WO2022135167A1 - Cloud service method and apparatus, device and storage medium - Google Patents

Abstract

Disclosed are a cloud service method and apparatus, a device and a storage medium. The method comprises: obtaining a service request of at least one tenant, wherein each tenant corresponds to a namespace, each namespace corresponds to at least one AI cloud service provided by an AI cloud platform system, and each AI cloud service is realized by at least one subsystem; and in response to a target cloud service requested by the tenant belonging to the namespace of the tenant, using a target subsystem corresponding to the target cloud service to provide a service.

Description

Cloud service method, device, device and storage medium

CROSS-REFERENCE TO RELATED APPLICATIONS

This disclosure claims the priority of the Chinese patent application filed on December 21, 2020 with the application number of 202011519718.3 and the invention titled "Cloud Service Method, Apparatus, Equipment and Storage Medium", the entire contents of which are disclosed in the Chinese patent application Incorporated herein by reference.

technical field

The present disclosure relates to the field of computer technologies, and in particular, to a cloud service method, apparatus, device, and storage medium.

Background technique

With the rapid development of cloud computing technology, the application of cloud platforms is becoming more and more extensive. Existing cloud platforms usually implement a multi-tenant system by virtualizing physical resources to support different tenants using computing services independently in the cloud. However, this approach has the problems of heavy resource usage and high management usage overhead.

SUMMARY OF THE INVENTION

The present disclosure provides a cloud service solution.

According to an aspect of the present disclosure, a cloud service method is proposed, which is applied to an artificial intelligence AI cloud platform system, the AI cloud platform system includes a plurality of subsystems; the method includes: obtaining a service request of at least one tenant, wherein each Each of the tenants corresponds to one namespace, each of the namespaces corresponds to at least one AI cloud service provided by the AI cloud platform system, and each of the AI cloud services is implemented by at least one of the subsystems; In response to the target cloud service requested by the tenant belonging to the namespace of the tenant, a service is provided using a target subsystem corresponding to the target cloud service.

With reference to any of the implementation manners provided in the present disclosure, the providing a service by using a target subsystem corresponding to the target cloud service includes: acquiring data to be processed for the target cloud service; The data to be processed is processed; the data processed by the target subsystem is transmitted and/or stored under the namespace of the tenant.

With reference to any implementation manner provided by the present disclosure, the transmitting and/or storing the data processed by the target subsystem in the namespace of the tenant includes at least one of the following manners: making the data processed by the target subsystem data, carry the tenant's namespace identifier for transmission and/or storage; make the data processed by the target subsystem be transmitted in the channel corresponding to the tenant's namespace, and/or in the tenant It is stored in the storage space corresponding to the namespace.

With reference to any of the embodiments provided in the present disclosure, the method further includes: receiving tenant information, where the tenant information is used to indicate the rights of the tenant to at least one cloud service provided by the AI cloud platform system; The tenant information is used to create a namespace corresponding to the tenant, and/or a corresponding relationship between the namespace and the subsystem is established.

With reference to any of the embodiments provided in the present disclosure, each of the subsystems has namespace resource information; the establishing a corresponding relationship between the namespace and the subsystem according to the tenant information includes: naming the tenants The space identifier is mapped to the namespace resource information of the subsystem to which the tenant has permission.

With reference to any of the embodiments provided in the present disclosure, the method further includes: mapping the service request of the at least one tenant to a namespace request, where the namespace request is used to indicate the namespace of the tenant and the The requested target cloud service; the providing a service by using the target subsystem corresponding to the target cloud service includes: determining the target subsystem corresponding to the target cloud service according to the namespace request.

With reference to any implementation manner provided in the present disclosure, the AI cloud platform system at least includes at least one interface gateway, and the interface gateway is configured to obtain the namespace request of the at least one tenant, and invoke the The target subsystem provides the service.

According to an aspect of the present disclosure, a cloud service device is proposed, which is applied to an artificial intelligence AI cloud platform system, the AI cloud platform system includes a plurality of subsystems; the device includes: an acquisition unit for acquiring services of at least one tenant request, wherein each of the tenants corresponds to a namespace, each of the namespaces corresponds to at least one AI cloud service provided by the AI cloud platform system, and each of the AI cloud services is provided by at least one The subsystem is implemented; the service unit is configured to provide a service by using the target subsystem corresponding to the target cloud service in response to the target cloud service requested by the tenant belonging to the namespace of the tenant.

