Communication method, and application apparatus

Abstract

Provided in the embodiments of the present application is a communication method, which is applied to the field of AI. After receiving a service request of a service request device for a non-declarative API of a first service, a first network element acquires from a second network element first interface vector information of the first service provided by a first service platform, and then calls a multi-modal large model on the basis of the first interface vector information and first information, so as to acquire first response information of the service request of the non-declarative API, wherein the first response information comprises first conversion information of converting the non-declarative API into a first interface. By means of the embodiments of the present application, a non-declarative API can be converted into a declarative API, which is conducive to improving the development efficiency.

Description

Communication methods and application devices

[0001] This application claims priority to Chinese Patent Application No. 202411608349.3, filed on November 12, 2024, entitled "Communication Method and Application Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of artificial intelligence (AI) technology, and in particular to a communication method and application device. Background Technology

[0003] Declarative application programming interfaces (APIs) refer to services whose APIs need to be defined in advance before clients can develop applications based on the API's interface documentation, description, protocol, or specifications. In scenarios involving interoperability between multiple vendors' devices (typically referring to a client consumer simultaneously connecting to multiple service providers offering similar functionality, such as an API for SMS services), having standardized specifications that clearly define the interoperability APIs of various vendors can avoid inconsistencies and reduce the workload of interoperability development, which is beneficial for service interoperability. This is also the original intention of the 3rd Generation Partnership Project (3GPP) in standardizing interoperability interfaces for network elements within the domain. With the increasing proportion of interoperability with external service interfaces, traditional declarative APIs can no longer meet the flexibility requirements of services within and outside the 3GPP domain. Summary of the Invention

[0004] This application discloses a communication method and application device that can convert non-declarative APIs into declarative APIs, thereby improving development efficiency.

[0005] In a first aspect, embodiments of this application disclose a communication system, including a first network element and a second network element, wherein: the second network element is used to store first interface vector information, the first interface vector information being interface vector information of a first interface of a first service provided by a first service platform, and the first interface being a declarative API; the first network element is used to receive first information from a service requesting device, the first information being used to indicate the service request of a non-declarative API of the first service; the first network element is also used to obtain the first interface vector information from the second network element; the first network element is also used to call a multimodal large model based on the first interface vector information and the first information to obtain first response information of the service request, the first response information including first conversion information of the non-declarative API to the first interface. Thus, the non-declarative API can be converted into a declarative API, which helps improve development efficiency.

[0006] In the embodiments of this application, the multimodal large model (MLM) may include a large language model (LLM), a large video model (LVM), or a multimodal large language model (MLLM), etc., and is not limited thereto. Optionally, the multimodal large model has communication capabilities and can interact with the first network element or other communication devices.

[0007] LLM can understand business requirements based on natural language and, after fine-tuning, complete the conversion of specific text formats. For example, LLM can generate code based on the semantics described in natural language. LLM can also learn domain knowledge after pre-training on a large amount of data through fine-tuning techniques. These fine-tuning techniques can be based on a one-shot prompt or a few-shot prompt.

[0008] In this application embodiment, it is used to provide business services. This application does not limit the type of business provided by the service platform; it can be SMS service, storage service, data service, etc. This application uses a first service platform and a second service platform providing a first service as examples. In reality, the communication system may also have other service platforms, and the first or second service platform may provide other services. The first service can be any service provided by the service platform.

[0009] Optionally, the priority of the second service platform in responding to the first service can be lower than the priority of the first service platform. The priorities of the second and first service platforms can be pre-configured information, specified by the service requesting device, or determined based on the operational status of each service platform. For example, the priority for processing the first service can be determined based on the bandwidth, processing speed, and remaining capacity of the server corresponding to each service platform. In this way, even if the first service platform is unable to respond to the first service, the second service platform can respond to the first service to execute the first service.

[0010] In this embodiment, the first network element is the network element that implements the user's artificial intelligence agent (AI Agent) logic function. Optionally, the first network element can be a subscriber AI Agent function (SAAF) network element. The first network element can be understood as a declarative API transformation agent.

[0011] The first network element can use examples of declarative APIs to perform a reasoning and acting (ReAct) process on business requests from non-declarative APIs to obtain response information for those requests. This includes conversion information from non-declarative to declarative APIs, response information for unidentified business requests, and response information for unsuccessful conversion of non-declarative APIs. In other words, the first network element can receive business requests that require the invocation of non-declarative APIs. This allows non-declarative APIs to be converted into declarative APIs, thus solving the problem of pre-declaring interfaces and improving development efficiency.

[0012] Optionally, FirstNet's operators can pre-configure the account opening information for each service platform.

[0013] Furthermore, the first network element is used to store account opening information for each service platform. This account opening information includes the service platform's account information and authentication information. Account information may include the service platform's account number, service information provided (such as business interface parameters, service pricing information), etc., while authentication information may include verification information such as the service platform's account password. This application does not limit the content of the account opening information. Pricing information is used to indicate the billing standards for using the service platform, thereby determining the fees payable for calling the service platform's services.

[0014] Optionally, the operators of the First Network Element can also configure resources for the services provided by the service platform to obtain resource configuration information. This resource configuration information indicates the resource location for obtaining the interface information of the service, thereby allowing the interface information of the service to be obtained based on the resource location, such as the interface's documentation information and example information. The interface's documentation information indicates the interface parameters, and the example information indicates at least one example of calling the interface to implement the service. The resource location can be determined by a resource identifier. Optionally, the resource identifier can be a Universal Resource Identifier (URI), or it can be a service resource identifier, such as a service URI.

[0015] In this embodiment, the resource location can be a location accessible to the first network element in the network. Whether the first network element can access the interface information in the resource location can be determined by verification based on the aforementioned authentication information or other authentication information. If authentication is successful, the first network element can obtain the interface information in the resource location. If authentication fails, the first network element cannot obtain the interface information in the resource location.

[0016] In this embodiment, the second network element is used to store interface vector information of APIs provided by various service platforms. For example, the second network element stores first interface vector information, second vector information, etc. Optionally, the second network element can be a subscriber vector database function (SVDF) network element. The second network element can be regarded as a vector database (VDB).

[0017] In this embodiment, the service request device can be a terminal device or a network device, such as an application server, and is not limited thereto. The service request device can be understood as a communication device used by a user with a service request or a communication device with a service request. That is to say, the service request can be a service request submitted (input or triggered) by the user, or a service request automatically triggered by the communication device.

[0018] In some embodiments, the terminal devices, network devices, various network elements, and multimodal large models mentioned above can all be referred to as communication devices. They can be general-purpose devices or special-purpose devices. This application does not specifically limit them.

[0019] Optionally, the first network element obtains the first interface vector information from the second network element, including: the first network element sending a first acquisition request to the second network element, and the first network element receiving the first interface vector information from the second network element. The first acquisition request is used to instruct the acquisition of the first interface vector information. Thus, after receiving the first information, the first network element can first determine that the business request in the first information pertains to a first service. After determining that the first service platform can provide the first service, it can obtain the first interface vector information from the second network element. This allows the first network element to use the first interface vector information to convert the non-declarative API targeted by the business request in the first information into a first interface, thereby responding to the business request through the first interface of the first service platform. This eliminates the need for prior declaration of the non-declarative API targeting the first service, improving development efficiency.

