Multimedia data processing method and device, computer device and storage medium

Abstract

The embodiment of the application relates to the technical field of data transmission, and discloses a multimedia data processing method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring at least one piece of multimedia data and constructing a corresponding relationship between each piece of multimedia data and a target algorithm identifier; determining a target algorithm package corresponding to each target algorithm identifier from a preset algorithm warehouse, wherein the target algorithm package comprises target algorithm data and target environment data; constructing a corresponding relationship between each target algorithm package and a target resource, and creating a target running environment of the target algorithm data in the target resource according to the corresponding target environment data, so as to obtain a target algorithm container corresponding to each target algorithm package; determining target multimedia data corresponding to each target algorithm container based on the corresponding relationship between the multimedia data and the target algorithm identifier; and processing the corresponding target multimedia data through each target algorithm container to obtain monitoring results corresponding to each target multimedia data.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of data transmission, and in particular to a multimedia data processing method and device, computer equipment and a storage medium. BACKGROUND

[0002] With the rapid evolution of artificial intelligence technology, it has become an inevitable choice to use artificial intelligence technology to analyze multimedia data.

[0003] In order to provide different application services for multimedia data, it is necessary to integrate various algorithms in the platform. The traditional algorithm integration scheme of the platform is an algorithm software development kit (SDK) integration scheme.

[0004] In the algorithm SDK integration scheme, the algorithm data of various algorithms is uniformly managed by the SDK algorithm warehouse. Since the algorithm data cannot be directly run alone, the algorithm data of various algorithms is encapsulated into different algorithm services, and these algorithm services run on a unified basic hardware facility to provide support to the upper-layer application system through the algorithm services. However, the algorithm services need to integrate the algorithm data of various algorithms, and the basic dependent running environment of the algorithm data is complex, and the dependencies of different algorithm SDKs are different. In order to run the SDKs of different algorithms in the hardware facility computing resource, different running environments need to be installed in advance in the hardware facility corresponding to the algorithm service during the development of the algorithm service, and the corresponding relationship between each running environment and the algorithm data needs to be constructed. Therefore, the integration workload of the algorithm service in the prior art during development is very large. SUMMARY

[0005] Embodiments of the present application provide a multimedia data processing method and device, computer equipment and a storage medium, which can reduce the integration workload during the development of the algorithm service.

[0006] In a first aspect, embodiments of the present application provide a multimedia data processing method, comprising:

[0007] Obtaining at least one multimedia data and constructing a corresponding relationship between each of the multimedia data and a target algorithm identifier, one target algorithm identifier corresponding to at least one of the multimedia data, and one of the multimedia data corresponding to at least one target algorithm identifier, the multimedia data including at least one of security scene multimedia data, smart city multimedia data and industrial scene multimedia data;

[0008] Determining a target algorithm package corresponding to each of the target algorithm identifiers from a preset algorithm warehouse, the target algorithm package including target algorithm data and target environment data dependent on the target algorithm data, and the algorithm warehouse storing a plurality of algorithm packages;

[0009] respectively, and a target running environment for creating the target algorithm data according to the corresponding target environment data in the target resource, to obtain a target algorithm container corresponding to each target algorithm package respectively, one target algorithm identifier corresponding to at least one target resource;

[0010] determining target multimedia data corresponding to each target algorithm container respectively from at least one piece of the multimedia data based on the correspondence between the multimedia data and the target algorithm identifier;

[0011] processing the corresponding target multimedia data through each target algorithm container to obtain monitoring results corresponding to each target multimedia data respectively.

[0012] In a second aspect, the embodiments of the present application further provide a multimedia data processing apparatus, comprising:

[0013] a transceiving module configured to acquire at least one piece of multimedia data, the multimedia data comprising at least one of security scene multimedia data, smart city multimedia data, and industrial scene multimedia data;

[0014] a processing module configured to establish a correspondence between each piece of the multimedia data and a target algorithm identifier, one target algorithm identifier corresponding to at least one piece of the multimedia data, and one piece of the multimedia data corresponding to at least one target algorithm identifier; determine target algorithm packages corresponding to each target algorithm identifier respectively from a preset algorithm warehouse, the target algorithm packages comprising target algorithm data and target environment data relied on by the target algorithm data, the algorithm warehouse storing a plurality of algorithm packages; establish a correspondence between each target algorithm package and a target resource, and create a target running environment for the target algorithm data according to the corresponding target environment data in the target resource, to obtain a target algorithm container corresponding to each target algorithm package respectively, one target algorithm identifier corresponding to at least one target resource; determine target multimedia data corresponding to each target algorithm container respectively from at least one piece of the multimedia data based on the correspondence between the multimedia data and the target algorithm identifier; and process the corresponding target multimedia data through each target algorithm container to obtain monitoring results corresponding to each target multimedia data respectively.

[0015] In some embodiments, the target multimedia data is a target data queue; and the processing module, when performing the step of processing the corresponding target multimedia data through each target algorithm container to obtain monitoring results corresponding to each target multimedia data respectively, is specifically configured to:

[0016] add queue data in the target data queue to a data cache pool;

[0017] read operation is performed on the corresponding queue data in the data cache pool in a distributed task manner in each target algorithm container, and the read queue data is processed respectively to obtain a monitoring result corresponding to each target multimedia data respectively.

[0018] In some embodiments, after performing the step of processing the corresponding target multimedia data by each target algorithm container respectively, the processing module is further configured to:

[0019] monitor resource utilization of each target algorithm container;

[0020] when a first resource utilization is monitored and a duration of existence of the first resource utilization is greater than a first preset duration threshold, performing capacity expansion processing on a first algorithm container corresponding to the first resource utilization, the first resource utilization being greater than a first preset utilization threshold of the resource utilization;

[0021] when a second resource utilization is detected and a duration of existence of the second resource utilization is greater than a second preset duration threshold, performing capacity reduction processing on a second algorithm container corresponding to the second resource utilization, the second resource utilization being less than a second preset utilization threshold of the resource utilization.

[0022] In some embodiments, after performing the step of processing the corresponding target multimedia data by each target algorithm container respectively, the processing module is further configured to:

[0023] determining a target algorithm package that meets a preset resource adjustment condition as a to-be-adjusted algorithm package;

[0024] receiving a resource adjustment instruction of a management user for the to-be-adjusted algorithm package;

[0025] performing capacity expansion processing or capacity reduction processing on a third algorithm container corresponding to the to-be-adjusted algorithm package according to the resource adjustment instruction.

[0026] In some embodiments, when performing the step of respectively constructing the corresponding relationship between each target algorithm package and target resource, the processing module is specifically configured to:

[0027] determining a plurality of idle resources in a preset computing resource pool;

[0028] determining a target resource corresponding to each target algorithm package from the plurality of idle resources according to a theoretical resource corresponding to each target algorithm package respectively, and respectively constructing a corresponding relationship between each target algorithm package and target resource.

