Service providing method, configuration method, service access system, device, storage medium and program product

Abstract

The embodiment of the invention provides a service providing method, a configuration method, a service access system, equipment, a storage medium and a program product, and is suitable for the field of artificial intelligence services, the service providing method is applied to a server side, and the server side is connected with service providing systems corresponding to a plurality of artificial intelligence services. The server determines a target artificial intelligence service selected from the multiple artificial intelligence services; based on configuration parameters provided for the target artificial intelligence service, generating at least one task and determining material content of the at least one task; sending at least one processing request to a target service providing system providing the target artificial intelligence service based on the at least one task and the configuration parameters; the processing request is used for triggering execution of the corresponding task to process the corresponding material content to obtain a processing result; and obtaining a processing result of the at least one task from the target service providing system. According to the scheme of the embodiment of the invention, the use convenience and efficiency of the artificial intelligence service are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of artificial intelligence services, and in particular to a service providing method, a configuration method, a service access system, a device, a storage medium, and a program product. Background Art

[0002] With the development of artificial intelligence (AI) technology, people can use some AI tools to obtain corresponding AI services, such as content generation, natural language processing, machine learning model training, etc.

[0003] How to use AI services portably and efficiently has become a technical problem that technicians in this field need to solve. Summary of the invention

[0004] The embodiments of the present application provide a service provision method, a configuration method, a service access system, a device, a storage medium, and a program product for realizing portable and efficient use of artificial intelligence services.

[0005] In a first aspect, an embodiment of the present application provides a service provision method, which is applied to a server, wherein the server is connected to a service provision system corresponding to a plurality of artificial intelligence services, and the method includes:

[0006] determining a target artificial intelligence service selected from the plurality of artificial intelligence services;

[0007] Based on the configuration parameters provided for the target artificial intelligence service, generate at least one task and determine the material content of the at least one task;

[0008] Based on the at least one task and the configuration parameters, at least one processing request is sent to a target service providing system that provides the target artificial intelligence service; the processing request is used to trigger the execution of a corresponding task to process corresponding material content and obtain a processing result;

[0009] A processing result of the at least one task is acquired from the target service providing system.

[0010] In a second aspect, an embodiment of the present application provides a configuration method, which is applied to a client, wherein the client provides a user interface, and the method includes:

[0011] Displaying selection prompt information of multiple artificial intelligence services in the user interface;

[0012] In response to the service selection operation, a target artificial intelligence service is determined and a service selection request is sent to a server based on the target artificial intelligence service; wherein the server is connected to service provision systems corresponding to the plurality of artificial intelligence services respectively;

[0013] Displaying configuration prompt information corresponding to the target artificial intelligence service on the user interface;

[0014] In response to the configuration operation, determining configuration parameters;

[0015] The configuration parameters are sent to the server so that the server generates at least one task and determines the material content of the at least one task based on the configuration parameters, and based on the at least one task and the configuration parameters, at least one processing request is sent to a target service providing system that provides the target artificial intelligence service, wherein the processing request is used to trigger the execution of a corresponding task to process the corresponding material content, obtain a processing result, and obtain the processing result of the at least one task from the target service providing system.

[0016] In a third aspect, an embodiment of the present application provides a service access system, including a client and a server; the server is used to connect to multiple service provision systems; the multiple service provision systems respectively provide corresponding artificial intelligence services;

[0017] The client is used to display selection prompt information of multiple artificial intelligence services in a user interface; in response to a service selection operation triggered by a user, determine a target artificial intelligence service and send a service selection request to the server based on the target artificial intelligence service; and display configuration prompt information corresponding to the target artificial intelligence service in the user interface, determine configuration parameters in response to the configuration operation triggered by the user, and send the configuration parameters to the server;

[0018] The server is used to respond to a service selection request triggered by a user, determine the target artificial intelligence service, and based on the configuration parameters, generate at least one task and determine the material content of the at least one task; based on the at least one task and the configuration parameters, send at least one processing request to a target service providing system that provides the target artificial intelligence service; the processing request is used to trigger the execution of a corresponding task to process the corresponding material content and obtain a processing result; and obtain the processing result of the at least one task from the target service providing system.

[0019] In a fourth aspect, an embodiment of the present application provides a computing device, comprising a storage component and a processing component; the storage component stores one or more computer program instructions, the computer program instructions are called and executed by the processing component, and the processing component executes the one or more computer program instructions to implement the service provision method described in the first aspect, or the configuration method described in the second aspect.

[0020] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, wherein the computer program is executed by a computer to implement the service providing method as described in the first aspect, or the configuration method as described in the second aspect.

[0021] In a sixth aspect, an embodiment of the present application provides a computer program product storing a computer program, which, when executed by a computer, implements the service providing method described in the first aspect, or the configuration method described in the second aspect.

[0022] In the solution of the present application, the server can be connected to a service providing system corresponding to a plurality of artificial intelligence services, and can determine a target artificial intelligence service selected from a plurality of artificial intelligence services, and based on the configuration parameters provided for the target artificial intelligence service, generate at least one task and determine the material content of at least one task, and based on at least one task and the configuration parameters, send at least one processing request to the target service providing system providing the target artificial intelligence service, and the processing request can be used to trigger the execution of the corresponding task to process the corresponding material content to obtain the processing result, so that the processing result of the at least one task can be obtained from the target service providing system. By connecting to a plurality of service providing systems, the acquisition and use of a plurality of artificial intelligence services are supported. For a target artificial intelligence service selected from a plurality of artificial intelligence services, at least one task can be generated based on the provided configuration parameters, and at least one processing request can be sent to the target service providing system to obtain the processing result, so as to achieve the acquisition and use of the target artificial intelligence service, and solve the problem of the need to switch to log in to different service providing systems to obtain different services in the traditional solution, resulting in cumbersome operation and low efficiency, and realize the convenient and efficient use of artificial intelligence services, and improve the user experience.

[0023] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0025] Figure 1 A flowchart of an embodiment of a service providing method provided by the present application is shown;

[0026] Figure 2 A schematic diagram of an artificial intelligence service selection page in an actual application is shown;

[0027] Figure 3a-3b Schematic diagrams of configuration pages in different practical applications are shown respectively;

[0028] Figure 4a-4b Schematic diagrams of result display interfaces in different practical applications are shown respectively;

[0029] Figure 5 A flowchart of an embodiment of a configuration method provided by the present application is shown;

[0030] Figure 6 A schematic diagram showing the structure of an embodiment of a service access system provided by the present application is shown;

[0031] Figure 7 A schematic diagram showing the structure of an embodiment of a service providing device provided by the present application is shown;

[0032] Figure 8 A schematic diagram showing the structure of an embodiment of a configuration device provided by the present application is shown;

[0033] Fig. 9 A schematic diagram of the structure of an embodiment of a computing device provided by the present application is shown. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0035] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0036] The technical solution of the embodiment of the present application can be applied to the field of artificial intelligence services. With the development of artificial intelligence (AI) technology, people can use some AI tools to obtain corresponding AI services, such as content generation, natural language processing, machine learning model training, etc.

[0037] Taking artificial intelligence content generation (AIGC) service as an example, there are many different AIGC services in actual applications, such as video generation based on images and video editing. These AIGC services are provided by different service providers. In the process of implementing this application, the inventor found that if you want to use different AIGC services, you need to use different AIGC tools connected to different service providers. The operation is cumbersome and requires frequent tool switching, resulting in low efficiency.

[0038] Therefore, how to use AI services portably and efficiently becomes a technical problem that technicians in this field need to solve.

[0039] In order to solve the above technical problems, the inventors have proposed the technical solution of the present application after a series of studies. In an embodiment of the present application, a service access system is provided, which is composed of a client and a server. The server is connected to the service providing systems corresponding to multiple artificial intelligence services, and is targeted at a target artificial intelligence service among the multiple artificial intelligence services; based on the configuration parameters provided for the target artificial intelligence service, at least one task can be generated and the material content of the at least one task can be determined; and based on the at least one task and the configuration parameters, at least one processing request can be sent to the target service providing system that provides the target artificial intelligence service; the processing request is used to trigger the execution of the corresponding task to process the corresponding material content and obtain the processing result; and the processing result of the at least one task is obtained from the target service providing system.