[0020] In some possible examples, based on the first interface vector information and the first information, invoking a multimodal large model to obtain the first response information of the business request includes: obtaining a first prompt word based on the first interface vector information and the first information; sending a first request including the first prompt word to the multimodal large model, the first request being used to obtain the first response information of the business request; and receiving the first response information from the multimodal large model. Thus, obtaining the first response information of the business request through a multimodal large model can improve the efficiency and accuracy of responding to business requests.

[0021] In some possible examples, the first network element is further configured to obtain the first interface vector information based on the account opening information and resource configuration information of the first service platform; the first network element is also configured to send a storage request for the first interface vector information to the second network element, the storage request being used to instruct the storage of the first interface vector information. Thus, when the first network element receives a request for the first service, it can obtain the first interface vector information from the second network element to respond to the request and call the first interface of the first service or call a non-declarative API by referring to the calling method of the first interface.

[0022] In some possible examples, the first response information may also include first billing information for the service request, and the first network element may further determine the first billing information based on the account opening information of the first service platform. Thus, when the first service platform responds to the service request, it can deduct fees from the account corresponding to the service requesting device according to the billing information, or prompt the service requesting device to complete payment, etc. This application does not limit the payment method.

[0023] In some possible examples, the first interface vector information includes the first document vector information and the first example vector information of the first interface; the first conversion information is obtained by the multimodal large model based on the first document information and the first example information to convert the business request; wherein, the vector information of the first document information is the first document vector information, and the vector information of the first example information is the first example vector information. Thus, non-declarative APIs can be converted into information of declared first interfaces based on the first document vector information of the first interface and the first example vector information, which can improve the accuracy of the conversion.

[0024] In some possible examples, the first network element is also used to send the first response information to the first service platform; the first network element is also used to receive a first confirmation response or a first error response from the first service platform in response to the first response information.

[0025] The first confirmation response, such as a 200 OK response, indicates that the first service platform can successfully call the first interface corresponding to the first response information, thus fulfilling the business request. The first error response, such as a 500 error, indicates that the first service platform failed to call the first interface corresponding to the first response information, and the first service platform cannot provide the first service to the requesting device. Optionally, the first error response can be an error response from the first service platform or an error response from the first service. That is, when the first service platform cannot respond or the first service of the first service platform cannot respond, the first service platform can send a first error response to the first network element based on the first response information. The first confirmation response or the first error response here can be based on the first conversion information in the first response information.

[0026] It is understandable that, if the first service platform can respond to the first response information, it can call the first interface to fulfill the business request and send a first confirmation response to the first network element, instructing the first interface of the first service platform to provide the service for the first business request. If the first service platform cannot respond to the first response information, it can send a first error response to the first network element, indicating that the first service platform cannot respond to the business request.

[0027] In some possible examples, the first network element can also be used to send a second confirmation response to the service request platform for the first information upon receiving the first confirmation response. The second confirmation response, such as a 200 OK response, indicates that the service request of the first information has been successfully responded to. For example, if the first service requested by the first information is an SMS service, and the first network element receives the first confirmation response, it can send a second confirmation response to the service request device to indicate that the SMS service has been successfully responded to, i.e., the SMS was successfully sent. In some possible examples, the second network element is used to store second interface vector information, which is the interface vector information of the second interface of the first service provided by the second service platform, and the second interface is a declarative API. The first network element is also used to obtain the second interface vector information from the second network element upon receiving the first error response. The first network element is also used to call the multimodal big model based on the second interface vector information and the first information to obtain the second response information of the service request, whereby the second response information includes second conversion information of the non-declarative API being converted to the second interface.

[0028] It is understandable that upon receiving a first error response from the first service platform in response to the first response information, it can be confirmed that the first service platform cannot respond to the business request or has failed to respond to the business request. Therefore, the first network element can obtain the second interface vector information from the second network element. This second interface vector information is the vector information of the second interface of the second service platform for the first business. Then, based on the second interface vector information, the first network element can convert the non-declarative API targeted by the business request in the first information into the second interface, so as to realize the response to the business request through the second interface of the second service platform. This eliminates the need for pre-definition of non-declarative APIs, improving development efficiency and increasing the success rate of business request execution.

[0029] Secondly, this application discloses a first communication method applied to a first network element, which can be understood as a non-declarative API conversion agent. The method includes: receiving first information from a service requesting device, the first information indicating a service request from a non-declarative application programming interface (API) of the first service; obtaining first interface vector information from a second network element, the first interface vector information being interface vector information of a first interface of a first service provided by a first service platform, the first interface being a declarative API; and, based on the first interface vector information and the first information, invoking a multimodal large model to obtain first response information for the service request, the first response information including first conversion information of the non-declarative API to the first interface.

[0030] In some possible examples, based on the first interface vector information and the first information, invoking a multimodal large model to obtain the first response information of the business request includes: obtaining a first prompt word based on the first interface vector information and the first information; sending a first request including the first prompt word to the multimodal large model, the first request being used to obtain the first response information of the business request; and receiving the first response information from the multimodal large model.

[0031] In some possible examples, the method further includes: obtaining the first interface vector information based on the account opening information and resource configuration information of the first service platform; and sending a storage request for the first interface vector information to the second network element, wherein the storage request is used to instruct the storage of the first interface vector information.

[0032] In some possible examples, the first response information may also include first billing information for the business request, and the method may further include: determining the first billing information based on the account opening information of the first service platform.

[0033] In some possible examples, the first interface vector information includes the first document vector information and the first example vector information of the first interface; the first transformation information is obtained by the multimodal large model based on the first document information and the first example information to transform the business request; wherein, the vector information of the first document information is the first document vector information, and the vector information of the first example information is the first example vector information.

[0034] In some possible examples, the method further includes: sending the first response information to the first service platform; and receiving a first confirmation response or a first error response from the first service platform in response to the first response information.

[0035] In some possible examples, the method further includes: upon receiving the first confirmation response, sending a second confirmation response to the service requesting device in response to the first information.

[0036] In some possible examples, the method further includes: upon receiving the first error response, obtaining second interface vector information from the second network element, wherein the second interface vector information is the interface vector information of the second interface of the first service provided by the second service platform, and the second interface is a declarative API; and, based on the second interface vector information and the first information, invoking the multimodal big model to obtain second response information of the service request, wherein the second response information includes second conversion information of the non-declarative API being converted into the second interface.

[0037] It is understood that the steps of the communication method corresponding to the second aspect are the steps executed by the first network element of the first aspect. Refer to the description of the beneficial effects of the first aspect, and it will not be repeated here.

[0038] Thirdly, the second communication method provided in this application embodiment, applied to a second network element, can be understood as a vector database. The method includes: storing first interface vector information, where the first interface vector information is the interface vector information of a first interface of a first service provided by a first service platform, and the first interface is a declarative application programming interface (API); receiving a first acquisition request from a first network element, where the first acquisition request is used to indicate the acquisition of the first interface vector information; and sending the first interface vector information to the first network element.

[0039] In some feasible examples, the method further includes: receiving a storage request from the first network element, the storage request being used to instruct the storage of the first interface vector information.