[0029] In some embodiments, the processing module is further configured to, before performing the step of determining the target resource corresponding to each target algorithm package from the plurality of idle resources according to the theoretical resource corresponding to each target algorithm package, determine a theoretical resource sum of the theoretical resources.

[0030] determine a theoretical resource sum of the theoretical resources.

[0031] determine whether the theoretical resource sum is greater than an idle resource sum corresponding to the plurality of idle resources.

[0032] The step of determining the target resource corresponding to each target algorithm package from the plurality of idle resources according to the theoretical resource corresponding to each target algorithm package includes:

[0033] if the theoretical resource sum is greater than the idle resource sum, determining a target priority corresponding to each target algorithm package according to a preset correspondence between algorithm packages and priorities.

[0034] determining the target resource corresponding to each target algorithm package from the plurality of idle resources according to the target priority corresponding to each target algorithm package and the theoretical resource corresponding to each target algorithm package.

[0035] In some embodiments, the processing module, when performing the step of constructing the correspondence between each multimedia data and target algorithm package, is specifically configured to:

[0036] obtain a data type corresponding to each multimedia data.

[0037] construct the correspondence between each multimedia data and target algorithm package according to the data type and a preset correspondence between data types and algorithm packages.

[0038] In a third aspect, an embodiment of the present application further provides a computer device, which includes a memory and a processor, the memory has stored thereon a computer program, and the processor implements the above method when executing the computer program.

[0039] In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium, which stores a computer program, the computer program includes program instructions, and the program instructions can implement the above method when executed by a processor.

[0040] In a fifth aspect, an embodiment of the present application provides a chip, which includes a transceiver coupled with a terminal and is configured to execute the technical solution provided in the first aspect of the present application.

[0041] In a sixth aspect, an embodiment of the present application provides a chip system, which comprises a processor configured to support a terminal to implement functions involved in the first aspect, for example, to generate or process information involved in the multimedia data processing method provided in the first aspect. In a possible design, the chip system further comprises a memory configured to store program instructions and data necessary for the terminal. The chip system can be composed of a chip, or can include the chip and other discrete devices.

[0042] In a seventh aspect, an embodiment of the present application provides a computer program product containing instructions, which, when executed on a computer, cause the computer to perform the multimedia data processing method provided in the first aspect, and thus achieve the beneficial effects of the multimedia data processing method provided in the first aspect.

[0043] Compared with the prior art, in the scheme provided in the embodiments of the present application, in the first aspect, since the algorithm data and the corresponding environment data are integrated in an algorithm package, the corresponding environment data is called when the corresponding algorithm data is called, and the environment data suitable for running the corresponding algorithm data in the algorithm package can be deployed by calling the data package, so that when the algorithm service is developed, it is not necessary to deploy various dependent environments in the computing resource in advance, and it is not necessary to construct the corresponding relationship between the dependent environment and the algorithm data, and thus the integration workload when the algorithm service is developed can be reduced through the embodiments; in the second aspect, the algorithm data and the environment data are packaged together, and when the algorithm data and / or the environment data are updated, the corresponding algorithm package can be directly updated, since the algorithm data and the environment data in the algorithm package are associated, the problem that the updated algorithm data depends on the old environment data can be avoided, and the algorithm can be more flexibly adapted to the update iteration in the later stage through the present application. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0045] Figure 1 An application scenario diagram of the multimedia data processing method provided in the embodiments of the present application;

[0046] Figure 2 A flowchart of the multimedia data processing method provided in the embodiments of the present application;

[0047] Figure 3 A diagram of a computing resource pool provided in the embodiments of the present application;

[0048] Figure 4 A schematic block diagram of a multimedia data processing apparatus provided by an embodiment of the present application;

[0049] Figure 5 A schematic diagram of a structure of a server in an embodiment of the present application;

[0050] Figure 6 A schematic diagram of a structure of a terminal in an embodiment of the present application;

[0051] Figure 7 A schematic diagram of another structure of a server in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The terms "first", "second", and the like in the description and claims of the present application and the above drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged, where appropriate, so that the embodiments described herein can be carried out in other than the order shown or described herein. Furthermore, the terms "comprise" and "have" and any variations thereof are intended to cover a non-exclusive inclusion, for example, a process, method, system, product, or apparatus that comprises a list of steps or modules as non-limiting examples of the process, method, system, product, or apparatus can include not only those steps or modules that are expressly listed, but also other steps or modules that are not expressly listed or inherent to such process, method, product, or apparatus. The division of modules in the embodiments of the present application is only a logical division, and in actual application, another division mode can be used, for example, a plurality of modules can be combined or integrated into another system, or some features can be omitted or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed modules can be through an interface, and the indirect coupling or communication connection between the modules can be electrical or other similar forms, which are not limited in the embodiments of the present application. In addition, the modules or sub-modules described as separate components can or can not be physically separate, can or can not be physical modules, or can be distributed into a plurality of circuit modules, and some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0053] The embodiments of the present application provide a multimedia data processing method, apparatus, computer device, and storage medium. The execution subject of the multimedia data processing method can be a multimedia data processing apparatus provided by the embodiments of the present application, or a computer device integrated with the multimedia data processing apparatus. The multimedia data processing apparatus can be realized in the form of hardware or software. The computer device can be a terminal or a server.

[0054] When the computer device is a server, the server can be a stand-alone physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, and basic cloud computing services such as big data and artificial intelligence platforms.

[0055] When the computer device is a terminal, the terminal can include a smartphone, a tablet computer, a notebook computer, a desktop computer, a smart television, a smart speaker, a personal digital assistant (PDA), a desktop computer, a smart watch, and the like, but is not limited thereto.

[0056] The scheme of the embodiments of the present application can be implemented based on artificial intelligence technology, and specifically relates to the field of computer vision technology in artificial intelligence technology and the fields of cloud computing, cloud storage, and databases in cloud technology, which will be introduced respectively.

[0057] Artificial intelligence (AI) is the use of digital computers or machine controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology of computer science, which aims to understand the essence of intelligence and produce a new intelligent machine that can react in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that machines have the functions of perception, reasoning and decision-making.

[0058] Artificial intelligence technology is a comprehensive discipline, involving a wide range of fields, both hardware and software technologies. Artificial intelligence basic technologies generally include sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, and the like. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0059] Computer Vision (CV) Computer vision is a science that studies how to make machines "see". More specifically, it refers to using cameras and computers to replace human eyes to identify, track and measure targets, and further process graphics so that the computer processing becomes images that are more suitable for human observation or transmitted to instruments for detection. As a scientific discipline, computer vision researches related theories and technologies, and attempts to establish artificial intelligence systems that can obtain information from images or multidimensional data. Computer vision technology usually includes image processing, model robustness detection, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content / behavior recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping, and other technologies. It also includes common model robustness detection, fingerprint recognition, and other biometric identification technologies.