With reference to any of the implementation manners provided in the present disclosure, the service unit is configured to: acquire data to be processed for the target cloud service; process the data to be processed by using the target subsystem; Data processed by the target subsystem is transmitted and/or stored in space.

With reference to any of the embodiments provided in the present disclosure, when the service unit transmits and/or stores data processed by the target subsystem under the namespace for the tenant, the service unit is configured to: enable the target subsystem to The processed data is transmitted and/or stored with the namespace identifier corresponding to the tenant; the data processed by the target subsystem is transmitted in the channel corresponding to the tenant, and/or in the It is stored in the storage space corresponding to the tenant's namespace.

With reference to any of the embodiments provided in the present disclosure, the apparatus further includes a establishing unit configured to receive tenant information, where the tenant information is used to indicate the tenant's information about at least one cloud service provided by the AI cloud platform system. permission; create a namespace corresponding to the tenant according to the tenant information, and/or establish a corresponding relationship between the namespace and the subsystem.

With reference to any of the implementation manners provided in the present disclosure, each of the subsystems has namespace resource information; when the establishment unit is used to establish the corresponding relationship between the namespace and the subsystem according to the tenant information, for : Map the namespace identifier of the tenant to the namespace resource information of the subsystem to which the tenant has permission.

With reference to any of the embodiments provided in the present disclosure, the apparatus further includes a determining unit configured to map the service request of the at least one tenant into a namespace request, where the namespace request is used to indicate the namespace of the tenant and The target cloud service requested by the tenant; when the service unit provides services by using the target subsystem corresponding to the target cloud service, the service unit is configured to: determine the target corresponding to the target cloud service according to the namespace request subsystem.

With reference to any implementation manner provided in the present disclosure, the AI cloud platform system at least includes at least one interface gateway, and the interface gateway is configured to obtain the namespace request of the at least one tenant, and invoke the The target subsystem provides the service.

According to an aspect of the present disclosure, there is provided an electronic device comprising a memory and a processor, the memory for storing computer instructions executable on the processor, the processor for executing the computer instructions to implement the present invention The cloud service method of any embodiment provided by the disclosure.

According to an aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, implements the cloud service method of any embodiment provided by the present disclosure.

In the embodiments of the present disclosure, the AI cloud platform system to which the cloud service method is applied includes multiple subsystems, the AI cloud platform system can provide multiple cloud services, each cloud service is implemented by at least one subsystem, and obtains at least one cloud service. A service request of a tenant, since each tenant corresponds to a namespace, and each namespace corresponds to at least one AI cloud service provided by the AI cloud platform system, the target cloud service requested by the tenant belongs to The namespace of the tenant, using the target subsystem corresponding to the target cloud service to provide services, can realize the multi-tenant design of the AI cloud service system and the lightweight virtualization of the computing service layer; The sub-services that can be realized by the system are recombined and arranged, and other cloud services can be customized on top of the existing algorithms and service functions provided by the AI cloud platform system, so that the provided AI cloud services have higher flexibility. .

Description of drawings

In order to illustrate one or more embodiments of the present disclosure or related technologies more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments or related technologies. Obviously, the accompanying drawings in the following description are only For some embodiments described in one or more embodiments of the present disclosure, for those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative effort.

FIG. 1 is a flowchart of a cloud service method provided by at least one embodiment of the present disclosure.

FIG. 2 is an architectural diagram of a cloud platform system provided by at least one embodiment of the present disclosure.

FIG. 3 is a schematic structural diagram of a cloud service apparatus according to at least one embodiment of the present disclosure.

FIG. 4 is a schematic structural diagram of an electronic device according to at least one embodiment of the present disclosure.