[0040] In some feasible examples, the method further includes: storing second interface vector information, the second interface vector information being the interface vector information of the second interface of the first service provided by the second service platform, the second interface being a declarative API; receiving a second acquisition request from the first network element, the second acquisition request being used to indicate the acquisition of the second interface vector information; and sending the second interface vector information to the first network element.

[0041] It is understood that the steps of the communication method corresponding to the third aspect are the steps executed by the second network element of the first aspect. Refer to the description of the beneficial effects of the first aspect, and will not be repeated here.

[0042] Fourthly, this application discloses a communication device including units, modules, or means for performing the various steps of the second or third aspect or any of the implementation methods described above.

[0043] Fifthly, embodiments of this application disclose another communication device. This communication device may include a processor configured to execute instructions stored in memory, or via logic circuitry, cause the communication device to perform any of the methods described above or any possible examples.

[0044] In some feasible examples, the communication device also includes one or more of a memory or transceiver for sending and receiving data and / or signaling.

[0045] Sixthly, this application discloses yet another communication device, including a processor and a memory and a communication interface connected to the processor, the memory being used to store one or more programs and configured to be executed by the processor according to any of the steps described above.

[0046] In a seventh aspect, embodiments of this application disclose another communication system, which includes the communication apparatus of any of the above aspects.

[0047] In one feasible example, the communication device may include a first network element, a second network element, a service request device, a multimodal large model, or devices thereof.

[0048] Eighthly, embodiments of this application disclose a computer-readable storage medium storing instructions that, when executed, cause the method described in any of the above aspects to be implemented.

[0049] Ninthly, embodiments of this application disclose a computer program product for storing a computer program, which, when run on a computer, causes the computer to perform the methods described above.

[0050] In a tenth aspect, this application provides a chip or chip system including at least one processor for calling and executing instructions stored in a memory, causing a communication device on which the chip or chip system is mounted to perform any of the above aspects or possible examples of the method.

[0051] Optionally, the chip or chip system may also include memory.

[0052] Eleventhly, this application provides another chip, including: an input interface, an output interface, and a processing circuit. The input interface, the output interface, and the processing circuit are connected via internal connection paths. The processing circuit is used to execute the method of any of the above aspects or possible examples. Optionally, the chip also includes a memory. The input interface, the output interface, the processor, and the memory are connected via internal connection paths. The processor is used to execute code in the memory. When the code is executed, the processor is used to execute the method of any of the above aspects or possible examples.

[0053] In a twelfth aspect, this application provides another chip system including at least one processor and a communication interface, the communication interface and at least one processor being interconnected via a line, the at least one processor being used to run a computer program or instructions to perform the methods in any of the above aspects or possible examples.

[0054] It should be understood that the implementation and beneficial effects of the above-mentioned aspects can be mutually referenced. Attached Figure Description

[0055] The accompanying drawings used in the embodiments of this application are described below.

[0056] Figure 1 is a schematic diagram of the architecture of a communication system provided in an embodiment of this application;

[0057] Figure 2 is an interactive schematic diagram of a communication method provided in an embodiment of this application;

[0058] Figure 3 is an interactive schematic diagram of another communication method provided in an embodiment of this application;

[0059] Figures 4A and 4B are schematic diagrams of a first prompt word provided in an embodiment of this application;

[0060] Figures 5A and 5B are schematic diagrams of a first conversion information provided in an embodiment of this application;

[0061] Figure 6 is an interactive schematic diagram of another communication method provided in an embodiment of this application;

[0062] Figure 7 is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0063] Figure 8 is a schematic diagram of another communication device provided in an embodiment of this application. Detailed Implementation

[0064] To facilitate understanding of the technical solutions of the embodiments of this application, before introducing the solutions of the embodiments of this application, some terms or concepts that may be involved in the embodiments of this application will be introduced first.

[0065] I. Declarative APIs refer to APIs that need to be defined in advance before clients can develop applications based on the API's interface documentation, descriptions, protocols, or specifications. There are some industry practices regarding Kubernetes declarative APIs. Kubernetes, or K8s for short, is an open-source application used to manage containerized applications across multiple hosts in a cloud platform. Kubernetes aims to make deploying containerized applications simple and efficient, and K8s provides a mechanism for application deployment, planning, updating, and maintenance. The declarative APIs described in this article are different from the declarative APIs used when creating server-side containers in Kubernetes. Kubernetes declarative APIs are a server-side container development technique, not a pre-declared API in the general sense.

[0066] The existing 5GC interface uses a declarative API for external communication. Examples of declarative APIs can be found in the interfaces corresponding to the 5G core network (5GC), such as the N5 interface. The N5 interface is used to execute policy charging control (PCC) procedures, serving as a reference point for policy control function (PCF) network elements and application function (AF) network elements. AF network elements are used to implement various application-layer services; these can be internal operator AF network elements or third-party AF network elements (such as video servers, game servers, etc.).

[0067] Optionally, from the perspective of the PCF network element, the proxy-call session control function (PCSCF) network element acts as an AF network element. The N5 reference point is defined in 3GPP protocol TS23.501, and the related protocol is in 3GPP protocol TS29.514. It provides functionality equivalent to the diameter-based receive (Rx) reference point.

[0068] The N5 interface defines several key elements, including: Application Service Provider Identifier (ASPI), 5G Quality of Service (QoS) Identifier (5QI), and Guaranteed Bit Rate (GBR). The ASPI is an identifier provided by the Access Point (AP) that identifies the application service provider and sponsors traffic to correlate metering from different users. 5QI is a scalar indicating a 5G QoS feature, specifically an access node parameter controlling QoS flow forwarding, such as scheduling weights, admission thresholds, queue management thresholds, and link-layer protocol configurations. GBR refers to the guaranteed bit rate, or the guaranteed minimum bandwidth.

[0069] II. While there's no universally accepted definition in academia and industry, the mainstream definition is an AI agent capable of autonomously completing tasks (driven by tasks / goals / intents). AI agents are task-driven, using natural language instead of a graphical interface to identify user needs, generate reasonable plans and interfaces, and help users complete tasks / achieve goals—essentially interacting with humans using natural language. Furthermore, AI agents autonomously decide actions and review results through multimodal large models (such as Language Learning Models, LLMs) to complete tasks. Users only need to provide requirements; the AI ​​handles most of the work itself, enabling intelligent reasoning, breaking down tasks into sub-tasks, reasoning solutions, achieving task results, and simultaneously reflecting, iterating, and learning. This reflective ability allows them to work in unpredictable environments with a lot of new information. In addition, AI agents can use tools (such as calendar tools, calculators, search functions, etc.) by calling external application programming interfaces (APIs). For example, they can browse web pages, read and write files, make payments, and control computers. AI agents can also inject environmental information by calling APIs or other tools or external functions to interact with the real environment and code environment.

[0070] The essence of an AI agent is to issue commands through a multimodal large model (such as an LLM) and use external APIs and tools as its hands and feet to perform tasks. The reasoning ability of the multimodal large model constrains the upper limit of the agent's intelligence. The ability to invoke tools constrains the upper limit of the agent's action capability; how much potential can be realized depends on prompt engineering. A multimodal large model needs sufficient context as prompt words to infer a solution in order to obtain the desired result.