[0060] With the research and progress of artificial intelligence technology, artificial intelligence technology has been researched and applied in many fields, such as common smart home, smart wearable device, virtual assistant, smart speaker, smart marketing, unmanned vehicle, autonomous vehicle, unmanned aerial vehicle, robot, smart medical treatment, smart customer service, etc. It is believed that with the development of technology, artificial intelligence technology will be applied in more fields and play an increasingly important role.

[0061] The scheme of the embodiments of the present application can be implemented based on cloud technology, specifically in the technical fields of cloud computing, cloud storage and database in cloud technology, which will be introduced respectively.

[0062] Cloud technology refers to a kind of hosting technology that unifies a series of resources such as hardware, software and network in a wide area network or local area network to realize data calculation, storage, processing and sharing. Cloud technology is a general term for network technology, information technology, integration technology, management platform technology and application technology based on cloud computing business model application, which can form a resource pool and be used on demand. Cloud computing technology will become an important support. The background service of the technical network system needs a large amount of computing and storage resources, such as video websites, image websites and more portals. With the high development and application of the Internet industry, every item may have its own identification mark in the future, which needs to be transmitted to the background system for logical processing. Different levels of data will be processed separately, and various industry data will need strong system support, which can only be realized through cloud computing. The embodiments of the present application can save the recognition results through cloud technology.

[0063] Cloud storage is a new concept extended and developed on the basis of cloud computing concept. Distributed cloud storage system (hereinafter referred to as storage system) refers to a storage system that collects a large number of various types of storage devices (storage device is also referred to as storage node) in a network through cluster application, grid technology and distributed storage file system, etc. to work cooperatively to provide data storage and business access functions. In the embodiments of the present application, network configuration information, etc. can be saved in the storage system, which is convenient for server to retrieve.

[0064] At present, the storage method of the storage system is as follows: a logical volume is created, and a physical storage space is allocated to each logical volume when the logical volume is created. The physical storage space can be a disk of a certain storage device or a disk group of several storage devices. The client stores data on a certain logical volume, that is, stores data on a file system. The file system divides the data into many parts, each part being an object. The object contains not only data but also additional information such as data ID (ID entity). The file system writes each object into the physical storage space of the logical volume, and records the storage location information of each object. Thus, when the client requests to access data, the file system can enable the client to access the data according to the storage location information of each object.

[0065] The process of allocating the physical storage space to the logical volume by the storage system is as follows: the physical storage space is divided into sections in advance according to the capacity estimation of the object stored in the logical volume (the estimation often has a large margin relative to the actual capacity of the object to be stored) and the group of RAID (Redundant Array of Independent Disk). A logical volume can be understood as a section, so that the logical volume is allocated with the physical storage space.

[0066] Database (Database) can be briefly regarded as an electronic file cabinet, i.e. a place for storing electronic files. Users can perform operations such as adding, querying, updating and deleting data in the files. The so-called "database" is a collection of data stored together in a certain way, shared by multiple users, with as little redundancy as possible, and independent of application programs.

[0067] A database management system (DBMS) is a computer software system that controls the storage, retrieval, security, backup, etc. of a database. A DBMS can be classified according to the database model it supports, such as relational, XML; or the computer types it supports, such as server clusters, mobile phones; or the query languages it supports, such as SQL, XQuery; or the performance focus, such as maximum size, highest speed; or other ways. Regardless of the classification, some DBMSs can cross categories, such as supporting multiple query languages. In the embodiments of the present application, the recognition result can be stored in the database management system, so as to facilitate the server to retrieve.

[0068] It should be noted that the service terminal in the embodiments of the present application can be a device that provides voice and / or data connectivity to the service terminal, a handheld device with wireless connection function, or other processing devices connected to a wireless modem. For example, mobile phones (also known as "cellular" phones) and computers with mobile terminals, such as portable, pocket, handheld, built-in computer or vehicle-mounted mobile devices, which exchange voice and / or data with a wireless access network. For example, personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), etc.

[0069] Next, in order to illustrate the specific application scenario of multimedia data processing in the embodiments of the present application, please refer to Figure 1 A multimedia data processing diagram is provided in the embodiments of the present application.

[0070] The multimedia data processing method can be applied to a multimedia data processing device, and the multimedia data processing device can communicate with one or more multimedia data collection devices. Each multimedia data collection device can collect images in different geographical locations or scenes (such as security scenes, smart cities, industrial scenes, etc.), and the obtained multimedia data includes at least one of security scene multimedia data, smart city multimedia data, and industrial scene multimedia data. After each multimedia data collection device collects multimedia data, the multimedia data is uploaded to the corresponding multimedia data processing device for monitoring and identification processing.

[0071] The multimedia data processing device and the multimedia data processing device can be centrally deployed or separately deployed, and the embodiments of the present application do not limit this, but only take the separately deployed as an example.

[0072] After at least one multimedia data collection device collects at least one multimedia data, the at least one multimedia data is sent to the multimedia data processing device. After the multimedia data processing device obtains the at least one multimedia data, it first constructs a corresponding relationship between each of the multimedia data and a target algorithm identifier, then determines a target algorithm package corresponding to each of the target algorithm identifiers from a preset algorithm warehouse, wherein the target algorithm package includes target algorithm data and target environment data dependent on the target algorithm data; then constructs a corresponding relationship between each target algorithm package and a target resource, and creates a target running environment of the target algorithm data in the target resource according to the corresponding target environment data, to obtain a target algorithm container corresponding to each of the target algorithm packages; finally, based on the corresponding relationship between the multimedia data and the target algorithm identifier, determines a target multimedia data corresponding to each of the target algorithm containers from the at least one multimedia data; and processes the corresponding target multimedia data through each target algorithm container to obtain a monitoring result corresponding to each target multimedia data.

[0073] Specifically, in the embodiment, the algorithm data required by different algorithm services and the environment data dependent on the algorithm data need to be packaged together to obtain an algorithm package, for example, the algorithm data and the corresponding environment data are encapsulated into an image, and then the obtained algorithm package is uploaded to the algorithm warehouse for unified management.

[0074] In the embodiment, the algorithm data and the environment data dependent on the algorithm data are packaged into an algorithm package, and the algorithm package is stored in the algorithm warehouse. In the algorithm warehouse, the full life cycle management of the algorithm package can be supported, including uploading, registering, viewing, modifying, distributing, deleting, etc.

[0075] In the following, the technical solutions of the present application will be described in detail with reference to specific embodiments.