Detailed ways

In order for those skilled in the art to better understand one or more embodiments of the present disclosure, one or more embodiments of the present disclosure will be described below with reference to the accompanying drawings in the one or more embodiments of the present disclosure, Obviously, the described embodiments are only some, but not all, embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on one or more embodiments of the present disclosure without creative efforts shall fall within the protection scope of the present disclosure.

FIG. 1 is a flowchart of a cloud service method provided by at least one embodiment of the present disclosure. The method is applied to an artificial intelligence (Artificial Intelligence, AI) cloud platform system, and the AI cloud platform system includes a plurality of subsystems. As shown in FIG. 1 , the cloud service method provided by at least one embodiment of the present disclosure may include steps 101 to 102 .

In step 101, a service request of at least one tenant is obtained.

In the embodiments of the present disclosure, the AI cloud platform system to which the cloud service method is applied is used to provide an AI cloud service to tenants in a cloud computing manner, and the AI cloud service includes but is not limited to at least one of the following service items: Inflow library, video stream creation, portrait parsing, structured parsing, video stream parsing, audio stream parsing, portrait library creation, etc., wherein the portrait parsing includes but is not limited to operations such as face recognition, and structured parsing includes but is not limited to The operation of classifying and analyzing other objects before the face, such as vehicles, human body parts, animals, plants, buildings, etc.

The AI cloud platform system may include a plurality of subsystems, each of which is used to execute at least one sub-service, such as a data access service, a data storage service, a data processing service, and the like. Each of the multiple AI services provided by the AI cloud platform system is realized by at least one subsystem, that is, through the cooperation between the various subsystems, including the transmission of data, parameters, and instructions, one can be jointly realized. or multiple AI services. For example, the video stream face parsing service can be jointly implemented by a data access subsystem, a video stream face parsing subsystem, and a data storage subsystem.

In the embodiment of the present disclosure, each tenant corresponds to one namespace, and each namespace corresponds to at least one AI cloud service provided by the AI cloud platform system. That is to say, each tenant is mapped to a namespace of the AI cloud platform system, and according to the authority of the AI cloud service owned by the tenant, that is, the AI cloud service purchased by the tenant, the naming is established. The correspondence between space and AI cloud services.

In step 102, in response to the target cloud service requested by the tenant belonging to the namespace of the tenant, a target subsystem corresponding to the target cloud service is used to provide a service.

The acquired service request of the tenant includes the target cloud service requested by the tenant, and the target cloud service may be a request for an AI cloud service provided by an AI cloud platform system, such as video streaming face parsing. Service requests, audio stream Chinese parsing service requests, etc.

Since each AI cloud service in the AI cloud platform system is implemented by at least one subsystem, for the target cloud service requested by the tenant, the target subsystem that executes the target cloud service can be invoked.

When the target cloud service requested by the tenant belongs to the namespace of the tenant, that is, the tenant has the authority of the AI cloud service, the target subsystem corresponding to the target cloud service is used to provide the service.

For example, if the tenant's service request is for requesting a video stream parsing service, if the tenant's namespace includes the video stream parsing service, the service that executes the video stream parsing service may be called. The data access subsystem, the video stream face parsing subsystem, and the data storage subsystem jointly provide services.

In the embodiments of the present disclosure, the AI cloud platform system to which the cloud service method is applied includes multiple subsystems, the AI cloud platform system can provide multiple cloud services, each cloud service is implemented by at least one subsystem, and obtains at least one cloud service. A service request of a tenant, since each tenant corresponds to a namespace, and each namespace corresponds to at least one AI cloud service provided by the AI cloud platform system, the target cloud service requested by the tenant belongs to The namespace of the tenant, using the target subsystem corresponding to the target cloud service to provide services, can realize the multi-tenant design of the AI cloud service system and the lightweight virtualization of the computing service layer; The sub-services that can be realized by the system are recombined and arranged, and other cloud services can be customized on top of the existing algorithms and service functions provided by the AI cloud platform system, so that the provided AI cloud services have higher flexibility. .

In some embodiments, the service can be provided by the target subsystem corresponding to the target cloud service by the following method.

