category scene information and the category scene data to obtain a constructed scene category model.

[0095] For this application, AR technology is applied on the basis of the scene category model, and the category scene information and category scene data are added to the scene category model for secondary association construction. Through the constructed scene category model, the different category scenes corresponding to different positions in the model and the category scene data corresponding to each category scene can be intuitively determined.

[0096] Step S14: Input the data resources to be stored into the scene category model for data verification to determine whether there is abnormal resource data in the data resources to be stored. If so, generate a data anomaly prompt based on the abnormal resource data. The data anomaly prompt includes the abnormal data resource node of the stored data resource and the data modification plan.

[0097] Specifically, the data resources to be stored are timestamp-calibrated to determine the timestamp generated by the data resources to be stored. Time alignment is performed based on the generated timestamp and the timestamp carried by each frame of the real scene image to obtain the data real scene image corresponding to the data resources to be stored. The dynamic scene model corresponding to the data real scene image in the scene category model is determined based on the data real scene image. According to the motion rules of the dynamic scene model, verification data resources are generated. The data resources to be stored are compared with the verification data resources to determine whether there is abnormal resource data in the data resources to be stored.

[0098] Based on the above embodiment, when verifying and managing data resources, the data resources to be stored and the data resource scenes relatively bound to the data resources to be stored are obtained, and then the category scene information of different categories and the category scene data corresponding to the category scene information are determined according to the data resource scenes, and then a scene category model is created. The scene category model is a model created according to the image captured according to the real scene corresponding to the data resource scene, and then the scene category model is secondary associated and constructed based on the category scene information and the category scene data to obtain the constructed scene category model, and then the data resources to be stored are input into the scene category model for data verification to determine whether there is abnormal resource data in the data resources to be stored. If so, a data anomaly prompt is generated based on the abnormal resource data. The data anomaly prompt includes the abnormal data resource node of the stored data resource and the data modification plan. The staff can independently select the data modification plan to modify the abnormal resource data of the abnormal data resource node, which not only saves the staff's data verification time, but also improves the quality and accuracy of data verification.

[0099] Furthermore, in an embodiment of the present application, a data anomaly prompt is generated based on the abnormal resource data, and then it also includes: checking whether the abnormal resource data is processed within a preset time period after the data anomaly prompt is generated. If not, the data resource data segment to be stored containing the abnormal resource data is cut, and the data segment adjacent to the abnormal resource data and unprocessed after the cut is processed first.

[0100] In one possible implementation method of the embodiment of the present application, the score of each frame target image is obtained through a trained clarity evaluation model, and it also includes: calculating the average score of multiple groups of continuous frame target images respectively, and determining the continuous frame target images that meet the preset scoring conditions based on the average score.

[0101] In one possible implementation method of the embodiment of the present application, a score for each frame of the target image is obtained through a trained clarity assessment model, which also includes: creating a clarity assessment model, and training the clarity assessment model based on the real scene image indicators of each frame with different clarity taken in the scene category model process to obtain a trained clarity assessment model.

[0102] The following is an introduction to a data resource management device provided in an embodiment of the present application. The data resource management device described below and the data resource management method described above can be referenced to each other. Please refer to Figure 2 , Figure 2 2 is a structural diagram of a data resource management device 20 provided in an embodiment of the present application, including:

[0103] The resource acquisition module 21 is used to acquire the data resources to be stored and the data resource scenarios bound to the data resources to be stored. The data resource scenarios are data resource generation scenarios corresponding to different resource data in the data resources to be stored.

[0104] A category determination module 22, configured to determine category scenario information of different categories and category scenario data corresponding to the category scenario information according to the data resource scenario;

[0105] A model creation module 23 is used to create a scene category model, where the scene category model is a model created based on images captured of real scenes corresponding to the data resource scene;

[0106] An association construction module 24 is configured to perform secondary association construction on the scene category model based on the category scene information and the category scene data to obtain a constructed scene category model;

[0107] The data verification module 25 is used to input the data resources to be stored into the scene category model for data verification, and determine whether there is abnormal resource data in the data resources to be stored. If so, a data anomaly prompt is generated based on the abnormal resource data. The data anomaly prompt includes the abnormal data resource node of the stored data resource and the data modification plan.

[0108] In one possible implementation of the embodiment of the present application, the category determination module 22 is specifically configured to:

[0109] Determine at least one influencing factor corresponding to the data resource scenario and the weight of each influencing factor based on the correspondence between the data resource scenario and the preset relationship. The correspondence includes: the correspondence between the data resource scenario and the influencing factor, and the weight of the influencing factor. The influencing factors include: scenario type, influencing data value, scenario data, number of parameters, filtering parameters, and scenario data variation range;

[0110] Determine, based on at least one influencing factor corresponding to the data resource scenario and the weight of each influencing factor, an evaluation value corresponding to different scenario information in the data resource scenario;

[0111] Determine whether the evaluation value meets the preset evaluation value. If so, determine it as category scene information and category scene data based on the scene information corresponding to the evaluation value and the influencing factors corresponding to the evaluation value.