[0076] Please refer toFigure 2 A multimedia data processing method provided by an embodiment of the present application is described below, which is applied to a multimedia data processing device. The embodiment of the present application includes:

[0077] Figure 2 FIG. 1 is a flowchart of the multimedia data processing method provided by the embodiment of the present application. As shown in FIG. 1, the method includes the following steps S110-S150. Figure 2

[0078] S110, acquiring at least one piece of multimedia data and constructing a correspondence between each of the multimedia data and a target algorithm identifier.

[0079] In the embodiment, one target algorithm identifier corresponds to at least one piece of the multimedia data, and one piece of the multimedia data corresponds to at least one target algorithm identifier. The multimedia data includes at least one of security scene multimedia data, smart city multimedia data, and industrial scene multimedia data.

[0080] Specifically, the multimedia data in the embodiment can be video data, audio data, or picture data, and the specific data type is not limited herein.

[0081] In the embodiment, after acquiring at least one piece of multimedia data from at least one multimedia data acquisition device, in order to determine which algorithm should be used to process different multimedia data respectively, a correspondence between each of the multimedia data and a target algorithm identifier needs to be constructed, and the specific construction steps are as follows:

[0082] Acquiring a data type corresponding to each of the multimedia data respectively; and then constructing a correspondence between each of the multimedia data and a target algorithm identifier according to the data type and a preset correspondence between a data type and an algorithm identifier.

[0083] Specifically, the embodiment can set a corresponding interface for different multimedia data acquisition devices, and set a corresponding data type for different interfaces (i.e., the multimedia data of the corresponding data type can be acquired through the interface), for example, the data type corresponding to interface 1 is data type a, and the data type corresponding to interface 2 is data type b. At this time, the data type of the multimedia data acquired through interface 1 is determined as data type a, and the data type of the multimedia data acquired through interface 2 is determined as data type b. The embodiment is preset with a correspondence between a data type and an algorithm identifier, and after the data type of the multimedia data is determined, the corresponding algorithm identifier can be determined according to the correspondence, wherein the algorithm identifier is an algorithm identifier corresponding to an algorithm package in an algorithm warehouse.

[0084] S120, determining a target algorithm package corresponding to each of the target algorithm identifiers from a preset algorithm warehouse. ​

[0085] The target algorithm package includes target algorithm data and target environment data on which the target algorithm data depends, and the algorithm repository stores multiple algorithm packages.

[0086] Specifically, in this embodiment, after determining the target algorithm identifier corresponding to each multimedia data in at least one multimedia data, the target algorithm package corresponding to each target algorithm identifier is determined from the algorithm repository, that is, the target algorithm package corresponding to each multimedia data is determined.

[0087] S130. Construct the correspondence between each target algorithm package and the target resource, and create the target running environment of the target algorithm data in the target resource according to the corresponding target environment data, so as to obtain the target algorithm container corresponding to each target algorithm package.

[0088] In this context, each target algorithm identifier corresponds to at least one target resource.

[0089] In this embodiment, after determining the target algorithm package corresponding to each multimedia data, the correspondence between each target algorithm package and the target resource will be further constructed, that is, the amount of computing power resources corresponding to each target algorithm package will be determined.

[0090] In some embodiments, during the development phase of the algorithm service, it is necessary to manage multiple computing servers in a unified manner to form a cluster, and pool the computing resources of each server, with each computing card being a computing slot in the computing resource pool, that is, a computing card being used as a computing resource in the computing resource pool.

[0091] like Figure 3 As shown, Figure 3 This is a schematic diagram of the computing power resource pool provided in this embodiment. The computing power resource pool includes multiple computing power slots. The algorithm A container is an algorithm container created by the target algorithm package A in the computing power slot. The algorithm B container is an algorithm container created by the target algorithm package B in the computing power slot. The algorithm C container is an algorithm container created by the target algorithm package C in the computing power slot. The resource slots are idle resources.

[0092] At this point, when constructing the correspondence between target algorithm packages and target resources, it is first necessary to obtain multiple idle resources in the computing power resource pool, and then, based on the theoretical resources corresponding to each target algorithm package, determine the target resources corresponding to each target algorithm package from the multiple idle resources, and construct the correspondence between each target algorithm package and target resource respectively.

[0093] The idle resources are those not currently occupied by the algorithm, while the theoretical resources are the computing power resources required by the corresponding algorithm package as set by the user.

[0094] For example, 10 idle resources are obtained from the computing resource pool, the theoretical resource corresponding to the target algorithm package 1 is 3 computing resources, and the theoretical resource corresponding to the target algorithm package 2 is 5 computing resources. At this time, 3 computing resources are allocated to the target algorithm package 1 and 5 computing resources are allocated to the target algorithm package 2 from the 10 idle resources.

[0095] Further, in some embodiments, in order to reasonably allocate idle resources, before allocating idle resources to each target algorithm package, it is necessary to first determine the theoretical resource sum of each theoretical resource; and then determine whether the theoretical resource sum is greater than the idle resource sum corresponding to the plurality of idle resources.

[0096] If the theoretical resource sum is less than or equal to the idle resource sum, it indicates that the idle computing resources are sufficient, and the computing resources can be directly allocated to each target algorithm package according to the theoretical resource corresponding to each target algorithm package.

[0097] If the theoretical resource sum is greater than the idle resource sum, it indicates that the idle computing resources are insufficient at this time, and in order to reasonably allocate idle resources, the resource allocation needs to be combined with the priority of each target algorithm package, that is, the idle resources are preferentially allocated to the target algorithm package with high priority.

[0098] That is, if the theoretical resource sum is greater than the idle resource sum, the target priority corresponding to each target algorithm package is determined according to the preset correspondence between the algorithm package and the priority; and the target resource corresponding to each target algorithm package is determined from the plurality of idle resources according to the target priority corresponding to each target algorithm package and the theoretical resource corresponding to each target algorithm package.

[0099] For example, the theoretical resource corresponding to the target algorithm package 1 is 3 computing resources, and the theoretical resource corresponding to the target algorithm package 2 is 5 computing resources. At this time, the theoretical resource sum is 8, and if the idle resource is only 6, the resource allocation needs to be further combined with the priority of each target algorithm package. If the priority of the target algorithm package 2 is 2 and the priority of the target algorithm package 1 is 1 according to the preset correspondence between the algorithm package and the priority, the priority of the target algorithm package 2 is higher than that of the target algorithm package 1, so the resources need to be preferentially allocated to the target algorithm package 2 to meet the resource required by the algorithm package with high priority. At this time, 5 computing resources are allocated to the target algorithm package 2 as target resources from the 6 idle resources, and 1 computing resource is allocated to the target algorithm package 1 as target resources from the remaining idle resources.