First, the data to be processed for the target cloud service is acquired. The data to be processed may be data uploaded by the tenant for the requested target cloud service, or sensor data or data from other data sources acquired by the AI cloud platform system for the target cloud service, etc. The implementation of the present disclosure For example, there is no restriction on the source of the data to be processed. Next, the data to be processed is processed by the target subsystem, and the data processed by the target subsystem is transmitted and/or stored in the namespace corresponding to the tenant who issued the service request.

In one example, the data generated by the target subsystem when executing the target cloud service can be transmitted and/or stored with the namespace identifier corresponding to the tenant who issued the service request, then for the For the data transmitted or stored in the AI cloud platform system, the namespace to which the data belongs can be determined, thereby realizing data isolation among multiple tenants, wherein the namespace identifier is obtained by mapping the tenant name. Specifically, the AI processing logic corresponding to the namespace, as well as the data, machine learning model, feature data, configuration data, etc. generated during the processing, carry the namespace identifier for transmission and/or storage, thereby realizing AI Lightweight virtualization of cloud platforms, as well as service isolation and data isolation at the AI service level.

In one example, the data generated by the target subsystem may be transmitted in a channel corresponding to the namespace of the tenant who issued the service request, and/or corresponding to the namespace of the tenant who issued the service request. In other words, data belonging to different namespaces are transmitted through different channels and stored in different storage areas, so as to realize the transmission and/or storage of data in the manner of namespace isolation, so as to achieve different Isolation of namespace data. The subsystem can make the transmitted and/or stored data carry the namespace identifier, and also transmit the data of different namespaces through different channels, and store the data of different namespaces in different areas, so as to realize the data of different namespaces. isolation.

In the embodiment of the present disclosure, the target subsystem supporting the namespace parses and processes the data to be processed, and performs operations such as isolation and scheduling of the processed data according to the namespace. Tenants only need to purchase the required services, and the AI cloud platform system can configure the calling rights of the corresponding subsystems for the namespaces to which the tenants belong, so that the requested target cloud services can be realized without purchasing independent resources, reducing physical resources. investment on.

In the embodiment of the present disclosure, one tenant may include multiple users, that is, the users included in the tenant may request AI cloud services through the namespace corresponding to the tenant; at the same time, the same user may also be included in multiple tenants middle.

In some embodiments, the cloud service method further includes: receiving tenant information, where the tenant information is used to indicate the rights of the tenant to at least one cloud service provided by the AI cloud platform system; creating a cloud service based on the tenant information A namespace corresponding to the tenant, and/or establishing a corresponding relationship between the namespace and the subsystem. That is to say, in the AI cloud service method, a namespace can be created according to tenant information, and one or more AI algorithm functions can be licensed for the namespace according to the tenant's authority to the cloud service, so that the naming The space obtains the use authority of the subsystem corresponding to the AI algorithm function.

Wherein, the tenant information usually includes the basic information of the tenant, such as the tenant's name registered in the AI cloud platform system, tenant attributes, etc., and may also include the permission information of the tenant, the permission information indicates that the tenant has The permission of at least one cloud service provided by the AI cloud platform system, that is, the service item purchased by the tenant.

In some embodiments, the AI cloud platform system further includes a namespace control module for managing the namespace corresponding to the tenant. The namespace control module may be an independent module in the AI cloud platform system, or may be a module in the subsystem. The basic information in the information creates a namespace corresponding to the tenant, and establishes the corresponding relationship between the namespace and the subsystem according to the permission information in the tenant information, that is, assigns the namespace to the use of the subsystem permissions.

Specifically, the namespace identifier corresponding to the tenant can be mapped to the namespace resource and logic of the subsystem to which the tenant has permission, that is, when the target subsystem executes the target cloud service The generated data is transmitted and/or stored in the namespace indicated by the namespace identifier.

In some embodiments, for the namespace corresponding to the existing tenant, the corresponding relationship between the namespace and the subsystem can also be established according to the permission information in the tenant information; it can also be based on the change of the permission information in the tenant information. , to change the corresponding relationship between the namespace and the subsystem (sub-service), that is, to change the sub-service arrangement under the namespace.

The namespace control module may also be used for at least one of the following:

read, update and delete the namespace;

Control the life cycle of data under the namespace;

Authentication and certification of namespace identification;

Tenant management, tenant organizational structure management.