[0112] In another possible implementation of the embodiment of the present application, the model creation module 23 is specifically configured to:

[0113] Determine each frame of a real scene image captured during the process of creating the scene category model, each frame of the real scene image carries a timestamp;

[0114] Classify each frame of real scene image through the pre-trained scene classification model to obtain the scene category and scene matching degree of each frame of real scene image;

[0115] Dividing the first preset time period into a plurality of second preset time periods according to the timestamp of each frame of the real scene image, determining the number of frames of images within the second preset time period whose scene matching degree is greater than / equal to a preset matching degree threshold, and if the determined number of frames is greater than the first frame number threshold, retaining the real scene images within the second preset time period as images whose scene matching degree satisfies the preset matching degree condition;

[0116] According to the scene categories of all real scene images, a target image of the target scene category is determined from the retained real scene images;

[0117] For target images in the target scene category whose scene matching degree meets the preset matching degree condition, the target images are sorted according to the video timestamps;

[0118] The score of each frame of the target image is obtained through the trained clarity evaluation model, and a scene category model is created based on the continuous frame target images that meet the preset scoring conditions.

[0119] In another possible implementation of the embodiment of the present application, the data verification module 25 performs data verification when inputting the data resources to be stored into the scene category model to determine whether there is abnormal resource data in the data resources to be stored, specifically for:

[0120] Perform timestamp calibration on the data resources to be stored to determine the timestamp generated by the data resources to be stored;

[0121] Perform time matching based on the generated timestamp and the timestamp carried by each frame of the real scene image to obtain the real scene image of the data corresponding to the data resource to be stored;

[0122] Determine, according to the data real scene image, a dynamic scene model corresponding to the data real scene image in the scene category model;

[0123] Generate verification data resources according to the motion rules of the dynamic scene model;

[0124] Compare the data resources to be stored with the verification data resources to determine whether there is any abnormal resource data in the data resources to be stored.

[0125] In another possible implementation of the embodiment of the present application, the apparatus 20 further includes: a data processing module, wherein:

[0126] The data processing module is used to verify whether the abnormal resource data is processed within a preset time period after the data abnormality prompt is generated. If not, the data resource data segment to be stored containing the abnormal resource data will be cut, and the data segment adjacent to the abnormal resource data and unprocessed after cutting will be processed first.

[0127] In another possible implementation of the embodiment of the present application, the apparatus 20 further includes: a mean value calculation module, wherein:

[0128] The mean calculation module is used to calculate the mean score of multiple groups of continuous frame target images respectively, and determine the continuous frame target images that meet the preset scoring conditions based on the mean score.

[0129] In another possible implementation of the embodiment of the present application, the apparatus 20 further includes: an evaluation creation module, wherein:

[0130] The evaluation creation module is used to create a clarity evaluation model and train the clarity evaluation model according to the real scene image indicators of each frame with different clarity taken in the scene category model process to obtain a trained clarity evaluation model.

[0131] An electronic device provided in an embodiment of the present application is introduced below. The electronic device described below and the data resource management method described above can refer to each other.

[0132] The present application embodiment provides an electronic device, such as Figure 3 As shown, Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3 The electronic device 300 shown includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 300 may further include a transceiver 304. It should be noted that in actual applications, the number of transceivers 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0133] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the embodiments disclosed herein. Processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0134] The bus 302 may include a path for transmitting information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0135] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0136] The memory 303 is used to store application code for executing the solution of the embodiment of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the above method embodiment.

[0137] Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0138] A computer-readable storage medium provided in an embodiment of the present application is introduced below. The computer-readable storage medium described below and the method described above can be referenced to each other.

[0139] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above data resource management method are implemented.

[0140] Since the embodiments of the computer-readable storage medium part and the embodiments of the method part correspond to each other, the embodiments of the computer-readable storage medium part refer to the description of the embodiments of the method part.

[0141] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0142] The above are only some of the implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A data resource management method, characterized in that: include: Acquire a data resource to be stored and a data resource scenario relatively bound to the data resource to be stored, wherein the data resource scenario is a data resource generation scenario corresponding to different resource data in the data resource to be stored; Determining different categories of category scenario information and category scenario data corresponding to the category scenario information according to the data resource scenario; The determining of different categories of category scenario information and category scenario data corresponding to the category scenario information according to the data resource scenario includes: Determine, based on a preset correspondence between the data resource scenario and the at least one influencing factor corresponding to the data resource scenario and the weight of each influencing factor, wherein the correspondence includes: a correspondence between the data resource scenario and the influencing factor, and the weight of the influencing factor, and the influencing factor includes: scenario type, influencing data value, scenario data, number of parameters, filtering parameters, and scenario data variation range; Determining evaluation values ​​corresponding to different scenario information in the data resource scenario based on at least one influencing factor corresponding to the data resource scenario and the weights of the influencing factors; Determine whether the evaluation value meets a preset evaluation value. If so, determine the evaluation value as category scene information and category scene data based on the scene information corresponding to the evaluation value and the influencing factors corresponding to the evaluation value. The category scene information is each production device of a production line, and the category scene data is the production data generated by each production device. Creating a scene category model, where the scene category model is a model created based on an image captured of a real scene corresponding to the data resource scene; Performing secondary association construction on the scene category model based on the category scene information and the category scene data to obtain a constructed scene category model; The data resources to be stored are input into the scenario category model for data verification to determine whether there is abnormal resource data in the data resources to be stored. If so, a data anomaly prompt is generated based on the abnormal resource data, and the data anomaly prompt includes the abnormal data resource node of the stored data resource and a data modification plan.