[0071] An artificial intelligence agent, or simply an intelligent agent, has many definitions. In this embodiment, an intelligent agent, based on user-given instructions or set goals, perceives and observes the state of the environment, retrieves built-in knowledge and perceptual experience memories, defines, decomposes, and plans tasks, forms and executes action strategies, and provides feedback to the target environment. An intelligent agent possesses the following characteristics:

[0072] (1) Autonomy: Intelligent agents can automatically adjust their behavior and state according to changes in the external environment, rather than just passively accepting external stimuli, and have the ability to self-manage and self-regulate.

[0073] (2) Reactivity: The ability to respond to external stimuli.

[0074] (3) Proactive: The ability of an intelligent agent to take proactive action in response to changes in the external environment.

[0075] (4) Social: Intelligent agents have the ability to cooperate with other intelligent agents or people. Different intelligent agents can interact with other intelligent agents according to their own intentions in order to solve problems.

[0076] (5) Evolutionary: Intelligent agents can accumulate or learn experience and knowledge, and modify their behavior to adapt to new environments.

[0077] Reasoning and Acting (ReAct) is a common agent iteration method that is essentially a paradigm that combines reasoning and acting.

[0078] Third, large multimodal models can include LLM, large video models (LVM), or large multimodal language models (MLLM), etc., without limitation. Among them, LLM can be based on natural language understanding of business requirements, and after relevant fine-tuning, complete the conversion of specific text formats. For example, LLM generates code based on the semantics described in natural language.

[0079] LLMs can also learn domain knowledge through fine-tuning techniques after pre-training on a large amount of data. These fine-tuning techniques can be based on either a one-shot prompt or a few-shot prompt. A one-shot prompt involves providing a single example prompt during interaction with the LLM, enabling it to complete the task based on that example. A few-shot prompt involves providing multiple example prompts during interaction, enabling the LLM to complete the task according to multiple examples.

[0080] For example, an LLM task is to answer questions in a consistent style. One sample prompt is an example of a conversation between a child and his grandfather, where the child says, "Teach me patience," and the grandfather replies, "The river that carves the deepest canyon originates from an unassuming spring; the grandest symphony begins with a single note; the most intricate tapestry begins with a solitary thread." If the input task is: "Teach me resilience," then the output could be: Resilience is like a tree; it needs to endure wind and rain, harsh winters and scorching summers, to grow stronger. Therefore, when you encounter setbacks and difficulties, don't give up easily; be like a tree, firmly rooted, constantly growing, and eventually becoming a tall tree.

[0081] Large Video Modeling (LVM) is a complex AI system designed to analyze and understand visual information, primarily images or videos. LVM can be viewed as the visual counterpart of LLM. MLLM, based on LLM, is capable of receiving and reasoning about multimodal information. MLLM is mainly divided into four types: multimodal instruction tuning, multimodal context learning, multimodal thought chaining, and LLM-assisted visual reasoning. Instruction tuning is a technique involving fine-tuning a pre-trained LLM on a dataset of instruction formats. Through this tuning, the LLM can generalize to unseen tasks by following new instructions.

[0082] IV. Terminal equipment is an entity on the user side used to receive or transmit signals, providing voice and / or data to the user. Terminal equipment may also be referred to as a terminal, user equipment (UE), access terminal, UE unit, UE station, mobile device, mobile station, mobile station, mobile terminal, mobile client, mobile unit, remote station, remote terminal, remote unit, wireless unit, wireless communication equipment, user agent, or user device, etc. Among these, an access terminal can be a cellular phone, cordless phone, session initiation protocol (SIP) phone, wireless local loop (WLL) station, personal digital assistant (PDA), handheld device with wireless communication capabilities, computing device or other processing device connected to a wireless modem, vehicle-mounted equipment, a terminal in a future 5G communication system, a terminal in a future evolved PLMN, or a terminal in a future NPN, etc.

[0083] As an example and not a limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, accessories, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0084] In this application embodiment, the terminal device can be a terminal as a final product, such as the various terminal devices described above, or it can be a component or part with terminal functions, or it can be a communication chip (such as a processor, baseband chip, or chip system, etc.) that can be applied in a terminal. That is to say, components, parts, or chips applied in the above-mentioned devices also belong to the terminal device. Among them, the chip system can be composed of chips, or it can include chips and other discrete devices.

[0085] V. Network devices are devices used to communicate with user equipment. As an example, a network device can be a device in a communication network used to provide services to user equipment. As an example, an access network (AN) device is used. An access network device, also known as a radio access network (RAN) device, or simply an access network, is a node or device that connects terminal devices to a wireless network. In other words, the access network provides access services to terminal devices, enabling them to access (or connect to) the network. Access networks can support both wired and wireless access.

[0086] Optionally, the access network consists of multiple AN / RAN nodes. AN / RAN nodes may include, but are not limited to: access points (APs), enhanced node Bs (eNBs), home evolved Node Bs (HNBs), baseband units (BBUs), next-generation node Bs (gNBs), transmit / receive points (TRPs), transmission points (TPs), or other access nodes, such as wireless relay nodes or wireless backhaul nodes. AN / RAN nodes may be one or more antenna panels, or network nodes constituting gNBs or transmission points, such as BBUs or distributed units (DUs), or devices performing RAN functions in communication systems such as D2D, V2X, M2M, and U2U. The AN / RAN node can be a radio controller in a cloud radio access network (CRAN) scenario, an open RAN (O-RAN or ORAN), or an access network in a communication system evolved after 5G, such as xNodeB in a 6G communication system, or an access network in a PLMN network evolved after 5G, etc., without limitation. Furthermore, the solution provided in this application can be applied to satellite communication systems, such as an NTN integrated into a 5G system or a future evolved communication system. In this case, the network equipment can be a satellite with access network equipment functionality, or access network equipment deployed on a satellite.

[0087] As another example, network devices may include one or more of the following: network exposure function (NEF) network elements, home subscriber server (HSS), serving-call session control function (S-CSCF) devices, access and mobility management function (AMF) network elements, unified data management (UDM) network elements, and application server (AS). It is understood that the application server can provide application-layer services to user equipment (or provide services to application clients in the user equipment), such as video services, navigation services, e-commerce services, or social communication services. The specific application-layer service is not limited in this embodiment.

[0088] In the embodiments of this application, a network element may also be referred to as a functional network element, functional entity, node, device, etc. A network element may be a network component implemented on dedicated hardware, a software instance running on dedicated hardware, or an instance of virtualized functionality on an appropriate platform.

[0089] The network device described in this application embodiment can be a network device as a final product, such as the various network devices mentioned above, or it can be a component or part with network device functions, or it can be a communication chip (such as a processor, baseband chip, or chip system) that can be applied in a network device. That is to say, components, parts, or chips applied in the above-mentioned devices also belong to network devices.