In some embodiments, the namespace identifier may be used to indicate the namespace corresponding to the tenant making the service request. The namespace identifier is unique to the service request, and is used to represent the unique tenant who makes the service request.

In some embodiments, the service request of the at least one tenant may be mapped to a namespace request, where the namespace request is used to indicate the namespace corresponding to the tenant and the target cloud service requested by the tenant; By describing the namespace request, the target subsystem corresponding to the target cloud service can be determined.

In some embodiments, the namespace request includes a namespace identifier corresponding to the tenant, and according to the namespace identifier, it is possible to determine the subsystem that the requesting tenant has the right to use; The target cloud service included, that is, by implementing the processing logic of the service, it is possible to determine the sub-services to be invoked, that is, to determine the sub-systems to be invoked for executing the sub-services, so that the sub-services to be invoked can be determined. The target subsystem that the namespace request needs to call and can call.

In one example, a tenant's service request may be mapped to a namespace request through an AI service virtualization operating system (Operating System, OS).

The AI service virtualization operating system proposed by the embodiments of the present disclosure belongs to the scheduling and management system of virtual resources. Compared with the general virtualized operating system, the system does not monitor and schedule the CPU and memory, but the AI The virtualized resources such as AI computing power/data provided by the cloud platform system are monitored and scheduled.

In the embodiment of the present disclosure, the minimum function scheduling unit of the AI cloud platform system is the smallest unit that provides algorithms and functions under a namespace. For example, the video stream parsing service may be the smallest scheduling unit under the namespace, that is to say, the video stream parsing service cannot be divided into more specific services to be executed.

For example, in the case where the namespace identifier "42514" is included in the namespace request of the tenant, the namespace corresponding to the tenant can be determined according to the namespace identifier, and the subsystem corresponding to the namespace can also be determined. That is, the tenant has the right to use the subsystem. Next, determine the processing logic according to the target cloud service included in the namespace request, such as a video stream face analysis service request, for example, determine that the video stream face analysis service can be accessed through data access, video stream face analysis , data storage and other sub-services are completed together, so that it can be determined that the subsystems to be called to execute the target request include a data access subsystem, a video stream face parsing subsystem, and a data storage subsystem. In the case where the subsystem corresponding to the namespace "42514" includes the above-mentioned subsystem, the above-mentioned subsystem can be determined as the target subsystem, and the target subsystem can be called to obtain the data obtained from the data access subsystem. data to perform video streaming face parsing service.

In an embodiment of the present disclosure, the AI cloud platform system at least includes at least one interface gateway, and the interface gateway is configured to obtain a namespace request of the at least one tenant, and call the target sub-system according to the namespace request The system provides services.

In some embodiments, the interface gateway may include an application programming interface (Application Programming Interface, API) for the AI cloud platform system to provide services to the outside, that is, the exit of the AI cloud platform system.

In some embodiments, the interface device may include separate APIs for each subsystem. The format of the API may include, but is not limited to, one or more of the following formats: RESTFUL, CLI, XML, JSON, TCP/UDP, HTTP/HTTPS, and the like. Each subsystem interacts and implements calls through APIs to jointly implement service functions. The interaction between the various subsystems supports various forms, such as HTTP, protocol buffer data serialization protocol, TCP/UDP and so on. The namespace can also be implemented in the API of the subsystems, so the interaction between the subsystems also supports the namespace mechanism. After the namespace identifier enters the AI cloud platform system from the AI cloud platform system and the external API, it runs through the entire API process and the entire life cycle of the data. For example, the data transmitted between the various subsystems always carries the namespace identifier, and the processing of the data after entering the subsystem also carries the namespace identifier.

In an embodiment of the present disclosure, the namespace may be a mechanism implemented in the API, for example, by adding a namespace field or structure and any other data structure representing the namespace in the API. Taking an API in HTTP format as an example, the namespace identifier may be an integer field in an HTTP message header (header), such as "42514" in "AI_namespace: 42514".

FIG. 2 is an architectural diagram of an AI cloud platform system provided by at least one embodiment of the present disclosure. For the sake of simplicity, those skilled in the art should understand that some of the subsystems in the AI cloud platform system shown in FIG. 2 are only examples, and the AI cloud platform system may also include other subsystems.