2. A data resource management method according to claim 1, characterized in that: The creating of the scene category model includes: Determine each frame of a real scene image captured during the process of creating the scene category model, wherein each frame of the real scene image carries a timestamp; Classifying each frame of the real scene image using a pre-trained scene classification model to obtain a scene category and a scene matching degree of each frame of the real scene image; Dividing the first preset time period into a plurality of second preset time periods according to the timestamp of each frame of the real scene image, determining the number of frames of images within the second preset time period whose scene matching degree is greater than / equal to a preset matching degree threshold, and if the determined number of frames is greater than the first frame number threshold, retaining the real scene images within the second preset time period as images whose scene matching degree satisfies the preset matching degree condition; According to the scene categories of all real scene images, a target image of the target scene category is determined from the retained real scene images; For target images in the target scene category whose scene matching degree meets a preset matching degree condition, sorting the target images according to video timestamps; The score of each frame of the target image is obtained through the trained clarity evaluation model, and a scene category model is created based on the continuous frame target images that meet the preset scoring conditions.

3. A data resource management method according to claim 2, characterized in that: The step of inputting the data resources to be stored into the scene category model for data verification to determine whether there is abnormal resource data in the data resources to be stored includes: Performing timestamp calibration on the data resource to be stored to determine the timestamp generated by the data resource to be stored; Performing a time comparison based on the generated timestamp and the timestamp carried by each frame of the real scene image to obtain a data real scene image corresponding to the data resource to be stored; Determine, according to the data real scene image, a dynamic scene model corresponding to the data real scene image in the scene category model; Generating verification data resources according to the motion rules of the dynamic scene model; The data resource to be stored is compared with the verification data resource to determine whether there is abnormal resource data in the data resource to be stored.

4. A data resource management method according to claim 1, characterized in that: The step of generating a data anomaly prompt based on the abnormal resource data further includes: Verify whether the abnormal resource data is processed within a preset time period after the data abnormality prompt is generated. If not, the data resource data segment to be stored containing the abnormal resource data is cut, and the data segment adjacent to the abnormal resource data and unprocessed after the cut is processed first.

5. A data resource management method according to claim 2, characterized in that: The step of obtaining a score for each frame of the target image through the trained clarity evaluation model further includes: The score means of multiple groups of continuous frame target images are calculated respectively, and the continuous frame target images that meet the preset scoring conditions are determined according to the score means.

6. A data resource management method according to claim 2, characterized in that: The score of each frame of the target image is obtained by using the trained clarity evaluation model, which also includes: A clarity evaluation model is created, and the clarity evaluation model is trained according to indicators of real scene images of different clarity for each frame captured during the scene classification model process to obtain a trained clarity evaluation model.

7. A data resource management device, characterized in that: include: A resource acquisition module, configured to acquire data resources to be stored and data resource scenarios bound to the data resources to be stored, wherein the data resource scenarios are data resource generation scenarios corresponding to different resource data in the data resources to be stored; A category determination module, configured to determine category scenario information of different categories and category scenario data corresponding to the category scenario information according to the data resource scenario; When determining category scenario information of different categories and category scenario data corresponding to the category scenario information according to the data resource scenario, the category determination module is specifically configured to: Determine, based on a preset correspondence between the data resource scenario and the at least one influencing factor corresponding to the data resource scenario and the weight of each influencing factor, wherein the correspondence includes: a correspondence between the data resource scenario and the influencing factor, and the weight of the influencing factor, and the influencing factor includes: scenario type, influencing data value, scenario data, number of parameters, filtering parameters, and scenario data variation range; Determining evaluation values ​​corresponding to different scenario information in the data resource scenario based on at least one influencing factor corresponding to the data resource scenario and the weights of the influencing factors; Determine whether the evaluation value meets a preset evaluation value. If so, determine the evaluation value as category scene information and category scene data based on the scene information corresponding to the evaluation value and the influencing factors corresponding to the evaluation value. The category scene information is each production device of a production line, and the category scene data is the production data generated by each production device. A model creation module, configured to create a scene category model, wherein the scene category model is a model created based on an image captured of a real scene corresponding to the data resource scene; an association construction module, configured to perform secondary association construction on the scene category model based on the category scene information and the category scene data to obtain a constructed scene category model; A data verification module is used to input the data resources to be stored into the scene category model for data verification, determine whether there is abnormal resource data in the data resources to be stored, and if so, generate a data anomaly prompt based on the abnormal resource data. The data anomaly prompt includes the abnormal data resource node of the stored data resource and the data modification plan.

8. An electronic device, characterized in that: include: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute a data resource management method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The device stores a computer program that can be loaded by a processor and executes a data resource management method according to any one of claims 1 to 6.

Images