[0090] The technical solutions of this application embodiment can be applied to various communication systems, such as long term evolution (LTE) communication systems, new radio (NR) communication systems, LTE-A advanced (LTE-A) communication systems, device-to-device (D2D) communication systems, vehicle-to-everything (V2X) communication systems, machine-to-machine (M2M) communication systems, internet of things (IoT) communication systems, narrowband internet of things (NB-IoT) communication systems, integrated sensing and communication systems, frequency division duplex (FDD) communication systems, time division duplex (TDD) communication systems, non-terrestrial network (NTN) communication systems, wireless projection communication systems, integrated access and backhaul (IAB) communication systems, public land mobile network (PLMN) communication systems, and non-public networks. The communication network can be an NPN (Network for Networks) communication system, or a communication system evolved from 5G (such as 6G), or a non-3rd Generation Partnership Project (3GPP) communication system, etc., without limitation. Furthermore, in the embodiments of this application, the communication network may include an operator's IP Multimedia Subsystem (IMS) network, an established communication network, or other communication networks, without limitation.

[0091] In some embodiments, network devices, terminal devices, network elements, etc., may be referred to as communication devices, which may be general-purpose devices or special-purpose devices. This application does not specifically limit this.

[0092] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in the embodiments of this application will be described below with reference to the accompanying drawings.

[0093] Please refer to Figure 1, which is a schematic diagram of the architecture of a communication system provided in an embodiment of this application. As shown in Figure 1, the architecture of this communication system may include the following devices, network elements, and network:

[0094] 1. Both the first service platform and the second service platform are service platforms, such as cloud service platforms, used to provide business services. This application does not limit the type of business services provided by the service platforms; they can be SMS services, storage services, data traffic services, etc. In this embodiment, the first service platform and the first service are used as examples. In reality, the communication system can also have other service platforms and other services. As shown in Figure 1, the communication system may also include a second service platform, which can be a service platform other than the first service platform that provides the first service. Optionally, the communication system may also include a service platform not shown in Figure 1, and either the first service platform or the second service platform can provide services not shown in Figure 1.

[0095] In this application embodiment, the interface of the first service provided by the first service platform can be referred to as the first interface, and the interface of the first service provided by the second service platform can be referred to as the second interface. This application does not limit the number of first interfaces and second interfaces; that is, the first service platform can provide one or more first interfaces for the first service, and the second service platform can provide one or more second interfaces for the first service. For example, if the first service is an SMS service, the first service platform can provide a first interface for sending mass SMS messages, and also a first interface for sending MMS messages, etc.

[0096] This application does not limit the number of first and second service platforms. There can be one or more first service platforms, and there can also be one or more second service platforms. Optionally, the priority of the second service platform in responding to the first service can be lower than the priority of the first service platform. The priorities of the second and first service platforms can be pre-configured information, specified by the service requesting device, or determined based on the operational status of each service platform. For example, the priority of processing the first service can be determined based on the bandwidth, processing speed, and remaining capacity of the server corresponding to each service platform. Thus, even if the first service platform is unable to respond to the first service, the second service platform can respond to the first service to execute the first service.

[0097] It is understandable that different service platforms can provide one or more different business services, and different service platforms can set the same or different APIs for the same business, and set one or more interface parameters. When calling the API of the first business of a service platform, it is necessary to first determine the interface parameters of the API of the first business provided by the service platform, and then generate the code to call the API of the first business on the service platform based on these interface parameters, so as to implement the first business.

[0098] Please refer to Table 1 below. Table 1 describes the API interface parameters of the SMS service provided by each of the multiple service platforms, such as the sender's number, the receiver's number, the template identifier, the list of variable values ​​for the template, and the signature name.

[0099] Table 1

[0100] As can be seen, the three service platforms described in Table 1 all provide SMS services, and the API interface parameters for the SMS services provided by each service platform can be different. Therefore, when calling the SMS service interface of a service platform, it is necessary to first determine the API interface parameters of the SMS service provided by that service platform, and then generate the code to call the SMS service API on that service platform based on these interface parameters, so as to respond to the SMS service and ensure that the SMS message is successfully sent.

[0101] 2. The first network element is the network element that implements the user's artificial intelligence agent (AI Agent) logic function. Optionally, the first network element can be a subscriber AI Agent function (SAAF) network element.

[0102] In this embodiment, the first network element can be understood as a declarative API conversion agent. The first network element can implement a ReACT process on business requests from non-declarative APIs using examples of declarative APIs to obtain response information for those requests, such as conversion information from non-declarative APIs to declarative APIs, response information for unidentified business requests, and response information for unsuccessful conversion of non-declarative APIs. In other words, the first network element can receive business requests that require the invocation of non-declarative API services. Thus, non-declarative APIs can be converted into declarative APIs, improving development efficiency.

[0103] Optionally, FirstNet's operators can pre-configure the account opening information for each service platform.

[0104] Furthermore, the first network element is used to store the account opening information of each service platform. For example, please refer to Figure 2, which is an interactive schematic diagram of a communication method provided in an embodiment of this application. Figure 2 can be understood as a preparation method for the interface of the first service platform to be called by the first network element, or as a configuration or preparation process of the first network element for the first service platform. As shown in Figure 2, the method may include step S201: the first network element stores the account opening information of the first service platform.

[0105] The account opening information includes the service platform's account information and authentication information. Account information may include the service platform's account number, service information provided (such as business interface parameters, service pricing information), etc., while authentication information may include verification information such as the service platform's account password. This application does not limit the content of the account opening information. Pricing information is used to indicate the billing standards for using the service platform, thereby determining the fees payable for calling the service platform's services.

[0106] For example, the operators of the first network element can register an account on the service platform to obtain the service platform's account information within the first network element. The operators can also authenticate relevant sessions on the service platform to obtain the service platform's authentication information within the first network element. Account information and authentication information, among other account opening information, can be stored in the first network element's memory, allowing the first network element to send a request to the service platform for the first service based on the service platform's account information, requesting the invocation of the service platform's first interface to provide the first service. The service platform can trigger authentication with the first network element in response to the service request. The first network element can complete the authentication based on the service platform's authentication information, and upon successful authentication, the first network element can establish a communication connection with the service platform and invoke the service platform's first interface to provide the first service.

[0107] Optionally, the operators of First Network Element can also configure resources for the services provided by the service platform to obtain resource configuration information. This resource configuration information indicates the resource location for obtaining the interface information of the service, thereby allowing the interface information of the service to be obtained based on the resource location, such as the interface's documentation information and example information. The interface's documentation information indicates the interface parameters, and the example information indicates at least one example of calling the interface to implement the service.

[0108] Resource location can be determined using a resource identifier. Optionally, the resource identifier can be a Universal Resource Identifier (URI), or it can be a service resource identifier, such as a service URI. Each interface has a different resource identifier; for example, the resource identifier for the first interface is used to identify the resources of the first interface, and the resource identifier for the second interface is used to identify the resources of the second interface.

[0109] In this embodiment, the resource location can be a location accessible to the first network element in the network. Whether the first network element can access the interface information in the resource location can be determined by verification based on the aforementioned authentication information or other authentication information. If authentication is successful, the first network element can obtain the interface information in the resource location. If authentication fails, the first network element cannot obtain the interface information in the resource location.

[0110] Optionally, the first network element is used to obtain the interface vector information of the first service provided by the service platform based on the account opening information and resource configuration information of the service platform. For example, the method shown in Figure 2 may further include step S202: the first network element obtains the first interface vector information based on the account opening information and resource configuration information of the first service platform, wherein the first interface vector information is the interface vector information of the first interface of the first service provided by the first service platform.