As shown in Figure 2, the service request sent by Tenant 1 to the AI cloud platform system is used to request the target cloud service among the multiple AI cloud services provided by the AI cloud platform system: video streaming face analysis service, and send the request to the AI cloud platform system. The AI cloud platform system uploads data to be processed, and the data to be processed can come from data sources or data from sensors.

The service request of tenant 1 is mapped to a namespace request by the AI service virtualization OS 201, and the namespace request includes the namespace identifier obtained by mapping the tenant name and the target cloud service requested by tenant 1. The namespace is created by the namespace control module 203, in this example the namespace identifier of tenant 1 is "ns-1". The namespace indicated by the namespace identifier is read by the namespace control module 203 in the AI cloud platform system.

FIG. 2 shows the subsystems 204 to 209 to which Tenant 1 has usage rights, wherein each subsystem, when receiving an instruction or data containing a namespace identifier of “ns-1”, has a namespace identifier of “ns-1”. 1" corresponding to the namespace to transmit and/or store data, realize the lightweight virtualization of the AI cloud platform, as well as service isolation and data isolation at the AI service level.

FIG. 3 is a schematic structural diagram of a cloud service device provided by at least one embodiment of the present disclosure, as shown in FIG. 3, applied to an artificial intelligence AI cloud platform system, the AI cloud platform system includes a plurality of subsystems; the device Including: an obtaining unit 301, configured to obtain a service request of at least one tenant, wherein each of the tenants corresponds to a namespace, and each of the namespaces corresponds to at least one item of AI cloud provided by the AI cloud platform system service, each AI cloud service is implemented by at least one of the subsystems; the service unit 302 is configured to respond to the target cloud service requested by the tenant belonging to the namespace of the tenant, and use the target cloud service corresponding to the target cloud service. The target subsystem provides services.

In some embodiments, the service unit is configured to: obtain data to be processed for the target cloud service; process the data to be processed by using the target subsystem; transmit and and/or store data processed by the target subsystem.

In some embodiments, when the service unit transmits and/or stores the data processed by the target subsystem under the namespace for the tenant, the service unit is configured to: make the data processed by the target subsystem, Carrying the namespace identifier corresponding to the tenant for transmission and/or storage; enabling the data processed by the target subsystem to be transmitted in the channel corresponding to the tenant, and/or in the tenant's namespace stored in the corresponding storage space.

In some embodiments, the apparatus further includes an establishment unit configured to receive tenant information, where the tenant information is used to indicate the rights of the tenant to at least one cloud service provided by the AI cloud platform system; The tenant information is used to create a namespace corresponding to the tenant, and/or a corresponding relationship between the namespace and the subsystem is established.

In some embodiments, each of the subsystems has namespace resource information; when the establishment unit is configured to establish a corresponding relationship between a namespace and the subsystem according to the tenant information, the establishment unit is configured to: The namespace identifier of the tenant is mapped to the namespace resource information of the subsystem to which the tenant has permission.

In some embodiments, the apparatus further includes a determining unit for mapping the service request of the at least one tenant to a namespace request, where the namespace request is used to indicate the namespace of the tenant and the The requested target cloud service; when the service unit provides services by using the target subsystem corresponding to the target cloud service, the service unit is configured to: determine the target subsystem corresponding to the target cloud service according to the namespace request.

In some embodiments, the AI cloud platform system at least includes at least one interface gateway, and the interface gateway is configured to obtain a namespace request of the at least one tenant, and call the target subsystem to provide the Serve.

FIG. 4 provides an electronic device according to at least one embodiment of the present disclosure, including a memory and a processor, the memory for storing computer instructions executable on the processor, and the processor for executing the computer instructions to The cloud service method described in any embodiment of the present disclosure is implemented.

At least one embodiment of the present disclosure further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the cloud service method described in any embodiment of the present disclosure.

As will be appreciated by one skilled in the art, one or more embodiments of the present disclosure may be provided as a method, system or computer program product. Accordingly, one or more embodiments of the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of the present disclosure may employ a computer implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein The form of the program product.