[0040] By connecting multiple service provider systems, it supports the acquisition and use of multiple artificial intelligence services. For the target artificial intelligence service selected from multiple artificial intelligence services, at least one task can be generated based on the provided configuration parameters, and at least one processing request can be sent to the target service provider system to obtain the processing result, thereby realizing the acquisition and use of the target artificial intelligence service. This solves the problem of traditional solutions that require switching tools to connect to different service provider systems to obtain different services, resulting in cumbersome operations and low efficiency. It realizes convenient and efficient use of artificial intelligence services and improves user experience.

[0041] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0042] The technical solution of the embodiment of the present application can be applied to a system architecture including a client and a server. The client and the server can establish a connection through a network. The network can include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0043] The client can interact with the server through the network to send configuration parameters or receive processing results, etc.

[0044] Optionally, the server can also be connected to a plurality of service providing systems corresponding to the artificial intelligence services, and the server can establish a connection with each service providing system through the network. The server can interact with each service providing system through the network to send processing requests or obtain processing results.

[0045] Among them, the user end can be a browser, an APP (Application), or a web application such as an H5 (Hyper Text Markup Language 5, Hypertext Markup Language Version 5) application, or a light application (also known as a mini-program, a lightweight application) or a cloud application, etc. The user end can be deployed in an electronic device and needs to rely on the device to run or some APPs in the device to run, etc. The electronic device can, for example, have a display screen and support information browsing, such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, etc. Various other types of applications can usually be configured in the electronic device, such as human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0046] The service end may include servers that provide various services, such as a server that processes configuration parameters sent by a client, a server that sends processing requests to multiple service provision systems, a gateway responsible for network interconnection, etc.

[0047] The service providing system may include a server that provides corresponding artificial intelligence services, such as a server that processes processing requests sent by a server to perform corresponding tasks.

[0048] It should be noted that the server can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. The server can also be a server of a distributed system, or a server combined with blockchain. The server can also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0049] The service provider system can also be implemented as a distributed server cluster consisting of multiple servers, or as a single server. The server can also be a server of a distributed system, or a server combined with blockchain. The server can also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0050] It should be noted that the service providing method provided in the embodiment of the present application is generally performed by the server, and the configuration method is generally performed by the client. However, in other embodiments of the present application, the client may also have similar functions to the server, thereby performing the service providing method provided in the embodiment of the present application. In other embodiments, the service providing method provided in the embodiment of the present application may also be performed jointly by the client and the server.

[0051] It should be noted that the embodiments of the present application may involve the use of user data. In actual applications, user-specific personal data can be used in the scheme described herein within the scope permitted by applicable laws and regulations, subject to the requirements of applicable laws and regulations of the country where the user is located (for example, with the user's explicit consent, effective notification to the user, etc.).

[0052] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0053] It should be noted that the technical solution of the embodiment of the present application is applicable to a network virtual environment. The users described generally refer to "virtual users". Real users can register a user account in the server through registration to obtain a user identity in the network environment.

[0054] like Figure 1 As shown, it is a flow chart of an embodiment of a service providing method provided by the present application. The method can be executed by a server, and the server can connect to the service providing systems corresponding to multiple artificial intelligence services. The method can include the following steps:

[0055] 101: Determine a target artificial intelligence service selected from among a plurality of artificial intelligence services.

[0056] In the embodiment of the present application, the server can be connected to multiple service provision systems, and each service provision system can provide corresponding artificial intelligence services. Taking the artificial intelligence content generation (AIGC) service as an example, the AIGC service can refer to the execution of processing to generate content related to the specified input content, such as the AIGC service that generates corresponding videos based on images, and the AIGC service that generates corresponding videos based on object (such as goods in e-commerce scenarios) information.

[0057] The server may determine the selected target AI service in response to a service selection request sent by the client. The service selection request may be generated by the client in response to a selection operation for any AI service.

[0058] 102: Generate at least one task and determine material content of at least one task based on configuration parameters provided for the target artificial intelligence service.

[0059] The configuration parameters can be used to determine the material content corresponding to the target AI service requested, and / or to determine the processing parameters for processing the material content. For example, if the target AI service is an AIGC service that generates videos based on images, the configuration parameters can be used to determine the image requested to generate the video, and can also be used to determine the processing parameters for the image, such as the duration and theme of the generated video.

[0060] The configuration parameters may be provided by the client to the server in response to the user's configuration operation, and the server may generate corresponding tasks and determine corresponding material content, processing parameters, etc. based on the configuration parameters.

[0061] Among them, the material content can refer to the processing object of the target artificial intelligence service. For example, for an AIGC service that generates videos based on images, the material content is the image. For example, for an AIGC service that edits videos, the material content is the video to be edited.

[0062] In this embodiment, in order to improve service efficiency, batch configuration of multiple tasks can be supported. Therefore, based on the provided configuration parameters, at least one task can be generated and the material content of at least one task can be determined. For example, the target AI service is an AIGC service that generates a video based on specified product information. The configuration parameters can be used to determine multiple product information for requesting video generation, where generating a video based on each product information can be used as a task, and the product information can be used as the material content of the task, so that multiple tasks can be generated and the material content of each task can be determined.

[0063] Of course, different AI services may correspond to different configuration items, allowing users to provide different configuration parameters. The server may provide configuration prompt information of the target AI service for users to configure, which will be described in detail in subsequent embodiments.

[0064] 103: Based on at least one task and configuration parameters, send at least one processing request to a target service providing system that provides a target artificial intelligence service.

[0065] Among them, based on at least one task and configuration parameters, at least one processing request corresponding to each task can be generated, and at least one processing request can be sent to the target service providing system, and the processing request can be used to trigger the target service providing system to use the target AI service to perform the corresponding task to process the corresponding material content and obtain the processing result. The specific implementation of the target service providing system using the target AI service to perform the corresponding task to obtain the processing result can refer to the implementation process in the traditional solution, and this application will not elaborate on this.

[0066] 104: Obtain a processing result of at least one task from the target service providing system.

[0067] After the target service providing system completes executing the corresponding task, the corresponding processing result may be fed back to the server, so that the server can receive the processing result corresponding to at least one task.

[0068] In this embodiment, the server can be connected to a service provider system corresponding to a plurality of AI services, and can determine a target AI service selected from the plurality of AI services, and based on the configuration parameters provided for the target AI service, generate at least one task and determine the material content of at least one task, and based on the at least one task and the configuration parameters, send at least one processing request to the target service provider system providing the target AI service, and the processing request can be used to trigger the execution of the corresponding task to process the corresponding material content to obtain the processing result, so that the processing result of the at least one task can be obtained from the target service provider system. By connecting to a plurality of service provider systems, the acquisition and use of a plurality of AI services are supported. For a target AI service selected from a plurality of AI services, at least one task can be generated based on the provided configuration parameters, and at least one processing request can be sent to the target service provider system to obtain the processing result, so as to achieve the acquisition and use of the target AI service, and solve the problem that the traditional solution needs to switch tools connected to different service provider systems to obtain different services, resulting in cumbersome operation and low efficiency, and realizes the convenient and efficient use of artificial intelligence services, and improves the user experience.

[0069] The following describes the process of selecting the target AI service and providing configuration parameters.

[0070] In some embodiments, determining a target artificial intelligence service selected from a plurality of artificial intelligence services may include:

[0071] Provide selection prompts for multiple AI services;

[0072] In response to the service selection request, a target artificial intelligence service is determined.

[0073] The selection prompt information may include selection controls for multiple AI services, text prompt information, etc. Optionally, the server may provide a selection page including the selection prompt information to the client for display by the client, and the client may generate a service selection request in response to a selection operation for any AI service and send it to the server.

[0074] For ease of understanding, Figure 2 FIG. 1 shows a schematic diagram of selecting a page in an actual application. Figure 2 As shown, the selection page 20 may include a selection list 201 of multiple AI services such as "Text to Image", "Image to Video", "Product Information to Video", and a text prompt 202 of "Please Select AI Service". The server may provide the selection page 20 to the client for display, and the client may respond to the selection operation for any AI service in the selection page 20, such as responding to the selection operation for "Image to Video", generate a service selection request and send it to the server, and the server may determine that the target AI service is an AIGC service for generating video from image.