[0100] The embodiment adopts containerization means to decouple algorithms and computing power, can dispatch algorithms to corresponding resources according to actual use scenarios, create a target running environment of the target algorithm data in the target resource according to the corresponding target environment data, obtain a target algorithm container corresponding to each target algorithm package, and when the corresponding algorithm is not needed, the corresponding algorithm container can be destroyed to release the computing power resource, and the computing power resource can be dispatched again for use by other algorithms. It can be seen that the embodiment can improve the utilization rate of computing power resources.

[0101] S140, determining target multimedia data corresponding to each target algorithm container from at least one piece of multimedia data based on the correspondence between the multimedia data and the target algorithm identifier.

[0102] In the embodiment, the correspondence between each multimedia data and the target algorithm container can be determined according to the correspondence between the multimedia data and the target algorithm identifier, and the correspondence between the target algorithm identifier and the target algorithm container. After the correspondence between each multimedia data and the target algorithm container is determined, each target algorithm container can determine the target multimedia data to be processed from at least one piece of multimedia data according to the correspondence.

[0103] S150, processing the corresponding target multimedia data by each target algorithm container to obtain monitoring results corresponding to each target multimedia data.

[0104] In the embodiment, after determining the target multimedia data corresponding to each target algorithm container, each target algorithm container reads and processes the corresponding target multimedia data to obtain the corresponding monitoring results.

[0105] In some embodiments, the target multimedia data is a target data queue, and the embodiment uses a distributed task mode for data processing to improve the processing efficiency of data. Specifically, each target algorithm container determines the monitoring results corresponding to each target multimedia data by the following steps: adding queue data in the target data queue to a data cache pool; performing a read operation on the corresponding queue data in the data cache pool in each target algorithm container in a distributed task mode, and processing the read queue data to obtain monitoring results corresponding to each target multimedia data.

[0106] In order to further reasonably utilize computing power resources, the embodiment of the application also realizes dynamic scaling of computing power resources by automatic or manual methods.

[0107] The automatic scaling of the computing resource is realized through the following steps: monitoring resource utilization of each target algorithm container; when a first resource utilization is monitored and a duration of the first resource utilization is greater than a first preset duration threshold, performing expansion processing on a first algorithm container corresponding to the first resource utilization, the first resource utilization being greater than the resource utilization of a first preset utilization threshold; when a second resource utilization is detected and a duration of the second resource utilization is greater than a second preset duration threshold, performing contraction processing on a second algorithm container corresponding to the second resource utilization, the second resource utilization being less than the resource utilization of a second preset utilization threshold.

[0108] Specifically, a resource state monitoring module is arranged to monitor the computing resource used by each target algorithm container in real time. When the computing resource utilization exceeds a threshold and lasts for a certain time, automatic expansion is performed to increase the computing resource for running the algorithm container. Meanwhile, the multimedia data to be calculated is distributed to all algorithm containers through load balancing. When the computing resource utilization is lower than the threshold and lasts for a certain time, automatic contraction is performed to remove part of the algorithm containers and release the corresponding computing resource.

[0109] The manual scaling of the computing resource is realized through the following steps: determining a target algorithm package meeting a preset resource adjustment condition as a to-be-adjusted algorithm package; receiving a resource adjustment instruction of a management user for the to-be-adjusted algorithm package; and performing expansion processing or contraction processing on a third algorithm container corresponding to the to-be-adjusted algorithm package according to the resource adjustment instruction, the resource adjustment instruction including a quantity of computing resource to be adjusted by the to-be-adjusted algorithm package, and the preset resource adjustment condition being the first resource utilization and the second resource utilization. After detecting the to-be-adjusted algorithm package meeting the preset resource adjustment condition, an algorithm exception information is generated, the algorithm exception information including information of the to-be-adjusted algorithm package. After the management user sees the algorithm exception information, the management user manually performs resource scaling processing on the to-be-adjusted algorithm package and inputs the resource adjustment instruction. After the device receives the resource adjustment instruction, the algorithm container of the algorithm package corresponding to the resource adjustment instruction is subjected to the expansion processing or the contraction processing.

[0110] In summary, the solutions provided in this application have the following advantages: First, since this solution integrates algorithm data and corresponding environment data into an algorithm package, when calling the corresponding algorithm data, its corresponding environment data will be called simultaneously. By calling the data package, suitable environment data for the corresponding algorithm data in the algorithm package can be deployed. Therefore, during algorithm service development, it is not necessary to pre-deploy various dependent environments in computing resources, nor is it necessary to build a correspondence between dependent environments and algorithm data. Thus, this embodiment can reduce the integration workload during algorithm service development. Second, by packaging algorithm data and environment data together, when there are updates to algorithm data and / or environment data, the corresponding algorithm package can be directly updated. Since the algorithm data and environment data in the algorithm package are related, the problem of updated algorithm data depending on old environment data can be avoided. This application can more flexibly adapt to later algorithm updates and iterations.

[0111] Figures 1 to 3 Any technical feature mentioned in the embodiments corresponding to any one of the above also applies to the embodiments of this application. Figures 4 to 7 The corresponding implementation examples will not be repeated hereafter.

[0112] The above describes a multimedia data processing method according to an embodiment of this application. The following describes a multimedia data processing device (e.g., a server, a user terminal) that performs the above multimedia data processing method.

[0113] See Figure 4 ,like Figure 4 The diagram shows a structure of a multimedia data processing device 400, which can be applied to monitoring scenarios such as security, smart cities, and industrial settings. The multimedia data processing device 400 in this embodiment can achieve the functions described above. Figures 1-3 The steps of the multimedia data processing method executed in any corresponding embodiment. The functions implemented by the multimedia data processing device 400 can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions, and the modules can be software and / or hardware. The multimedia data processing device 400 may include a transceiver module 401 and a processing module 402, wherein:

[0114] The transceiver module 401 is used to acquire at least one piece of multimedia data, which includes at least one of security scenario multimedia data, smart city multimedia data, and industrial scenario multimedia data.

[0115] The processing module 402 is configured to: construct a correspondence relationship between each of the multimedia data and a target algorithm identifier, one target algorithm identifier corresponding to at least one piece of the multimedia data, and one piece of the multimedia data corresponding to at least one target algorithm identifier; determine a target algorithm package corresponding to each of the target algorithm identifiers from a preset algorithm warehouse, the target algorithm package including target algorithm data and target environment data relied on by the target algorithm data, the algorithm warehouse storing a plurality of algorithm packages; construct a correspondence relationship between each target algorithm package and a target resource, and create a target running environment of the target algorithm data in the target resource according to the corresponding target environment data, to obtain a target algorithm container corresponding to each of the target algorithm packages, one target algorithm identifier corresponding to at least one target resource; determine target multimedia data corresponding to each of the target algorithm containers from at least one piece of the multimedia data based on the correspondence relationship between the multimedia data and the target algorithm identifier; and process the corresponding target multimedia data through each target algorithm container to obtain monitoring results corresponding to each target multimedia data.