The various embodiments in the present disclosure are described in a progressive manner, and the same and similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the data processing device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for related parts, please refer to the partial description of the method embodiment.

The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the acts or steps recited in the claims can be performed in an order different from that in the embodiments and still achieve desirable results. Additionally, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Embodiments of the subject matter and functional operations described in this disclosure can be implemented in digital electronic circuitry, in tangible embodied computer software or firmware, in computer hardware including the structures disclosed in this disclosure and their structural equivalents, or in a combination of one or more. Embodiments of the subject matter described in this disclosure may be implemented as one or more computer programs, ie, one or more of computer program instructions encoded on a tangible, non-transitory program carrier for execution by, or to control the operation of, data processing apparatus. multiple modules. Alternatively or additionally, the program instructions may be encoded on an artificially generated propagated signal, such as a machine-generated electrical, optical or electromagnetic signal, which is generated to encode and transmit information to a suitable receiver device for interpretation by the data. The processing device executes. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of these.

The processes and logic flows described in this disclosure can be performed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, eg, an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit).

Computers suitable for the execution of a computer program include, for example, general and/or special purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit will receive instructions and data from read only memory and/or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include, or be operatively coupled to, one or more mass storage devices for storing data, such as magnetic, magneto-optical or optical disks, to receive data therefrom or to It transmits data, or both. However, the computer does not have to have such a device. Additionally, the computer may be embedded in another device, such as a mobile phone, personal digital assistant (PDA), mobile audio or video player, game console, global positioning system (GPS) receiver, or a universal serial bus (USB) ) flash drives for portable storage devices, to name a few.

Computer-readable media suitable for storage of computer program instructions and data include all forms of non-volatile memory, media, and memory devices including, for example, semiconductor memory devices (eg, EPROM, EEPROM, and flash memory devices), magnetic disks (eg, internal hard disks or memory devices). removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. The processor and memory may be supplemented by or incorporated in special purpose logic circuitry.

While this disclosure contains many specific implementation details, these should not be construed as limiting the scope of any invention or what may be claimed, but rather are used primarily to describe features of specific embodiments of particular inventions. Certain features that are described in this disclosure in multiple embodiments can also be implemented in combination in a single embodiment. On the other hand, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination. Furthermore, although features may function as described above in certain combinations and even be originally claimed as such, one or more features from a claimed combination may in some cases be removed from the combination and the claimed A protected combination may point to a subcombination or a variation of a subcombination.

Similarly, although operations are depicted in the figures in a particular order, this should not be construed as requiring the operations to be performed in the particular order shown or sequentially, or that all illustrated operations be performed, to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of the various system modules and components in the above-described embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems may generally be integrated together in a single software product , or packaged into multiple software products.

Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. Furthermore, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some implementations, multitasking and parallel processing may be advantageous.

The above descriptions are only preferred embodiments of one or more embodiments of the present disclosure, and are not intended to limit one or more embodiments of the present disclosure. Any modifications, equivalent replacements, improvements, etc. made within the scope of the present disclosure should be included within the protection scope of one or more embodiments of the present disclosure.

Claims (16)

1. A cloud service method is applied to an artificial intelligence AI cloud platform system, wherein the AI cloud platform system includes a plurality of subsystems; the method includes:

   Acquire a service request of at least one tenant, where each tenant corresponds to a namespace, each namespace corresponds to at least one AI cloud service provided by the AI cloud platform system, and each of the AI The cloud service is implemented by at least one of said subsystems;

   In response to the target cloud service requested by the tenant belonging to the namespace of the tenant, a service is provided using a target subsystem corresponding to the target cloud service.
2. The method according to claim 1, wherein the providing a service by using a target subsystem corresponding to the target cloud service comprises:

   obtaining data to be processed for the target cloud service;

   Use the target subsystem to process the data to be processed;

   Data processed by the target subsystem is transmitted and/or stored under the tenant's namespace.
3. The method according to claim 2, wherein the transmitting and/or storing the data processed by the target subsystem in the namespace of the tenant includes at least one of the following ways:

   causing the data processed by the target subsystem to carry the tenant's namespace identifier for transmission and/or storage;