[0075] In practical applications, for the selected target AI service, in order to facilitate user configuration, the above method may further include:

[0076] In response to the service selection request, provide configuration prompt information corresponding to the target artificial intelligence service;

[0077] Get the configuration parameters for the target AI service.

[0078] The configuration prompt information may include multiple configuration items corresponding to the target AI service, parameter input boxes or candidate parameter selection controls corresponding to each configuration item, text prompt information, etc. For example, when the target AI service is to generate video from images, the configuration prompt information may include multiple configuration items such as image selection, video duration, and video theme.

[0079] Optionally, the server may pre-generate configuration prompt information corresponding to a plurality of AI services respectively, and when responding to a service selection request, provide the configuration prompt information corresponding to the target AI service to the client, and obtain the configuration parameters sent by the client.

[0080] Optionally, the server can pre-generate configuration pages corresponding to multiple AI services, and the configuration pages include corresponding configuration prompt information. In response to the service selection request, the server can provide the configuration page corresponding to the target AI service to the client for display by the client, and the client can send the configuration parameters to the server in response to the configuration operation.

[0081] Optionally, the configuration page may also include a confirmation control, and the client may also generate a service processing request in response to a trigger operation on the confirmation control, and send the service processing request to the server, so that the server can respond to the service processing request and obtain configuration parameters for the target AI service configuration.

[0082] In this embodiment, by providing selection prompt information for multiple AI services, it is convenient for users to directly and accurately select AI services, thereby improving user experience. In addition, for the selected target AI service, by providing configuration prompt information corresponding to the target AI service, it is convenient for users to quickly and accurately configure parameters for configurable items, thereby improving configuration efficiency and accuracy, and further improving user experience.

[0083] As described in the aforementioned embodiments, different AI services may correspond to different configuration items, allowing users to provide different configuration parameters. Therefore, the configuration parameters may be implemented in a variety of ways.

[0084] In an optional implementation, the configuration parameter may include an object identifier or an object combination identifier.

[0085] At this time, based on the configuration parameters provided for the target artificial intelligence service, generating at least one task and determining the material content of at least one task may include:

[0086] Generate a task corresponding to the object identifier according to the object identifier, and obtain object-related information corresponding to the object identifier from the object providing system as material content of the task;

[0087] Alternatively, tasks corresponding to multiple object identifiers are generated according to multiple object identifiers in the object combination indexed by the object combination identifier, and for any task, object related information corresponding to its corresponding object identifier is obtained from the object providing system as material content of the task.

[0088] In this embodiment, the target AI service may be, for example, an AIGC service that generates a video based on specified object information, and the configuration parameters may include an object identifier or an object combination identifier that can determine the object information. Taking the case where the object is a commodity in an e-commerce scenario, the object identifier may refer to a commodity ID, and the object combination identifier may refer to a commodity library ID. The commodity library may include multiple commodities, and multiple commodities in the commodity library may be of the same category or the same price, etc. This application does not restrict the division of the commodity library. Object-related information may refer to commodity information, such as the name, price, and historical sales data of the commodity. The object providing system may include a commodity providing system that stores commodity information, such as a commodity provider and a commodity seller. The commodity providing system may store the commodity ID in correspondence with the commodity information, and may store the commodity library ID in correspondence with the commodity information corresponding to multiple commodity IDs and multiple commodities in the commodity library. It can be understood that the commodity ID or the commodity library ID can be used as an index to obtain the corresponding commodity information from the commodity providing system.

[0089] Therefore, when the provided configuration parameter is an object identifier, the server can generate a task corresponding to the object identifier, and obtain object-related information corresponding to the object identifier from the object providing system as material content of the task.

[0090] When the configuration parameter provided is an object combination identifier, the server can determine multiple object identifiers in the object combination indexed by the object combination identifier based on the object combination identifier, and generate tasks corresponding to the multiple object identifiers respectively. For each task, the server can obtain object-related information corresponding to the object identifier from the object providing system as the material content of the task, thereby realizing batch configuration of multiple tasks.

[0091] In this embodiment, the configuration parameters provided for the target AI service may include an object identifier or an object combination identifier. The server can generate a corresponding task based on the object identifier and obtain the corresponding object-related information from the object providing system as the material content of the task. With this configuration method, the user does not need to provide specific material content, which can achieve the acquisition of material content and improve configuration efficiency. In addition, the server can also generate corresponding tasks based on multiple object identifiers in the object combination indexed by the object combination identifier.

[0092] Optionally, the configuration parameters may also include processing parameters for the object. Taking the object as a commodity as an example, the processing parameters may include, for example, specifying one or more description information obtained from the commodity providing system, audio data added to the video, the expected duration of the generated video, etc., which may be configured according to actual needs.

[0093] Optionally, the configuration prompt information provided by the server may include the configuration items corresponding to the above-mentioned object identifier, object combination identifier and processing parameters. Figure 3a Figure 1 shows a schematic diagram of a configuration page in an actual application. Figure 3a As shown, the configuration page 301 may include configuration items such as a commodity ID selection control 3011, a commodity library ID selection control 3012, a commodity ID or commodity library ID input box 3013, a description information selection control 3014, a video duration input box 3015, and an audio selection control 3016 for the user to configure, and may also include a task submission control 3017. For example, the user may click on the commodity library ID selection control 3012, and enter the commodity library ID, such as 0001, in the commodity ID or commodity library ID input box 3013, and may also click on the description information selection control 3014 to select the two description information of commodity price and historical sales data, and may also enter the desired video duration, such as 30 seconds, in the video duration input box 3015, and may also click on the audio selection control 3016 to select the option of no audio data. At this time, the corresponding configuration parameters may include the commodity library ID 0001, the specified description information is the commodity price and historical sales data, and the desired video duration is 30 seconds. Based on the configuration parameters, the server can generate tasks corresponding to multiple product IDs in the product library indexed by product library ID0001. The content of each task is to generate a 30-second video based on the product price and historical sales data of the corresponding product. The material content of each task is the product price and historical sales data of the corresponding product, and the material content is obtained from the product provision system.

[0094] In the above configuration, the user does not need to provide material content. Of course, in actual applications, the user can also directly provide material content. In another optional implementation, the configuration parameter may include at least one material content.

[0095] At this time, based on the configuration parameters provided for the target artificial intelligence service, generating at least one task and determining the material content of at least one task may include:

[0096] Based on at least one material content, at least one task corresponding to each material content is generated.

[0097] In this embodiment, the target AI service may be, for example, an AIGC service for generating videos based on images, and the material content, namely the specified image, may be directly uploaded from a local or specified address during parameter configuration. Among them, one or more images may be uploaded, and the server may generate corresponding tasks according to the one or more images.

[0098] By directly providing material content, the server does not need to perform material content acquisition operations, thereby improving material content acquisition efficiency. In addition, multiple material contents can be provided to achieve batch configuration of multiple tasks, thereby improving configuration efficiency.

[0099] Optionally, the configuration parameters may also include processing parameters. The processing parameters may include, for example, the expected duration of the video, the theme of the video, the size of the video screen, etc., which may be configured according to actual needs.

[0100] Optionally, the configuration prompt information may also include material provision prompt information. In this case, the method may also include:

[0101] In response to the triggered material providing request, at least one material content to be provided is determined.

[0102] The configuration prompt information provided by the server may include the configuration items corresponding to the above-mentioned material content and processing parameters. Optionally, the configuration prompt information may also include material provision prompt information, such as material provision controls, text prompt information, etc. The server may determine at least one material content to be provided in response to the triggered material provision request, and the material provision request may be generated by the client in response to the material provision operation.

[0103] For ease of understanding, Figure 3b FIG. 1 shows another schematic diagram of a configuration page in an actual application. Figure 3b As shown, the configuration page 302 may include configuration items such as a material upload control 3021 and a video theme selection control 3022 for the user to configure, and may also include a submission generation control 3023. For example, the user may click the material upload control 3021 to upload three clothing images from the local computer, and may also click the video theme selection control 3022 to select a clothing theme. At this time, the corresponding configuration parameters may include three clothing images and a clothing theme. Based on the configuration parameters, the server may generate tasks corresponding to the three clothing images, and the content of each task is to generate a video with the theme of clothing according to the corresponding clothing image, and the material content of each task is the corresponding clothing image.