[0116] In some embodiments, the target multimedia data is a target data queue; and the processing module 402, when performing the step of processing the corresponding target multimedia data through each target algorithm container to obtain monitoring results corresponding to each target multimedia data, is specifically configured to:

[0117] add queue data in the target data queue to a data cache pool;

[0118] perform a read operation on the corresponding queue data in the data cache pool in a distributed task manner in each target algorithm container, and process the read queue data to obtain monitoring results corresponding to each target multimedia data.

[0119] In some embodiments, after performing the step of processing the corresponding target multimedia data through each target algorithm container, the processing module 402 is further configured to:

[0120] monitor resource utilization of each target algorithm container;

[0121] when a first resource utilization is monitored and a duration for which the first resource utilization exists is greater than a first preset duration threshold, perform expansion processing on a first algorithm container corresponding to the first resource utilization, the first resource utilization being greater than a first preset utilization threshold.

[0122] When the second resource utilization is detected and the second resource utilization exists for a duration greater than a second preset duration threshold, a second algorithm container corresponding to the second resource utilization is scaled, and the second resource utilization is the resource utilization less than a second preset utilization threshold.

[0123] In some embodiments, the processing module 402, after performing the step of processing the corresponding target multimedia data by each target algorithm container, is further configured to:

[0124] determining a target algorithm package that currently meets a preset resource adjustment condition as a to-be-adjusted algorithm package;

[0125] receiving a resource adjustment instruction of a management user for the to-be-adjusted algorithm package;

[0126] performing scaling or scaling of a third algorithm container corresponding to the to-be-adjusted algorithm package according to the resource adjustment instruction.

[0127] In some embodiments, the processing module 402, when performing the step of constructing the corresponding relationship between each target algorithm package and target resource, is specifically configured to:

[0128] determining a plurality of idle resources in a preset computing resource pool;

[0129] determining a target resource corresponding to each target algorithm package from a plurality of idle resources according to a theoretical resource corresponding to each target algorithm package, and constructing a corresponding relationship between each target algorithm package and target resource.

[0130] In some embodiments, the processing module 402, before performing the step of determining a target resource corresponding to each target algorithm package from a plurality of idle resources according to a theoretical resource corresponding to each target algorithm package, is further configured to:

[0131] determining a theoretical resource sum of each theoretical resource;

[0132] determining whether the theoretical resource sum is greater than an idle resource sum corresponding to a plurality of idle resources;

[0133] The step of determining a target resource corresponding to each target algorithm package from a plurality of idle resources according to a theoretical resource corresponding to each target algorithm package includes:

[0134] If the theoretical resource sum is greater than the idle resource sum, determining a target priority corresponding to each target algorithm package according to a preset corresponding relationship between algorithm package and priority;

[0135] According to the target priority corresponding to each target algorithm package and the corresponding theoretical resource, a target resource corresponding to each target algorithm package is determined from the plurality of idle resources.

[0136] In some embodiments, the processing module 402, when performing the step of constructing the correspondence between each multimedia data and the target algorithm identifier, is specifically configured to:

[0137] Obtain a data type corresponding to each multimedia data;

[0138] According to the data type and the preset correspondence between the data type and the algorithm identifier, the correspondence between each multimedia data and the target algorithm identifier is constructed.

[0139] In summary, in the scheme provided by the embodiments of the present application, in a first aspect, since the multimedia data processing apparatus 400 integrates algorithm data and corresponding environment data in an algorithm package, when the corresponding algorithm data is called, the corresponding environment data is also called, and by calling the data package, the environment data suitable for running the corresponding algorithm data in the algorithm package can be deployed, so when developing an algorithm service, it is not necessary to deploy various dependent environments in the computing resource in advance, and it is not necessary to construct the correspondence between the dependent environment and the algorithm data, so by using the multimedia data processing apparatus 400 in the embodiments, the integration workload when developing an algorithm service can be reduced; in a second aspect, the multimedia data processing apparatus 400 packages the algorithm data and the environment data together, when the algorithm data and / or the environment data are updated, the multimedia data processing apparatus 400 can directly update the corresponding algorithm package, since the algorithm data and the environment data in the algorithm package are associated, the problem of the updated algorithm data depending on the old environment data can be avoided, and by the present application, the update iteration of the algorithm in the later stage can be more flexible and adaptive.

[0140] The multimedia data processing apparatus in the embodiments of the present application is described from the perspective of modular functional entities above, and the multimedia data processing apparatus in the embodiments of the present application is described from the perspective of hardware processing below.

[0141] It should be noted that all the transceiver modules in each embodiment (including Figure 4 all the transceiver modules in each embodiment) of the present application can be transceivers, and all the processing modules can be processors. When one of the apparatuses has a structure as shown in Figure 4 the processor, the transceiver and the memory realize the same or similar functions of the transceiver module and the processing module provided by the apparatus embodiment corresponding to the apparatus, Figure 5 the memory stores the computer program required by the processor to execute the above multimedia data processing method.

[0142] Figure 4 The system shown can have, for example Figure 5 The structure shown, when Figure 4 The device shown has the following characteristics: Figure 5 When the structure shown is used, Figure 5 The processor in the device can perform the same or similar functions as the processing module provided in the aforementioned device embodiments. Figure 5 The transceiver in the device can perform the same or similar functions as the transceiver module provided in the aforementioned device embodiments corresponding to this device. Figure 5 The memory stores the computer programs that the processor needs to call when executing the above-described multimedia data processing method. In the embodiments of this application... Figure 4 In the illustrated embodiment, the physical device corresponding to the transceiver module can be an input / output interface, and the physical device corresponding to the processing module can be a processor.

[0143] This application also provides a terminal, such as... Figure 6 As shown, for ease of explanation, only the parts related to the embodiments of this application are shown. For specific technical details not disclosed, please refer to the method section of the embodiments of this application. The terminal can be any terminal including mobile phones, tablets, personal digital assistants (PDAs), point-of-sale (POS) terminals, in-vehicle computers, etc. Taking a mobile phone as an example:

[0144] Figure 6 This is a block diagram illustrating a portion of the structure of a mobile phone related to the terminal provided in the embodiments of this application. (Reference) Figure 6 The mobile phone includes: a radio frequency (RF) circuit 55, a memory 520, an input unit 530, a display unit 540, a sensor 550, an audio circuit 560, a wireless fidelity (Wi-Fi) module 570, a processor 580, and a power supply 590, among other components. Those skilled in the art will understand that... Figure 6 The mobile phone structure shown does not constitute a limitation on the mobile phone and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0145] The following is combined Figure 6 A detailed introduction to each component of a mobile phone:

[0146] The RF circuit 55 can be used for receiving and sending signals in the process of information or communication, in particular, receiving the downlink information from the base station and processing by the processor 580; in addition, sending the uplink data to the base station. Generally, the RF circuit 55 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (LNA), a duplexer, etc. In addition, the RF circuit 55 can also communicate with the network and other devices through wireless communication. The above-mentioned wireless communication can use any communication standard or protocol, including but not limited to Global System of Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), etc.