[0111] As mentioned earlier, the resource configuration information of the first service platform can be determined based on the account opening information, and the first interface vector information can be obtained based on this resource configuration information. Similarly, the first network element can also obtain the interface vector information of the first service provided by the second service platform based on the account opening information and resource configuration information of the second service platform, etc., which will not be elaborated here.

[0112] In this embodiment, the interface vector information of the first interface of the first service provided by the first service platform can be referred to as the first interface vector information, and the interface vector information of the second interface of the first service provided by the second service platform can be referred to as the second interface vector information. The first interface vector information may include first document vector information and first example vector information, wherein the first document vector information may be the vector information of the first document information of the first interface, etc. The first example vector information may be the vector information of the first example information of the first interface. Similarly, the second interface vector information may include the second document vector information of the second document information of the second interface and the second example vector information of the second example information of the second interface, etc.

[0113] 3. The second network element stores the interface vector information of the APIs provided by various service platforms. For example, the second network element stores the first interface vector information, the second vector information, etc. Optionally, the second network element can be a subscriber vector database function (SVDF) network element. The second network element can be regarded as a vector database (VDB).

[0114] In some feasible examples, as shown in Figure 2, the method may further include steps S203 and S204, wherein,

[0115] S203: The first network element sends a storage request for the first interface vector information to the second network element. The storage request is used to indicate the storage of the first interface vector information.

[0116] Correspondingly, the second network element receives the storage request from the first network element.

[0117] S204: The second network element stores the vector information of the first interface.

[0118] As can be understood, in the method shown in Figure 2, after the first network element stores the account opening information of the first service platform, it can obtain the first interface vector information of the first service provided by the first service platform based on the account opening information and resource configuration information of the first service platform. The first network element then sends a storage request for the first interface vector information to the second network element, so that the second network element can store the first interface vector information. Thus, when the first network element receives a request for the first service, it can obtain the first interface vector information from the second network element to respond to the request and call the first interface of the first service or call the non-declarative API by referring to the calling method of the first interface.

[0119] 4. The multimodal large model can be referred to the foregoing and will not be repeated here. In the embodiments of this application, the multimodal large model has communication function and can interact with the first network element or other communication devices.

[0120] 5. The service request device can be any of the aforementioned terminal devices or network devices, such as application servers, and is not limited thereto. In this embodiment, the service request device can be understood as a communication device used by a user with a service request or a communication device with a service request. That is, the service request can be a service request submitted (inputted or triggered) by the user, or a service request automatically triggered by the communication device.

[0121] In some embodiments, the terminal devices, network devices, various network elements, and multimodal large models mentioned above can all be referred to as communication devices. They can be general-purpose devices or special-purpose devices. This application does not specifically limit them.

[0122] The network architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0123] The functions of the above service platform, first network element, second network element, service request device and multimodal large model can be referred to the description in Figure 3 below, and will not be elaborated here.

[0124] Please refer to Figure 3, which is an interactive schematic diagram of another communication method provided in this application embodiment. Figure 3 can be understood as the execution method of the first network element responding to the service request platform's service request. This method is applied after the method provided in Figure 2, such as after step S204. The communication devices involved in this method may include a service request device, a first network element, a second network element, and a multimodal large model, etc. These communication devices can be referred to the description in Figure 1, and will not be repeated here. This method includes, but is not limited to, the following steps S301 to S303, wherein:

[0125] S301, The first network element receives the first information from the service requesting device. The first information is used to indicate the service request of the non-declarative API of the first service.

[0126] Accordingly, the service requesting device sends the first information to the first network element.

[0127] In this embodiment, the service request device can be used to send first information to a first network element. This first information is a service request from the service request device via a non-declarative API for a first service. The first information can be text, video, etc., and is not limited here. If the information type of the first information is the same as the model type of the multimodal large model, then no information type conversion is needed. If the information type of the first information is different from the model type of the multimodal large model, it needs to be processed into information of the model type of the multimodal large model before calling the multimodal large model. For example, if the multimodal large model is LLM and the first information is a service request described in natural language, no information type conversion is needed. As another example, if the multimodal large model is LLM and the first information is video or an image, the first information can be converted into a service request described in natural language before calling the multimodal large model.

[0128] Optionally, the first information can be used to indicate the first business.

[0129] When the first information indicates the first service, the interface that can provide the first service can be determined through the services provided by each service platform, and the interface vector information of the interface can be obtained from the second network element.

[0130] Optionally, if multiple service platforms provide the first service, the first network element can designate one of them as the first service platform. The first service platform can be the service platform with the highest priority, and the priority can be predefined or determined by configuration.

[0131] The priority information can be designated as "first information," which further indicates at least two service platforms and specifies the preferred platform. This allows the system to determine the first service platform to be used. In the event of a failure of the first service platform, resulting in an inability to respond or a delayed response, the service platform indicated in the first information can be invoked to fulfill the business request.

[0132] Optionally, the initial information can be used to indicate interface parameters. In this way, responses to business requests can be implemented based on the interface parameters.

[0133] For example, the first message might include the following business request: Please use the SMS service interfaces of the first and second service platforms to send an SMS to XXXXXXXXXXX. The SMS requirements are: send only once, prioritize the first service platform, and if the first service platform fails to send the message, then call the interface of the second service platform. The SMS template identifier is 54321, the signature name is "Meeting Notification Only," and the SMS content is "Second Floor Meeting Room, 14:00-16:00." Thus, the business request can be identified as an SMS service request, requesting that the SMS be sent first on the first service platform. If the first service platform cannot respond to this business request, a request is made to send the SMS on the second service platform. The content of this SMS is used to notify that a meeting will be held in the second floor meeting room from 14:00 to 16:00.

[0134] In the embodiments of this application, the first information may not indicate the service platform, nor may it indicate the preferred service platform. This application does not limit the first information.

[0135] S302. The first network element obtains the first interface vector information from the second network element. The first interface vector information is the interface vector information of the first interface of the first service provided by the first service platform. The first interface is a declarative API.

[0136] The first interface vector information can be referred to the foregoing and will not be repeated here. In some feasible examples, the first interface vector information includes the first document vector information and the first instance vector information of the first interface; wherein, the vector information of the first document information is the first document vector information, and the vector information of the first instance information is the first instance vector information.

[0137] In this embodiment, the first network element can be used to obtain first interface vector information from the second network element. Optionally, step S302 may include: the first network element sending a first acquisition request to the second network element, and the first network element receiving the first interface vector information from the second network element. Correspondingly, the second network element receives the first acquisition request from the first network element, and the second network element sends the first interface vector information to the first network element.

[0138] The first acquisition request is used to instruct the acquisition of first interface vector information. Thus, after the first network element receives the first information, it can first determine that the business request in the first information pertains to a first service. After determining that the first service platform can provide the first service, it can acquire the first interface vector information from the second network element. This allows the first network element to use the first interface vector information to convert the non-declarative API targeted by the business request in the first information into a first interface, thereby responding to the business request through the first interface of the first service platform. This eliminates the need for prior declaration of the non-declarative API for the first service, improving development efficiency.