[0104] It is understandable that the configuration page provided in the above one or more embodiments is only exemplary, and the present application does not limit the page format, layout, etc. of each configuration item in the configuration page.

[0105] In actual applications, after the server obtains the material content, it can also store the material content. Therefore, in some embodiments, the above method can also include:

[0106] The material content corresponding to at least one task is stored.

[0107] At this time, based on the at least one task and the configuration parameters, sending at least one processing request to the target service providing system providing the target artificial intelligence service may include:

[0108] Based on at least one task, a first storage address of material content corresponding to at least one task, and configuration parameters, at least one processing request is sent to a target service providing system that provides a target artificial intelligence service.

[0109] The first storage address is the storage address of the material content on the server. For each task, the server can generate a corresponding processing request based on the first storage address of the material content corresponding to the task and the configuration parameters. Specifically, the processing request can be generated based on the first storage address and other configuration parameters in the configuration parameters except the material content, object identifier, and object combination identifier.

[0110] The server may send the processing request to the target service providing system, and the target service providing system may obtain the stored material content from the server according to the first storage address to execute the corresponding task.

[0111] In this embodiment, the material content is stored, and a processing request is generated based on the first storage address and sent to the target service providing system, so that the target service providing system obtains the material content from the server according to the first storage address for processing.

[0112] In practical applications, when the number of tasks is large, in order to avoid sending a large number of processing requests at the same time, resulting in a large transmission pressure and affecting network stability, in some embodiments, based on at least one task and configuration parameters, sending at least one processing request to a target service providing system that provides a target artificial intelligence service may include:

[0113] Generate multiple processing requests based on multiple tasks and configuration parameters;

[0114] When the number of processing requests exceeds a preset number, multiple processing requests are sent to a target service providing system that provides the target artificial intelligence service through current limiting operations and / or retry operations.

[0115] The current limiting operation may refer to sending a preset number of processing requests to the target service provider system within the current time window, and delaying the processing requests exceeding the preset number to be sent within the next one or more time windows. The time window and the preset number may be set according to actual needs. The retry operation may refer to regenerating the processing request and waiting to send it when the waiting time for the processing request to be sent exceeds the preset time.

[0116] After the server sends the processing request to the target service providing system, it can wait for the target service providing system to execute the corresponding task. In actual applications, the target service providing system usually provides multiple execution machines to execute tasks. Each execution machine executes a task at the same time, and the next task will not be executed until the current task is completed. In addition, the target service providing system usually also provides a waiting queue, which is used to put the received tasks into the waiting queue in order from early to late in the order of receiving time. The tasks in the waiting queue will be allocated to the idle execution machines in the order of being placed in the waiting queue. Idle can mean that the execution machine has no tasks to execute. If there is no idle execution machine, each execution machine is waited for to execute its current task, and it is allocated to the first idle execution machine in turn. That is to say, the execution machine that first completes the current task executes the next task in the waiting queue. Therefore, after the server sends the processing request to the target service providing system, in order to know the execution status of the task, in some embodiments, the above method may also include:

[0117] For any task, a task query request is sent to the target service providing system, and the task status of the task is determined based on the query result fed back by the target service providing system.

[0118] The task status may include a running status and a waiting status. Specifically, if the query result includes the execution time of the task, the corresponding execution machine, etc., it can be determined that the task is in a running status. If the query result includes the position of the task in the waiting queue, etc., it can be determined that the task is in a waiting status.

[0119] In order to further understand the status of the task, the remaining time of the task in the current state can also be predicted. In some embodiments, the above method can also include:

[0120] For any target task in operation, predict the remaining execution time of the target task based on the historical execution time of the historical tasks corresponding to the target artificial intelligence service and the execution time of the target task in the target service provision system;

[0121] For any target task in a waiting state, the remaining waiting time of the target task is predicted based on the position of the target task in the waiting queue corresponding to the target service providing system, at least one execution machine in the target service providing system, the execution time of the tasks in the running state on the execution machine, and the historical execution time.

[0122] Specifically, for any target task in operation, the historical execution time of the historical task corresponding to the target AI service can be obtained. Among them, the historical execution time may refer to the execution time required for the target AI service to execute a corresponding historical task. It can be understood that for the same AI service, the execution time required to execute the same type of tasks is usually the same. Therefore, the historical execution time of the target AI service to execute the corresponding historical task can be used as the execution time required for the target task, and combined with the execution time of the target task, the remaining execution time of the target task can be predicted. Specifically, the average can be calculated based on the total execution time of multiple historical tasks executed by the target AI service and the number of historical tasks to obtain the average execution time, which is used as the historical execution time of the target AI service to execute the corresponding historical task.

[0123] Optionally, based on the historical execution time of the target artificial intelligence service on the historical tasks and the execution time of the target task in the target service providing system, predicting the remaining execution time of the target task may include:

[0124] The difference between the historical execution time of the target artificial intelligence service on the historical tasks and the execution time of the target tasks in the target service provision system is calculated to obtain the remaining execution time of the target task.

[0125] For any target task in a waiting state, the execution machine assigned to the target task and the remaining waiting time can be predicted based on the waiting status of the target task in the waiting queue and the execution status of each execution machine in the target service providing system, and according to the principle that the execution machine that first completes the current task executes the next task in the waiting queue.

[0126] Optionally, for any execution machine, the remaining execution time of the execution machine is counted based on the execution time and historical execution time of the tasks in running state in the execution machine; the operation of cyclically executing the principle that the execution machine with the shortest remaining execution time executes the next task to be executed in the waiting queue, adding the remaining waiting time corresponding to the execution machine and the historical execution time, and updating the remaining execution time of the execution machine based on the calculation result, until the next task to be executed in the waiting queue is the target task; the shortest remaining execution time is used as the remaining waiting time of the target task.

[0127] Take three execution machines as an example, namely, execution machine A, execution machine B, and execution machine C. If the execution time of the task in the running state in execution machine A is 10 seconds, the execution time of the task in execution machine B is 20 seconds, the execution time of the task in execution machine C is 15 seconds, and the historical execution time is 30 seconds, then the difference between the historical execution time and the execution time can be calculated to predict the remaining execution time of the current task of each execution machine, that is, the remaining execution time of execution machine A is 20 seconds, the remaining execution time of execution machine B is 10 seconds, and the remaining execution time of execution machine C is 15 seconds. From this, the execution machine with the shortest remaining execution time is determined, that is, the execution machine B that first completes the current task. According to the principle that the execution machine that first completes the current task executes the next task in the waiting queue, it can be predicted that the execution machine B will execute the next task in the waiting queue. The historical execution time of the next task is added to the remaining execution time of execution machine B to update the remaining execution time of execution machine B, that is, the remaining execution time of execution machine B is 40 seconds at this time. Based on the updated remaining execution time, continue to determine the execution machine with the shortest remaining execution time until the next task to be executed in the waiting queue is the target task. At this time, the execution machine to be assigned to the target task can be predicted, and the remaining execution time of the execution machine is the remaining waiting time of the target task.

[0128] In this embodiment, for any target task in the running state, by combining the historical execution time of the historical tasks corresponding to the target AI service and the execution time of the target task, the remaining execution time of the target task in the running state is predicted, which is convenient for having a clear perception of the execution status of the target task. For any target task in the waiting state, by combining the waiting status of the target task and the execution status of the tasks in each execution machine in the target service providing system, the remaining waiting time of the target task in the waiting state is predicted, which is convenient for having a clear perception of the waiting status of the target task and helps to realize task status management.

[0129] On this basis, the task status update prediction can also be performed with the help of the predicted remaining time. In some embodiments, the above method can also include:

[0130] For any target task in a waiting state, based on the remaining waiting time, a first query request is sent to a target service providing system when a state update of the target task is predicted; when a state update is determined to occur based on the first query result sent by the target service providing system, the target task is updated from a waiting state to a running state;

[0131] For any target task in the running state, based on the remaining execution time, when it is predicted that the target task will be updated in state, a second query request is sent to the target service providing system; when it is determined that the state update occurs based on the second query result sent by the target service providing system, the target task is updated from the running state to the ending state;

[0132] Alternatively, the end status fed back by the target service providing system when the target task execution is completed is obtained.