[0147] The memory 520 can be used to store software programs and modules, and the processor 580 can execute various function applications and data processing of the mobile phone by running the software programs and modules stored in the memory 520. The memory 520 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 520 can include a high-speed random access memory, and can also include a non-volatile memory, for example, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state memory device.

[0148] The input unit 530 can be used to receive input digital or character information, and to generate key signal input with respect to user setting of the mobile phone and control of the function. Specifically, the input unit 530 can include a touch panel 531 and other input devices 532. The touch panel 531, also called a touch screen, can collect a touch operation (such as an operation of a user using a finger, a stylus, or any suitable object or accessory on or near the touch panel 531) of the user on or near it, and drive the corresponding connection device according to a pre-set program. Optionally, the touch panel 531 can include two parts of a touch detection device and a touch controller. Among them, the touch detection device detects the touch position of the user and detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, and converts it into touch coordinates and sends it to the processor 580, and can receive the command from the processor 580 and execute it. In addition, the touch panel 531 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 531, the input unit 530 can also include other input devices 532. Specifically, the other input devices 532 can include one or more of a physical keyboard, a function key (such as a volume control button, an on-off button, etc.), a trackball, a mouse, a joystick, etc.

[0149] The display unit 540 can be used to display information input by the user or information provided to the user and various menus of the mobile phone. The display unit 540 can include a display panel 541, which can be configured in the form of a liquid crystal display (English full name: Liquid Crystal Display, English abbreviation: LCD), an organic light-emitting diode (English full name: Organic Light-Emitting Diode, English abbreviation: OLED), etc. Further, the touch panel 531 can cover the display panel 541, and when the touch panel 531 detects a touch operation on or near it, it is transmitted to the processor 580 to determine the type of touch event, and then the processor 580 provides corresponding visual output on the display panel 541 according to the type of touch event. Although in the Figure 6 In some embodiments, the touch panel 531 and the display panel 541 can be integrated to realize the input and output functions of the mobile phone.

[0150] The mobile phone may also include at least one sensor 550, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. The ambient light sensor can adjust the brightness of the display panel 541 according to the ambient light level, and the proximity sensor can turn off the display panel 541 and / or backlight when the phone is moved to the ear. As a type of motion sensor, an accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity and can be used for applications that recognize the phone's posture (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition-related functions (such as pedometer, taps), etc. Other sensors that may be configured in the mobile phone, such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, will not be described in detail here.

[0151] Audio circuit 560, speaker 561, and microphone 562 provide an audio interface between the user and the mobile phone. Audio circuit 560 converts received audio data into electrical signals and transmits them to speaker 561, where speaker 561 converts them into sound signals for output. On the other hand, microphone 562 converts collected sound signals into electrical signals, which are received by audio circuit 560, converted into audio data, and then processed by processor 580 before being transmitted via RF circuit 55 to, for example, another mobile phone, or the audio data can be output to memory 520 for further processing.

[0152] Wi-Fi is a short-range wireless transmission technology. Through the Wi-Fi module 570, mobile phones can help users send and receive emails, browse web pages, and access streaming media, providing users with wireless broadband internet access. Although Figure 6 The Wi-Fi module 570 is shown, but it is understood that it is not a necessary component of the mobile phone and can be omitted as needed without changing the nature of the application.

[0153] The processor 580 is the control center of the mobile phone, connecting various parts of the phone through various interfaces and lines. It performs various functions and processes data by running or executing software programs and / or modules stored in the memory 520, and by calling data stored in the memory 520, thereby providing overall monitoring of the phone. Optionally, the processor 580 may include one or more processing modules; preferably, the processor 580 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into the processor 580.

[0154] The mobile phone also includes a power supply 590 (such as a battery) that supplies power to various components. The power supply can be logically connected to the processor 580 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system.

[0155] Although not shown, mobile phones may also include a camera, Bluetooth module, etc., which will not be described in detail here.

[0156] In this embodiment of the application, the processor 580 included in the mobile phone also has the function of controlling and executing the above-mentioned... Figure 2 The flowchart shown is for a multimedia data processing method.

[0157] Figure 7 This is a schematic diagram of a server structure provided in an embodiment of this application. The server 620 can vary significantly due to different configurations or performance. It may include one or more central processing units (CPUs) 622 (e.g., one or more processors) and memory 632, and one or more storage media 630 (e.g., one or more mass storage devices) for storing application programs 642 or data 644. The memory 632 and storage media 630 can be temporary or persistent storage. The program stored in the storage media 630 may include one or more modules (not shown in the diagram), each module may include a series of instruction operations on the server. Furthermore, the CPU 622 may be configured to communicate with the storage media 630 and execute the series of instruction operations in the storage media 630 on the server 620.

[0158] Server 620 may also include one or more power supplies 626, one or more wired or wireless network interfaces 650, one or more input / output interfaces 658, and / or one or more operating systems 641, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc.

[0159] The steps performed by the server in the above embodiments can be based on this Figure 7 The structure of server 620 is shown. For example, in the above embodiment, it consists of... Figure 2 The steps of the server shown can be based on this Figure 7 The server architecture is shown. For example, the processor 622 performs the following operations by calling instructions in memory 632:

[0160] acquire at least one piece of multimedia data and build a correspondence between each of the multimedia data and a target algorithm identifier, one target algorithm identifier corresponding to at least one piece of the multimedia data, and one piece of the multimedia data corresponding to at least one target algorithm identifier, the multimedia data including at least one of security-scene multimedia data, smart-city multimedia data, and industrial-scene multimedia data;

[0161] determine, from a preset algorithm warehouse, a target algorithm package corresponding to each of the target algorithm identifiers, the target algorithm package including target algorithm data and target environment data on which the target algorithm data depends, the algorithm warehouse storing a plurality of algorithm packages;

[0162] build a correspondence between each target algorithm package and a target resource, and create a target running environment of the target algorithm data in the target resource according to the corresponding target environment data, to obtain a target algorithm container corresponding to each of the target algorithm packages, one target algorithm identifier corresponding to at least one target resource;

[0163] determine, based on the correspondence between the multimedia data and the target algorithm identifiers, target multimedia data corresponding to each of the target algorithm containers from at least one piece of the multimedia data;

[0164] process, by each target algorithm container, the corresponding target multimedia data, to obtain a monitoring result corresponding to each target multimedia data.

[0165] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0166] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the system, device and module described above can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0167] In several embodiments provided in the embodiments of the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. In actual implementation, another division mode can be used. For example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed mutual elements can be indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0168] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, i.e., may be located in one place, or may be distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment.