   The data processed by the target subsystem is transmitted in the channel corresponding to the namespace of the tenant, and/or stored in the storage space corresponding to the namespace of the tenant.
4. The method according to any one of claims 1 to 3, further comprising:

   receiving tenant information, where the tenant information is used to indicate the rights of the tenant to at least one cloud service provided by the AI cloud platform system;

   Create a namespace corresponding to the tenant according to the tenant information, and/or establish a corresponding relationship between the namespace and the subsystem.
5. The method according to claim 4, wherein each of the subsystems has namespace resource information; and the establishing the corresponding relationship between the namespace and the subsystem according to the tenant information includes:

   The namespace identifier of the tenant is mapped to the namespace resource information of the subsystem to which the tenant has permission.
6. The method according to any one of claims 1 to 5, further comprising:

   mapping the service request of the at least one tenant to a namespace request, where the namespace request is used to indicate the tenant's namespace and the target cloud service requested by the tenant;

   The using the target subsystem corresponding to the target cloud service to provide services includes:

   Determine the target subsystem corresponding to the target cloud service according to the namespace request.
7. The method according to claim 6, wherein the AI cloud platform system at least comprises at least one interface gateway, and the interface gateway is configured to obtain the namespace request of the at least one tenant, and invoke the The target subsystem provides services.
8. A cloud service device is applied to an artificial intelligence AI cloud platform system, the AI cloud platform system includes a plurality of subsystems; the device includes:

   The obtaining unit is configured to obtain a service request of at least one tenant, wherein each of the tenants corresponds to a namespace, each of the namespaces corresponds to at least one AI cloud service provided by the AI cloud platform system, and each one of the AI cloud services is implemented by at least one of the subsystems;

   A service unit, configured to provide a service by using a target subsystem corresponding to the target cloud service in response to the target cloud service requested by the tenant belonging to the namespace of the tenant.
9. The apparatus of claim 8, wherein the service unit is used to:

   obtaining data to be processed for the target cloud service;

   Use the target subsystem to process the data to be processed;

   Data processed by the target subsystem is transmitted and/or stored under the tenant's namespace.
10. The apparatus according to claim 9, wherein, when the service unit transmits and/or stores the data processed by the target subsystem under the namespace for the tenant, for:

    causing the data processed by the target subsystem to carry the tenant's namespace identifier for transmission and/or storage;

    The data processed by the target subsystem is transmitted in the channel corresponding to the namespace of the tenant, and/or stored in the storage space corresponding to the namespace of the tenant.
11. The apparatus according to any one of claims 8 to 10, further comprising a establishing unit for:

    receiving tenant information, where the tenant information is used to indicate the rights of the tenant to at least one cloud service provided by the AI cloud platform system;

    Create a namespace corresponding to the tenant according to the tenant information, and/or establish a corresponding relationship between the namespace and the subsystem.
12. The apparatus according to claim 11, wherein each of the subsystems has namespace resource information; when the establishment unit is used to establish the corresponding relationship between the namespace and the subsystem according to the tenant information , for:

    The namespace identifier of the tenant is mapped to the namespace resource information of the subsystem to which the tenant has permission.
13. The apparatus of any one of claims 8 to 12, further comprising:

    a determining unit, configured to map the service request of the at least one tenant into a namespace request, where the namespace request is used to indicate the namespace of the tenant and the target cloud service requested by the tenant;

    When the service unit provides the service by using the target subsystem corresponding to the target cloud service, it is used for:

    According to the namespace request, the target subsystem corresponding to the target cloud service is determined.
14. The apparatus according to claim 13, wherein the AI cloud platform system at least comprises at least one interface gateway, and the interface gateway is configured to obtain the namespace request of the at least one tenant, and invoke the The target subsystem provides services.
15. An electronic device, comprising a memory and a processor, the memory for storing computer instructions executable on the processor, the processor for executing the computer instructions to implement any one of claims 1 to 7. method described.
16. A computer-readable storage medium on which a computer program is stored, which implements the method of any one of claims 1 to 7 when the program is executed by a processor.

Images