[0133] Among them, for the target task in the waiting state, when the predicted remaining waiting time is about to arrive, the target task may undergo a state update, such as updating from a waiting state to a running state. For example, if the predicted remaining waiting time is 10 seconds, then it is predicted that the target may undergo a state update after 8 to 10 seconds. A first query request can be sent to the target service providing system, and the task state of the target task can be determined based on the first query result fed back by the target service providing system, which will not be repeated here. Among them, the time when the target task is predicted to undergo a state update can be determined based on the predicted remaining waiting time. If the time difference between the remaining waiting time and the target task is less than a threshold, the threshold can be set according to actual needs.

[0134] When it is determined based on the first query result obtained from the target service providing system that the state of the target task is updated, the state of the target task may be updated, such as from a waiting state to a running state.

[0135] For a target task in the running state, when the predicted remaining execution time is about to arrive, the target task may undergo a state update, such as updating from the running state to the completed state. Therefore, when the target task is predicted to undergo a state update, a second query request may be sent to the target service providing system, and the task state of the target task may be determined based on the second query result fed back by the target service providing system, which will not be described in detail.

[0136] When it is determined based on the second query result obtained from the target service providing system that the state of the target task is updated, the state of the target task may be updated, such as from the running state to the ending state.

[0137] Alternatively, the target service providing system may actively obtain the end status fed back by the target service providing system when the target task is completed, wherein the end status may include a success status or a failure status.

[0138] In this embodiment, based on the predicted remaining waiting time or remaining execution time, it is possible to predict the update of the status of the target task and send a corresponding query request to the target service provider system. When it is determined that a status update has occurred based on the obtained query results, the status of the target task can be updated accordingly, so that there is a clear perception of the status and updates of the task, and clear task status management is achieved.

[0139] In addition, the above method may further include:

[0140] For any target task in the running state, if the processing result of the target task is not obtained from the target service providing system within a first preset time after the remaining execution time, a first abnormal prompt information is sent to the target service providing system;

[0141] For any target task in the waiting state, the waiting execution time of the target task is obtained based on the sum of the remaining waiting time and the historical execution time; if the processing result of the target task is not obtained from the target service provider system within a second preset time after the remaining waiting time, a second abnormal prompt information is sent to the target service provider system.

[0142] In this embodiment, it can also be determined whether the processing result sent by the target service provider system is received within the corresponding preset time after the predicted remaining execution time or the remaining waiting time is reached. If the processing result is not received, it can be considered that the target service provider system may have a fault, and corresponding abnormal prompt information can be sent to the target service provider system so that the target service provider system can perform fault detection and recovery in a timely manner.

[0143] In some embodiments, the above method may further include:

[0144] Feedback the processing result of at least one task.

[0145] Optionally, the task status, predicted remaining waiting time, remaining execution time, etc. corresponding to at least one task may also be fed back so that the user has a clear perception of the task execution status.

[0146] Optionally, feeding back to the user the processing result of at least one task may include:

[0147] Generate result prompt information of at least one task based on the processing result and configuration parameters of at least one task;

[0148] Feedback the result prompt information.

[0149] The result prompt information may include, for example, the task identifier, processing result, processing parameters, processing time, etc.

[0150] In some embodiments, the above method may further include:

[0151] The processing result corresponding to at least one task is stored.

[0152] At this time, based on the processing result and configuration parameters of at least one task, generating result prompt information of at least one task may include:

[0153] Based on the second storage address and configuration parameters of the processing results respectively corresponding to the at least one task, result prompt information of the at least one task is generated.

[0154] The second storage address may refer to the storage address of the processing result on the server. For each task, the server may generate result prompt information based on the second storage address of the processing result corresponding to the task and the configuration parameters. Specifically, the result prompt information may be generated based on the second storage address and other configuration parameters in the configuration parameters except the material content, object identifier, and object combination identifier.

[0155] The server may send result prompt information to the client, so that the user can obtain the stored processing result from the server according to the second storage address.

[0156] Optionally, the server can provide a result display page containing the above result prompt information. Different AI services can have different result display pages. For ease of understanding, Figure 4a-4b Schematic diagrams of two result display pages in actual applications are shown respectively. Figure 4a As shown, the target AI service corresponding to the result display page may be an AIGC service that generates videos based on product information. The result display page 401 displays result prompt information, which may include multiple product IDs and videos corresponding to each product ID, where the video corresponding to each product ID is the processing result of the task corresponding to the product ID. Figure 4a As shown, the result display page 401 displays multiple product ID display boxes 4011, a video display box 4012 corresponding to each product ID display box, and a download control 4013 corresponding to each video display box, wherein a product ID is displayed in each product ID display box 4011, and a video corresponding to the product ID is displayed in the corresponding video display box 4012. Optionally, a video cover and a video playback control (not shown in the figure) may be displayed in the video display box 4012, and a preset video clip or a complete video may be played in response to a trigger operation on the video playback control, which may be set according to actual needs.

[0157] like Figure 4bAs shown, the target AI service corresponding to the result display page can be an AIGC service that generates videos based on images, and the result display page 402 can include multiple task identification display boxes 4021, video display boxes 4022 corresponding to each task identification display box 4021, and video theme display boxes 4023 corresponding to each video display box. Among them, the task identification is displayed in each task identification display box 4021, the video corresponding to the task is displayed in the corresponding video display box 4022, and the theme corresponding to the video is displayed in the corresponding video theme display box 4023. Optionally, the video cover and video playback controls (not shown in the figure) can be displayed in the video display box 4022, and a preset video clip or a complete video can be played in response to a trigger operation on the video playback control, which can be set according to actual needs.

[0158] Optionally, the result display page may also include a generation time display box, a video aspect ratio display box, a processing parameter display box, a task status display box, etc. (not shown in the figure) corresponding to each video display box, so as to respectively display the generation time, aspect ratio, processing parameters, and task status corresponding to the video, such as success or failure, etc., which can be set according to actual needs.

[0159] Optionally, the result display page may also include a search control such as a search input box (not shown in the figure). In response to a search operation for a product ID or a task ID, a corresponding video may be determined to quickly find the processing result of a specific task.

[0160] It is understandable that the result display page provided in the above one or more embodiments is merely exemplary, and the present application does not impose any limitation on the page format, layout, etc. of the result display page.

[0161] The technical solution of this application is explained below from the perspective of the client.

[0162] like Figure 5 As shown, it is a flowchart of an embodiment of a configuration method provided by the present application, which can be executed by a client, and the client provides a user interface. The method can include the following steps:

[0163] 501: Displaying selection prompt information for multiple artificial intelligence services in the user interface.

[0164] Optionally, an AI service selection page may be displayed in the user interface, and the AI ​​service selection page may include selection prompt information for multiple AI services, such as Figure 2 The schematic diagram shown will not be described in detail.

[0165] 502: In response to the service selection operation, determine the target artificial intelligence service and send a service selection request to the server based on the target artificial intelligence service.

[0166] Among them, the server is connected to the service provision systems corresponding to multiple artificial intelligence services.

[0167] 503: Display configuration prompt information corresponding to the target artificial intelligence service on the user interface.

[0168] Optionally, a configuration page corresponding to the target AI service may be displayed in the user interface, and the configuration page may include configuration prompt information, such as Figure 3a-3b The schematic diagram shown will not be described in detail.

[0169] 504: In response to the configuration operation, determine configuration parameters.

[0170] 505: Send the configuration parameters to the server, so that the server can generate at least one task and determine the material content of at least one task based on the configuration parameters, and send at least one processing request to the target service providing system that provides the target artificial intelligence service based on the at least one task and the configuration parameters. The processing request is used to trigger the execution of the corresponding task to process the corresponding material content and obtain the processing result, and obtain the processing result of at least one task from the target service providing system. No further details will be given.

[0171] Optionally, the above method may further include:

[0172] Display a confirmation prompt in the user interface.

[0173] At this time, sending configuration parameters to the server may include:

[0174] In response to a confirmation operation triggered by the confirmation prompt information, a service processing request including configuration parameters is sent to the server.

[0175] Optionally, the confirmation prompt information may be, for example, a submit generation control in the configuration page.

[0176] Optionally, when the configuration parameters include material content, material provision prompt information may also be displayed in the user interface.