[0169] In addition, each functional module in each embodiment of the present application can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module. The integrated module can be realized in the form of hardware or in the form of a software functional module. When the integrated module is realized in the form of a software functional module and sold or used as an independent product, it can be stored in a computer readable storage medium.

[0170] In the above embodiments, all or part can be realized by software, hardware, firmware or any combination thereof. When realized by software, all or part can be realized in the form of a computer program product.

[0171] The computer program product includes one or more computer instructions. When the computer program is loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another, for example, the computer instructions can be transferred from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that a computer can store or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be magnetic media (such as floppy disk, hard disk, magnetic tape), optical media (such as DVD), or semiconductor media (such as solid state disk (SSD)) and the like.

[0172] The technical solutions provided by the embodiments of the present application are described in detail above, and the principles and implementation manners of the embodiments of the present application are described by applying specific examples. The above description of the embodiments is only used to help understand the method and the core idea of the embodiments of the present application. Meanwhile, for those skilled in the art, the specific implementation manners and application ranges will be changed according to the ideas of the embodiments of the present application. In conclusion, the content of the specification should not be understood as a limitation of the embodiments of the present application.

Claims

1. A multimedia data processing method, characterized by, The method comprises the following steps: acquiring at least one piece of multimedia data and constructing a corresponding relationship between each piece of the multimedia data and a target algorithm identifier, one target algorithm identifier corresponding to at least one piece of the multimedia data, and one piece of the multimedia data corresponding to at least one target algorithm identifier, the multimedia data comprising at least one of security scene multimedia data, smart city multimedia data and industrial scene multimedia data; determining, from a preset algorithm warehouse, a target algorithm package corresponding to each target algorithm identifier, the target algorithm package comprising target algorithm data and target environment data relied on by the target algorithm data, the algorithm warehouse storing a plurality of algorithm packages; constructing a corresponding relationship between each target algorithm package and a target resource, and creating a target running environment of the target algorithm data in the target resource according to the corresponding target environment data, to obtain a target algorithm container corresponding to each target algorithm package, one target algorithm identifier corresponding to at least one target resource; based on the corresponding relationship between the multimedia data and the target algorithm identifier, determining, from at least one piece of the multimedia data, target multimedia data corresponding to each target algorithm container; processing, by each target algorithm container, corresponding target multimedia data to obtain monitoring results corresponding to each target multimedia data.

2. The method of claim 1, wherein, The target multimedia data is a target data queue; the processing, by each target algorithm container, of corresponding target multimedia data to obtain monitoring results corresponding to each target multimedia data comprises: adding queue data in the target data queue to a data cache pool; performing a read operation on corresponding queue data in the data cache pool in each target algorithm container in a distributed task mode, and processing the read queue data to obtain monitoring results corresponding to each target multimedia data.

3. The method according to claim 1 or 2, characterized in that, After the processing, by each target algorithm container, of corresponding target multimedia data, the method further comprises: monitoring resource utilization rates of each target algorithm container; when a first resource utilization rate is monitored and a duration of existence of the first resource utilization rate is greater than a first preset duration threshold, performing expansion processing on a first algorithm container corresponding to the first resource utilization rate, the first resource utilization rate being greater than a first preset utilization rate threshold; when a second resource utilization rate is detected and a duration of existence of the second resource utilization rate is greater than a second preset duration threshold, performing contraction processing on a second algorithm container corresponding to the second resource utilization rate, the second resource utilization rate being less than a second preset utilization rate threshold.

4. The method according to claim 1 or 2, characterized in that, After the processing, by each target algorithm container, of corresponding target multimedia data, the method further comprises: determining a target algorithm package that meets a preset resource adjustment condition as a to-be-adjusted algorithm package; receiving a resource adjustment instruction of a management user for the to-be-adjusted algorithm package; performing expansion processing or contraction processing on a third algorithm container corresponding to the to-be-adjusted algorithm package according to the resource adjustment instruction.

5. The method according to claim 1 or 2, characterized in that, The constructing of the corresponding relationship between each target algorithm package and a target resource comprises: Determine a plurality of idle resources in a preset computing resource pool; According to the theoretical resources corresponding to each target algorithm package, determine the target resources corresponding to each target algorithm package from the plurality of idle resources, and construct the correspondence between each target algorithm package and target resource.

6. The method of claim 5, wherein, Before the step of determining the target resources corresponding to each target algorithm package from the plurality of idle resources according to the theoretical resources corresponding to each target algorithm package, the method further comprises: Determine the theoretical resource sum of each theoretical resource; Determine whether the theoretical resource sum is greater than the idle resource sum corresponding to the plurality of idle resources; The step of determining the target resources corresponding to each target algorithm package from the plurality of idle resources according to the theoretical resources corresponding to each target algorithm package comprises: If the theoretical resource sum is greater than the idle resource sum, determine the target priority corresponding to each target algorithm package according to the preset correspondence between algorithm package and priority; Determine the target resources corresponding to each target algorithm package from the plurality of idle resources according to the target priority corresponding to each target algorithm package and the corresponding theoretical resources.

7. The method according to claim 1 or 2, characterized in that, The step of constructing the correspondence between each multimedia data and target algorithm identifier comprises: Obtain the data type corresponding to each multimedia data; According to the data type and the preset correspondence between data type and algorithm identifier, construct the correspondence between each multimedia data and target algorithm identifier.

8. A multimedia data processing apparatus, characterized by comprising: Comprise: The transceiver module is used for obtaining at least one multimedia data, and the multimedia data comprises at least one of security scene multimedia data, smart city multimedia data and industrial scene multimedia data; The processing module is used for constructing the correspondence between each multimedia data and target algorithm identifier, one target algorithm identifier corresponds to at least one multimedia data, and one multimedia data corresponds to at least one target algorithm identifier; determining the target algorithm package corresponding to each target algorithm identifier from a preset algorithm warehouse, the target algorithm package comprises target algorithm data and target environment data relied on by the target algorithm data, and the algorithm warehouse stores a plurality of algorithm packages; constructing the correspondence between each target algorithm package and target resource, and creating a target running environment of the target algorithm data in the target resource according to the corresponding target environment data, to obtain the target algorithm container corresponding to each target algorithm package, one target algorithm identifier corresponds to at least one target resource; According to the correspondence between the multimedia data and the target algorithm identifier, determine the target multimedia data corresponding to each target algorithm container from at least one multimedia data; process the corresponding target multimedia data through each target algorithm container to obtain the monitoring result corresponding to each target multimedia data.

9. A computer device, comprising: The computer device comprises a memory and a processor, the memory stores a computer program, and the processor executes the computer program to realize the method in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, and the computer program includes program instructions. The program instructions, when executed by a processor, can implement the method in any one of claims 1-7.

Images