[0139] In some feasible examples, the method may further include: the first network element obtaining first interface vector information based on the account opening information and resource configuration information of the first service platform; the first network element sending a storage request for the first interface vector information to the second network element. Correspondingly, the second network element receives the storage request from the first network element and stores the first interface vector information.

[0140] The storage request is used to instruct the storage of the first interface vector information. This example can be seen in the description in Figure 2, and will not be repeated here. It can be understood that when the first network element receives a business request for the first service, and this business request is also for a non-declarative API, it can obtain the first interface vector information from the second network element to respond to the request. The response to the business request is then implemented through the first interface of the first service platform, eliminating the need for pre-definition of the non-declarative API and improving development efficiency.

[0141] S303. The first network element calls the multimodal large model to obtain the first response information of the business request based on the first interface vector information and the first information. The first response information includes the first conversion information of the non-declarative API to the first interface.

[0142] The first transformation information is used to indicate how the non-declarative API on the first service platform should provide the service of the first business according to the first interface. In some feasible examples, the first transformation information can be obtained by a multimodal large model based on the transformation of business requirements using first document information and first example information. Here, the vector information of the first document information is the first document vector information, and the vector information of the first example information is the first example vector information. Thus, the non-declarative API can be transformed into the information of the declared first interface based on the first document vector information of the first interface and the first example vector information, which can improve the accuracy of the transformation.

[0143] In some feasible examples, step S303 may include: the first network element obtaining a first prompt word based on the first interface vector information and the first information; the first network element sending a first request including the first prompt word to the multimodal big data model; and the first network element receiving first response information of the service request from the multimodal big data model. Correspondingly, the multimodal big data model receives the first request from the first network element; and the multimodal big data model sends the first response information of the service request to the first network element.

[0144] The first request is used to obtain the first response information for the business request. The first prompt can include prompts corresponding to the business request and prompts converted from the first interface vector information, such as prompts composed of interface parameters corresponding to the first document vector information in the first interface vector information, or prompts corresponding to the first example vector information in the first interface vector information. It can be understood that obtaining the first response information for the business request through a multimodal large model can improve the efficiency and accuracy of responding to business requests.

[0145] For example, please refer to Figure 4A or Figure 4B, which are schematic diagrams of a first prompt word provided in an embodiment of this application. As shown in Figure 4A, the first prompt word may include a task prompt word for a business request, input parameters of a first interface, an interface example, and a business request, etc. The input parameters of the first interface can be understood as prompt words for first document vector information, and the interface example can be understood as prompt words for first example vector information. The business request can be understood as a prompt word for first information conversion, as illustrated in the aforementioned example. The task prompt word for the business request can be understood as the main task of the business request.

[0146] In Figure 4A, the action indicates the first service, such as sending a message (e.g., SendSms). The version indicates the version number of the non-declarative API, which in this example is indicated by a time format like 2021-01-11. The host can be the network address of the first interface for the SMS service in the first service platform, such as sms.XXXcloudapi.com. The content type (e.g., Content-Type) indicates the description of the SMS content, such as applicant or JavaScript key-value pair data (JSON). The phone number set (e.g., PhoneNumberSet or PhoneNumbers) indicates the example phone number, such as +86AAAAAAAAAAA, +86BBBBBBBBBBB. The application identifier for sending the SMS (e.g., SmsSdkAppId) indicates the interface for sending the SMS. The signature name (SignName or signature) indicates the subject of the SMS, such as: First Service Platform. Template identifiers (such as templateId or templateCode), such as 1110, are used to indicate the template. The list of template variable values ​​(such as TemplateParamSet, TemplateParam, etc.) is used to indicate the SMS content.

[0147] In Figure 4B, the input parameters include content type and authorization (e.g., authorization). Authorization is used to indicate the authentication information for the first service. Interface examples may include the actual URL, actual port, domain name, content length (e.g., content-length), date (e.g., date), authorization, received information (e.g., the character corresponding to accept), content type, sent information (e.g., the character corresponding to form), etc.

[0148] It should be noted that the prompt words in Figure 4A or Figure 4B are merely examples. In reality, the first prompt word can include other or more prompt words, such as additional input parameters. The example of the first interface in Figure 4A sends an SMS message via Hypertext Transfer Protocol version 1.1 (HTTP). In practice, other network protocols or other versions of HTTP can be used; this is not limited to here.

[0149] It is understood that after sending the first information containing the first prompt word to the multimodal large model, the multimodal large model can first obtain the business request, and then obtain the response information of the business request, in order to obtain the first conversion information of the non-declarative API into the first interface. For example, please refer to Figure 5A or Figure 5B, which are schematic diagrams of a first conversion information provided by an embodiment of this application. The first conversion information shown in Figure 5A can be understood as the response information in Figure 4A, and the first conversion information shown in Figure 5B can be understood as the response information in Figure 4B.

[0150] As shown in Figure 5A or Figure 5B, the first conversion information may include the input parameters of the first interface and the output parameters of the non-declarative API. The input parameters of the first interface can be described with reference to Figure 4A or Figure 4B, and are not limited here. In Figure 5A, the application identifier for sending SMS messages in the output parameters of the non-declarative API is the same as in Figure 4A. The phone number set, signature name, template representation, and template variable value list in the output parameters of the non-declarative API have been converted according to business requirements. In Figure 5B, the content of sending SMS messages in the output parameters of the non-declarative API is modified to the content corresponding to the business requirements in Figure 5A. Thus, the non-declarative API can be converted into the first interface. The difference is that the example of the first interface can send SMS messages to multiple phone numbers, while the first interface after the non-declarative API conversion can only send SMS messages to a single phone number.

[0151] It should be noted that the business requirements shown in Figures 4A and 4B are merely examples. In reality, other business requirements may also be included. For instance, the business requirement could be sending an SMS message to a number within a number range. The example provided by the first service platform for the SMS service focuses on sending an SMS to a single number. If the number range includes 10 numbers, conversion information for each of the 10 numbers can be generated separately, allowing the first service platform to send an SMS message individually to one of the 10 numbers.

[0152] In some feasible examples, the first response information also includes the first billing information of the business request, and the method further includes: the first network element determining the first billing information based on the account opening information of the first service platform.

[0153] For example, the first service is SMS service, and the first billing information for the service request can be the fee information that needs to be paid through the first interface. It is understood that, when converting a non-declarative API into the first interface, the first billing information for the service request can also be determined based on account information, such as tariff information. Thus, when the first service platform responds to the service request, it can deduct the fees from the account corresponding to the service requesting device according to the billing information, or prompt the service requesting device to complete the payment, etc. This application does not limit the payment method.

[0154] As can be understood, in the method shown in Figure 3, after the first network element receives the first information, it can obtain the first interface vector information from the second network element. Then, based on the first interface vector information and the first information, it calls the multimodal large model to obtain the first response information for the business request. This first response information includes the first transformation information for converting a non-declarative API into a first interface. In this way, a non-declarative API can be converted into a declarative API, thereby solving the problem of the interface needing to be declared in advance and improving development efficiency.

[0155] In some feasible examples, the method may further include: the first network element sending a first response message to the first service platform; the first network element receiving an acknowledgment response or an error response from the first service platform in response to the first response message. Correspondingly, the first service platform receives the first response message from the first network element; the first service platform sends a first acknowledgment response or a first error response to the first network element in response to the first response message.