[0177] At this time, in response to the configuration operation triggered by the user, determining the configuration parameters may include:

[0178] In response to a material providing operation triggered by a user in response to material providing prompt information, at least one material content provided by the user is determined.

[0179] Optionally, the material providing prompt information may be, for example, a material upload control in a configuration page.

[0180] In this embodiment, by interacting with a server connected to multiple service provider systems, selection prompt information of multiple AI services is displayed in the user interface, and the acquisition and use of multiple AI services are realized. For the target AI service selected from multiple AI services, the configuration prompt information corresponding to the target AI service is displayed in the user interface so that the user can configure the corresponding parameters. The server generates at least one task based on the configuration parameters, and sends at least one processing request to the target service provider system to obtain the processing results, thereby realizing the acquisition and use of the target AI service. This solves the problem of the need to switch and log in to different service provider systems to obtain different services in the traditional solution, resulting in cumbersome operations and low efficiency, realizes convenient and efficient use of artificial intelligence services, and improves user experience.

[0181] In some embodiments, the above method may further include:

[0182] Get the processing result of at least one task sent by the server;

[0183] Result prompt information of the processing result of at least one task is displayed in the user interface.

[0184] Optionally, a result display page may be displayed in the user interface, and the result display page may include result prompt information, such as Figure 4a-4b The schematic diagram shown will not be described in detail.

[0185] like Figure 6 As shown, it is a structural diagram of an embodiment of a service access system provided by the present application, which may include a client 601 and a server 602. The server 602 is used to connect to multiple service providing systems 603; and the multiple service providing systems 603 respectively provide corresponding AI services.

[0186] Among them, the client 601 can be used to display selection prompt information of multiple AI services in the user interface; in response to a service selection operation triggered by the user, determine the target AI service and send a service selection request to the server 602 based on the target AI service; and display configuration prompt information corresponding to the target AI service in the user interface, determine configuration parameters in response to a configuration operation triggered by the user, and send the configuration parameters to the server 602.

[0187] The server 602 can be used to respond to a service selection request triggered by a user, determine the target AI service, and based on the configuration parameters, generate at least one task and determine the material content of at least one task; based on at least one task and the configuration parameters, send at least one processing request to the target service providing system 603 that provides the target AI service; the processing request is used to trigger the execution of the corresponding task to process the corresponding material content and obtain the processing result; and obtain the processing result of at least one task from the target service providing system 603.

[0188] By utilizing the server to connect to multiple service provider systems, it supports the acquisition and use of multiple AI services. For a target AI service selected from multiple AI services, it can generate at least one task based on the provided configuration parameters, and send at least one processing request to the target service provider system to obtain the processing result, thereby achieving the acquisition and use of the target AI service. This solves the problem in traditional solutions of having to switch tools to connect to different service provider systems to obtain different services, resulting in cumbersome operations and low efficiency. It achieves convenient and efficient use of artificial intelligence services and improves user experience.

[0189] Optionally, the server 602 may include a request module 6021 and a gateway module 6022 .

[0190] Specifically, the request module 6021 can respond to the service selection request triggered by the user, determine the target AI service, and based on the configuration parameters, generate at least one task and determine the material content of at least one task; based on at least one task and the configuration parameters, send at least one processing request to the gateway module 6022.

[0191] The gateway module 6022 may send at least one processing request to a target service providing system 603 that provides a target AI service, and obtain a processing result of at least one task from the target service providing system 603 .

[0192] Among them, the request module and the gateway module may include one or more servers. Optionally, the request module may include a request distribution server, a current limiting server and a retry server. The request distribution server can be used to send processing requests for different AI services to the gateway module to request the gateway module to send them to the corresponding service provider system. The current limiting server can be used to perform current limiting processing when the number of processing requests exceeds a preset number. The retry server can be used to perform retry processing when the waiting time for processing requests to be sent exceeds a preset time. The specific implementation can refer to the records in the aforementioned embodiments and will not be repeated.

[0193] Optionally, the gateway module 6022 may include a request gateway and a callback gateway, wherein the request gateway may be used to send a processing request or a query request to the target service providing system, and the callback gateway may be used to receive a processing result or a query result fed back by the target service providing system. The gateway module may integrate a variety of interfaces (Application Programming Interface, referred to as API), such as a task submission interface, a query interface, a callback interface, etc. Specifically, the task submission interface may be used to send a processing request to the target service providing system, and the query interface may be used to send a query request to the target service providing system to obtain the task status, and the callback interface may be used to receive a query result or a processing result fed back by the target service providing system.

[0194] Optionally, the request module 6021 can also provide the client 6011 with an AI service selection page, a target AI service configuration page, etc., and provide selection prompt information for multiple AI services to facilitate users to directly and accurately select AI services, thereby improving user experience. For the selected target AI service, by providing configuration prompt information corresponding to the target AI service, users can quickly and accurately configure parameters for configurable items, thereby improving configuration efficiency and accuracy and further improving user experience.

[0195] Optionally, the server 602 may further include a storage module 6023. The storage module 6023 may store the material content corresponding to each of the at least one task, and provide the first storage address corresponding to the material content to the request module 6021 to generate a processing request, and the storage module 6023 may also store the processing result corresponding to each of the at least one task provided by the gateway module 6022, and generate result prompt information based on the second storage address corresponding to the processing result and feedback it to the client 601. The storage module may also include one or more servers, for example, may include a material content storage device, a processing result storage device, etc. The material content storage device may be used to store the material content corresponding to each of the at least one task, and the processing result storage device may be used to store the processing result corresponding to each of the at least one task.

[0196] Optionally, the server 602 may also include a status module 6024. Specifically, the request module 6021 may send a processing request to the gateway module 6022 via the status module 6024 so as to comprehensively record the task status. The status module 6024 may be used to record and update the task status corresponding to at least one task. The status confirmation and update process may refer to the implementation recorded in the aforementioned embodiment, and will not be repeated here. Among them, the status module may also include one or more servers, such as a status initialization server, a status update server, a task success server, and a task failure server. Among them, the status initialization server may be used to initialize the corresponding task status when receiving the processing request sent by the request module 6021, such as recording it as an unexecuted state, etc. The status update server may be used to determine that the target task has a state update based on the query result of the target task provided by the gateway module 6022, and update the state of the target task. The task success server may be used to update the state of the target task to a successful state based on the processing result of the successful execution provided by the gateway module 6022, and the task failure server may be used to update the state of the target task to a failed state based on the failure prompt information provided by the gateway module 6022, etc.

[0197] By recording and updating the task status, you can have a clear understanding of the task status and updates, and achieve clear task status management.

[0198] Optionally, the server 602 may further include a time prediction module 6025. The time prediction module 6025 may be used to predict the remaining waiting time or remaining execution time of the target task based on the query result of the target task provided by the state module 6024, and feed back to the state module 6024. The prediction process of the remaining waiting time or the remaining execution time may refer to the implementation described in the aforementioned embodiment, and will not be repeated here. Among them, the time prediction module may also include one or more prediction models, for example, it may include a remaining waiting time prediction model and a remaining execution time prediction model, the remaining waiting time prediction model may be used to predict the remaining waiting time of the target task in the waiting state, and the remaining execution time prediction model may be used to predict the remaining execution time of the target task in the running state.

[0199] By predicting the remaining execution time of the target task in the running state and the remaining waiting time of the target task in the waiting state, it is convenient to have a clear perception of the execution status of the target task, which helps to realize task status management.

[0200] like Figure 7 FIG. 1 is a schematic diagram of a structure of an embodiment of a service providing device provided by the present application. The device may include the following units:

[0201] A first determination unit 701 is used to determine a target artificial intelligence service selected from a plurality of artificial intelligence services;

[0202] A generating unit 702, configured to generate at least one task and determine material content of at least one task based on configuration parameters provided for the target artificial intelligence service;

[0203] The first sending unit 703 is used to send at least one processing request to a target service providing system that provides a target artificial intelligence service based on at least one task and configuration parameters; the processing request is used to trigger the execution of a corresponding task to process corresponding material content and obtain a processing result;

[0204] The first acquisition unit 704 is configured to acquire a processing result of at least one task from the target service providing system.

[0205] In some embodiments, the first determination unit 701 may be specifically configured to provide selection prompt information for a plurality of artificial intelligence services; determine a target artificial intelligence service in response to a service selection request;

[0206] The device may also include:

[0207] The second acquisition unit is used to provide configuration prompt information corresponding to the target artificial intelligence service in response to the service selection request; and obtain configuration parameters configured for the target artificial intelligence service.

[0208] In some embodiments, the configuration parameters include an object identifier or an object combination identifier;

[0209] The generation unit 702 can be specifically used to generate a task corresponding to the object identifier according to the object identifier, and obtain the object-related information corresponding to the object identifier from the object providing system as the material content of the task; or, generate tasks corresponding to multiple object identifiers according to multiple object identifiers in the object combination indexed by the object combination identifier, and for any task, obtain the object-related information corresponding to its corresponding object identifier from the object providing system as the material content of the task.

[0210] In some embodiments, the configuration parameters include at least one material content;

[0211] The generating unit 702 may be specifically configured to generate at least one task corresponding to at least one material content based on at least one material content.

[0212] In some embodiments, the apparatus may further include:

[0213] A storage unit, used to store material content corresponding to at least one task;

[0214] The first sending unit 703 can be specifically used to send at least one processing request to a target service providing system that provides a target artificial intelligence service based on at least one task, a first storage address of material content corresponding to at least one task, and configuration parameters.

[0215] In some embodiments, the apparatus may further include:

[0216] A prediction unit is used to predict the remaining execution time of any target task in a running state based on the historical execution time of historical tasks corresponding to the target artificial intelligence service and the execution time of the target task in the target service providing system; and to predict the remaining waiting time of any target task in a waiting state based on the position of the target task in the waiting queue corresponding to the target service providing system, at least one execution machine in the target service providing system, the execution time of the task in a running state on the execution machine, and the historical execution time.

[0217] In some embodiments, the prediction unit can be specifically used to calculate the difference between the historical execution time of the target artificial intelligence service for the historical task and the execution time of the target task in the target service providing system for any target task in the running state, so as to obtain the remaining execution time of the target task; for any target task in the waiting state, for any execution machine, according to the execution time and the historical execution time of the tasks in the running state in the execution machine, calculate the remaining execution time of the execution machine; cyclically execute the operation according to the principle that the execution machine with the shortest remaining execution time executes the next task to be executed in the waiting queue, add the remaining execution time corresponding to the execution machine and the historical execution time, and update the remaining execution time of the execution machine based on the calculation result, until the next task to be executed in the waiting queue is the target task; and use the shortest remaining execution time as the remaining waiting time of the target task.

[0218] In some embodiments, the apparatus may further include:

[0219] The query unit is used for, for any target task in a waiting state, based on the remaining waiting time, predicting that the target task will undergo a state update, sending a first query request to a target service providing system; when it is determined that a state update will occur based on the first query result sent by the target service providing system, the target task is updated from a waiting state to a running state; for any target task in a running state, based on the remaining execution time, predicting that the target task will undergo a state update, sending a second query request to the target service providing system; when it is determined that a state update will occur based on the second query result sent by the target service providing system, the target task is updated from a running state to an ending state; or, obtaining an ending state fed back by the target service providing system when the target task execution ends.

[0220] In some embodiments, at least one task includes a plurality of tasks;

[0221] The first sending unit 703 can be specifically used to generate multiple processing requests based on multiple tasks and configuration parameters; when the number of processing requests exceeds a preset number, multiple processing requests are sent to a target service providing system that provides a target artificial intelligence service through current limiting operations and / or retry operations.

[0222] In some embodiments, the apparatus may further include:

[0223] The feedback unit is used to feed back the processing result of at least one task.

[0224] In some embodiments, the feedback unit may be specifically configured to generate result prompt information of at least one task based on the processing result and configuration parameters of at least one task; and to feed back the result prompt information.

[0225] In some embodiments, the storage unit may also be used to store the processing results corresponding to at least one task;

[0226] The feedback unit can be specifically used to generate result prompt information of at least one task based on the second storage address and configuration parameters of the processing results respectively corresponding to at least one task; and feed back the result prompt information.

[0227] Figure 7 The service provider shown can be used to perform Figure 1 The service provision method shown, its implementation principle and technical effect are not repeated here. Figure 7 One or more units of the service provider shown may constitute Figure 6 A module in the server architecture shown. The specific manner in which each unit performs operations in the service providing device in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0228] like Figure 8 As shown, it is a structural schematic diagram of an embodiment of a configuration device provided by the present application, and the device may include the following units.

[0229] A first display unit 801 is used to display selection prompt information of multiple artificial intelligence services in the user interface;

[0230] The second determination unit 802 is used to determine the target artificial intelligence service in response to the service selection operation and send a service selection request to the server based on the target artificial intelligence service; wherein the server is connected to the service providing systems corresponding to the multiple artificial intelligence services respectively;

[0231] The second display unit 803 is used to display configuration prompt information corresponding to the target artificial intelligence service on the user interface;

[0232] A third determining unit 804 is configured to determine a configuration parameter in response to the configuration operation;

[0233] The second sending unit 805 is used to send the configuration parameters to the server, so that the server can generate at least one task and determine the material content of at least one task based on the configuration parameters, and send at least one processing request to the target service providing system that provides the target artificial intelligence service based on the at least one task and the configuration parameters, and the processing request is used to trigger the execution of the corresponding task to process the corresponding material content, obtain the processing result, and obtain the processing result of at least one task from the target service providing system.

[0234] In some embodiments, the apparatus may further include:

[0235] The third display unit is used to obtain the processing result of at least one task sent by the server; and display the result prompt information of the processing result of at least one task in the user interface.

[0236] Figure 8 The configuration device shown can be used to perform Figure 5 The implementation principle and technical effect of the configuration method shown are not described in detail. The specific manner in which each unit performs operations in the configuration device in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0237] like Fig. 9 , which is a schematic diagram of a structure of an embodiment of a computing device provided by the present application, the device may include a storage component 901 and a processing component 902;

[0238] The storage component 901 may be used to store one or more computer program instructions, wherein the one or more computer program instructions are invoked and executed by the processing component 902 to implement Figure 1 The method of providing the service as indicated, or Figure 5 The configuration method shown.

[0239] Of course, the above computing device may also include other components, such as input / output interfaces, communication components, etc.

[0240] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc. The communication component is configured to facilitate wired or wireless communication between the computing device and other devices.

[0241] It should be noted that the above computing device implements Figure 1 In the case of the service provision method shown, it can be a physical device or an elastic computing host provided by a cloud computing platform, etc. It can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device.

[0242] The computing device described above implements Figure 5 In the case of the configuration method shown, it can be implemented as an electronic device. The electronic device can refer to a device used by a user and having the functions of surfing the Internet, computing, communicating, etc. required by the user, such as a mobile phone, a tablet computer, a personal computer, a wearable device, etc. It is understandable that the above electronic device may also include a display component, an input / output interface, a communication component, and other components, which will not be repeated.

[0243] In one or more of the above embodiments, the processing component may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0244] The storage component is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0245] The display component may be an electroluminescent (EL) element, a liquid crystal display or a micro display having a similar structure, or a retinal direct display or a similar laser scanning display.

[0246] The present application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a computer, Figure 1 The method of providing the service as indicated, or Figure 5 The configuration method shown. The computer readable medium may be included in the computing device described in the above embodiments; or it may exist independently without being assembled into the computing device.

[0247] The computer-readable storage medium may be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above.

[0248] The present application also provides a computer program product, which includes a computer program carried on a computer-readable storage medium, and when the computer program is executed by a computer, Figure 1 The method of providing the service as indicated, or Figure 5 The configuration method shown.

[0249] In such an embodiment, the computer program may be downloaded and installed from a network, and / or installed from a removable medium. When the computer program is executed by a processor, various functions defined in the system of the present application are performed.

[0250] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0251] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0252] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0253] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A service providing method, characterized in that: Applied to a server, the server is connected to a service providing system corresponding to a plurality of artificial intelligence services, and the method comprises: determining a target artificial intelligence service selected from the plurality of artificial intelligence services; Based on the configuration parameters provided for the target artificial intelligence service, generate at least one task and determine the material content of the at least one task; Based on the at least one task and the configuration parameters, at least one processing request is sent to a target service providing system that provides the target artificial intelligence service; the processing request is used to trigger the execution of a corresponding task to process corresponding material content and obtain a processing result; A processing result of the at least one task is acquired from the target service providing system.

2. The method according to claim 1, characterized in that Determining a target artificial intelligence service selected from the plurality of artificial intelligence services comprises: Providing selection prompt information for the plurality of artificial intelligence services; In response to the service selection request, determining a target artificial intelligence service; The method further comprises: In response to the service selection request, providing configuration prompt information corresponding to the target artificial intelligence service; Get configuration parameters for the target artificial intelligence service configuration.

3. The method according to claim 2, characterized in that The configuration parameters include an object identifier or an object combination identifier; The generating at least one task and determining the material content of the at least one task based on the configuration parameters provided for the target artificial intelligence service includes: Generating a task corresponding to the object identifier according to the object identifier, and acquiring object-related information corresponding to the object identifier from an object providing system as material content of the task; Alternatively, tasks corresponding to the multiple object identifiers are generated according to the multiple object identifiers in the object combination indexed by the object combination identifier, and for any task, object-related information corresponding to its corresponding object identifier is obtained from the object providing system as material content for the task.

4. The method according to claim 2, characterized in that: The configuration parameters include at least one material content; The generating at least one task and determining the material content of the at least one task based on the configuration parameters provided for the target artificial intelligence service includes: Based on the at least one material content, tasks corresponding to the at least one material content are generated.

5. The method according to claim 1, characterized in that Also includes: Storing material content corresponding to each of the at least one task; The sending at least one processing request to a target service providing system providing the target artificial intelligence service based on the at least one task and the configuration parameters comprises: Based on the at least one task, the first storage address of the material content respectively corresponding to the at least one task, and the configuration parameters, at least one processing request is sent to the target service providing system that provides the target artificial intelligence service.

6. The method according to claim 1, characterized in that Also includes: For any target task in operation, predict the remaining execution time of the target task based on the historical execution time of the historical tasks corresponding to the target artificial intelligence service and the execution time of the target task in the target service providing system; For any target task in a waiting state, the remaining waiting time of the target task is predicted based on the position of the target task in the waiting queue corresponding to the target service providing system, at least one execution machine in the target service providing system, the execution time of the tasks in the running state on the execution machine, and the historical execution time.

7. The method according to claim 6, characterized in that The predicting of the remaining execution time of the target task according to the historical execution time of the target artificial intelligence service on the historical task and the execution time of the target task in the target service providing system includes: Calculate the difference between the historical execution time of the target artificial intelligence service on the historical task and the execution time of the target task in the target service providing system to obtain the remaining execution time of the target task; The predicting the remaining waiting time of the target task according to the position of the target task in the waiting queue of the target service providing system, at least one execution machine in the target service providing system, the execution time of the task in running state on the execution machine, and the historical execution time comprises: For any execution machine, the remaining execution time of the execution machine is counted according to the execution time of the tasks in the running state in the execution machine and the historical execution time; the operation of cyclically executing the principle that the execution machine with the shortest remaining execution time executes the next task to be executed in the waiting queue, adding the remaining execution time corresponding to the execution machine and the historical execution time, and updating the remaining execution time of the execution machine based on the calculation result, until the next task to be executed in the waiting queue is the target task; the shortest remaining execution time is used as the remaining waiting time of the target task.

8. The method according to claim 6, characterized in that Also includes: For any target task in a waiting state, based on the remaining waiting time, when it is predicted that the target task will be updated in state, a first query request is sent to the target service providing system; When it is determined based on the first query result sent by the target service providing system that a state update occurs, updating the target task from a waiting state to a running state; For any target task in the running state, based on the remaining execution time, when it is predicted that the target task will be updated in state, a second query request is sent to the target service providing system; When it is determined based on the second query result sent by the target service providing system that a state update occurs, updating the target task from a running state to a finished state; Alternatively, the end status fed back by the target service providing system when the execution of the target task is completed is obtained.

9. The method according to claim 1, characterized in that: The at least one task includes a plurality of tasks; The sending at least one processing request to a target service providing system providing the target artificial intelligence service based on the at least one task and the configuration parameters comprises: Based on the plurality of tasks and the configuration parameters, generating a plurality of processing requests; When the number of processing requests exceeds a preset number, the multiple processing requests are sent to the target service providing system that provides the target artificial intelligence service through current limiting operations and / or retry operations.

10. The method according to claim 1, characterized in that Also includes: Feedback the processing result of the at least one task.

11. The method according to claim 10, characterized in that The feeding back of the processing result of the at least one task includes: Based on the processing result and configuration parameters of the at least one task, generating result prompt information of the at least one task; Feedback the result prompt information.

12. The method according to claim 11, characterized in that Also includes: storing a processing result corresponding to each of the at least one task; The generating result prompt information of the at least one task based on the processing result and configuration parameters of the at least one task includes: Based on the second storage address and configuration parameters of the processing results respectively corresponding to the at least one task, result prompt information of the at least one task is generated.

13. A configuration method, characterized in that: Applied to a client, the client providing a user interface, the method comprising: Displaying selection prompt information of multiple artificial intelligence services in the user interface; In response to the service selection operation, a target artificial intelligence service is determined and a service selection request is sent to a server based on the target artificial intelligence service; wherein the server is connected to service provision systems corresponding to the plurality of artificial intelligence services respectively; Displaying configuration prompt information corresponding to the target artificial intelligence service on the user interface; In response to the configuration operation, determining configuration parameters; The configuration parameters are sent to the server so that the server generates at least one task and determines the material content of the at least one task based on the configuration parameters, and based on the at least one task and the configuration parameters, at least one processing request is sent to a target service providing system that provides the target artificial intelligence service, wherein the processing request is used to trigger the execution of a corresponding task to process the corresponding material content, obtain a processing result, and obtain the processing result of the at least one task from the target service providing system.

14. The method according to claim 13, characterized in that Also includes: Obtaining a processing result of each of at least one task sent by the server; Result prompt information of the processing result of each of the at least one task is displayed in the user interface.

15. A service access system, characterized in that: It includes a client and a server; the server is used to connect to multiple service provision systems; the multiple service provision systems respectively provide corresponding artificial intelligence services; The client is used to display selection prompt information of multiple artificial intelligence services in a user interface; in response to a service selection operation triggered by a user, determine a target artificial intelligence service and send a service selection request to the server based on the target artificial intelligence service; and displaying configuration prompt information corresponding to the target artificial intelligence service on the user interface, determining configuration parameters in response to a configuration operation triggered by the user, and sending the configuration parameters to the server; The server is used to respond to a service selection request triggered by a user, determine a target artificial intelligence service, and generate at least one task and determine the material content of the at least one task based on the configuration parameters; Based on the at least one task and the configuration parameters, at least one processing request is sent to a target service providing system that provides the target artificial intelligence service; the processing request is used to trigger the execution of a corresponding task to process corresponding material content and obtain a processing result; A processing result of the at least one task is acquired from the target service providing system.

16. The system according to claim 15, characterized in that The server includes a request module and a gateway module; The request module is used to respond to the service selection request triggered by the user, determine the target artificial intelligence service, and generate at least one task and determine the material content of the at least one task based on the configuration parameters; Based on the at least one task and the configuration parameters, sending at least one processing request to the gateway module; and obtaining a processing result of the at least one task from the gateway module; The gateway module is used to send at least one processing request to a target service providing system that provides the target artificial intelligence service, and obtain the processing result of the at least one task from the target service providing system.

17. A computing device, characterized in that It comprises a storage component and a processing component; the storage component stores one or more computer program instructions, the computer program instructions are called and executed by the processing component, and the processing component executes the one or more computer program instructions to implement the service providing method as described in any one of claims 1 to 12, or the configuration method as described in any one of claims 13 to 14.

18. A computer-readable storage medium, characterized in that: A computer program is stored, and the computer program is executed by a computer to implement the service providing method according to any one of claims 1 to 12, or the configuration method according to any one of claims 13 to 14.

19. A computer program product, characterized in that A computer program is stored, and when the computer program is executed by a computer, the service providing method according to any one of claims 1 to 12 or the configuration method according to any one of claims 13 to 14 is implemented.

Images