[0156] The first confirmation response, such as a 200 OK response, indicates that the first service platform can successfully call the first interface corresponding to the first response information, thus fulfilling the business request. The first error response, such as a 500 error, indicates that the first service platform failed to call the first interface corresponding to the first response information, and the first service platform cannot provide the first service to the requesting device. Optionally, the first error response can be an error response from the first service platform or an error response from the first service. That is, when the first service platform cannot respond or the first service of the first service platform cannot respond, the first service platform can send a first error response to the first network element based on the first response information. The first confirmation response or the first error response here can be based on the first conversion information in the first response information.

[0157] It is understandable that, if the first service platform can respond to the first response information, it can call the first interface to fulfill the business request and send a first confirmation response to the first network element, instructing the first interface of the first service platform to provide the service for the first business request. If the first service platform cannot respond to the first response information, it can send a first error response to the first network element, indicating that the first service platform cannot respond to the business request.

[0158] In some possible examples, the first network element can also be used to send a second confirmation response to the service request platform for the first information upon receiving the first confirmation response. The second confirmation response, such as a 200 OK response, indicates that the service request in the first information has been successfully fulfilled. For example, if the first service requested in the first information is an SMS service, and the first network element receives the first confirmation response, it can send a second confirmation response to the service request device to indicate that the SMS service has been successfully fulfilled, i.e., the SMS was successfully sent.

[0159] If the first service platform cannot respond to the first response information, it can send a first error response to the first network element and may also stop processing the business request. Alternatively, the business request can be processed through another service platform. For example, in some feasible examples, the method may further include: upon receiving the first error response from the first service platform regarding the first response information, the first network element obtains second interface vector information from the second network element; the first network element, based on the second interface vector information and the first information, calls a multimodal large model to obtain the second response information of the business request, the second response information including second transformation information of converting a non-declarative API into a second interface.

[0160] The second interface vector information refers to the interface vector information of the second interface of the first service provided by the second service platform. The second interface is a declarative API. The second interface vector information includes the second document vector information and the second example vector information of the second interface. Specifically, the second document vector information is the vector information of the second document information of the second interface, and the second example vector information is the vector information of the second example information of the second interface. The description of the second interface vector information can be referenced from that of the first interface vector information and will not be repeated here.

[0161] Optionally, the first network element obtains the second interface vector information from the second network element, including: the first network element sending a second acquisition request to the second network element; and the first network element receiving the second interface vector information. Correspondingly, the second network element receives the second acquisition request; and the second network element sends the second interface vector information to the first network element. The second acquisition request is used to obtain the second interface vector information.

[0162] It is understandable that upon receiving a first error response from the first service platform in response to the first response information, the first network element can obtain the second interface vector information. This second interface vector information is the vector information of the second interface of the second service platform for the first service. Thus, based on the second interface vector information, the first network element can convert the non-declarative API targeting the business request in the first information into the second interface, so that the response to the business request can be realized through the second interface of the second service platform. This eliminates the need for pre-definition of non-declarative APIs, thereby improving development efficiency.

[0163] Optionally, the second response information may also include second billing information for the business request. The first network element may also determine the second billing information for the business request based on the account opening information of the second service platform.

[0164] The fees in the second billing information may be the same as or different from the fees in the first billing information. The fees in the second billing information are related to the tariff information in the account opening information of the second service platform, and the fees in the first billing information are related to the tariff information in the account opening information of the first service platform.

[0165] It should be noted that in the above example, when the first network element receives an error response from the first service platform regarding the first response information, it obtains the second interface vector information from the second network element. In reality, the step of the first network element obtaining the second interface vector information from the second network element can be performed regardless of whether a response from the first service platform regarding the first response information has been received. That is, even if the first network element receives an acknowledgment response from the first service platform regarding the first response information, it can still obtain the second interface vector information from the second network element. Alternatively, it can obtain the second interface vector information from the second network element simultaneously with or before obtaining the first interface vector information from the second network element, etc., without further limitation.

[0166] Please refer to Figure 6, which is an interactive schematic diagram of another communication method provided in an embodiment of this application. Figure 6 can be understood as the method after Figure 3, such as after step S303. This method includes, but is not limited to, the following steps S601 to S605, wherein:

[0167] S601: The first network element sends the first response information to the first service platform.

[0168] Correspondingly, the first service platform receives the first response information from the first network element.

[0169] S602: The first network element receives the first confirmation response or the first error response from the first service platform in response to the first response information.

[0170] Accordingly, the first service platform sends a first confirmation response or a first error response to the first network element in response to the first response information.

[0171] S603: Upon receiving the first confirmation response, the first network element sends a second confirmation response to the service request platform regarding the first information.

[0172] Correspondingly, the business request platform receives a second confirmation response from the first network element regarding the first information.

[0173] S604: Upon receiving a first error response, the first network element obtains the second interface vector information from the second network element.

[0174] S605: The first network element calls the multimodal large model to obtain the second response information of the business request based on the second interface vector information and the first information. The second response information includes the second transformation information of the non-declarative API being converted into the second interface.

[0175] S606: The first network element sends a second response message to the second service platform.

[0176] Correspondingly, the second service platform receives the second response information from the first network element.

[0177] S607: The first network element receives the first confirmation response or the first error response from the second service platform in response to the second response information.

[0178] Correspondingly, the second service platform sends a first confirmation response or a first error response to the first network element in response to the second response information.

[0179] It can be understood that the first confirmation response or the first error response in step S607 is for the second response information, specifically for the second conversion information in the second response information. The first confirmation response or the first error response in step S602 is for the first response information. Therefore, when the first network element receives the first confirmation response from the second service platform for the second response information, it can send a second confirmation response for the first information to the service requesting device, as shown in step S603. When the first error response from the first service platform for the first response information is received, the service request may not be processed. Alternatively, as shown in step S604, the service request can be processed through another second service platform. That is, the second interface vector information obtained by the first network element from the second network element is the interface vector information of the second interface of the first service provided by another second service platform. Then, based on the second interface vector information and the first information, the multimodal big model is called to re-obtain the second response information of the service request.

[0180] The methods for steps S601 to S605 can refer to the example above. Thus, if the first service platform, capable of providing the first service, fails to respond, executing the business request via a non-declarative API through the second service platform can improve the success rate of business request execution.

[0181] It should be noted that this application addresses the execution of non-declarative API business requests through a second service platform in the event of a failure in the response from the first service platform. In fact, non-declarative API business requests can also be executed through the second service platform even before the first service platform fails. That is, the first network element can first obtain the first interface vector information from the first service platform and the second interface vector information from the second service platform. Then, based on the first interface vector information and the first information, it can invoke a multimodal large model to obtain the first response information, and based on the second interface vector information and the second information, it can invoke the multimodal large model to obtain the second response information. Finally, it sends the first response information to the first service platform and the second response information to the second service platform. In this way, business requests can be responded to through at least two service platforms. Furthermore, after one service platform sends a first confirmation response to the first network element, the first network element can send an instruction to the other service platform to indicate that it will no longer respond to the business request.

[0182] Alternatively, based on the first and second interface vector information, it can be determined whether the first or second service platform will execute the business request, and then the response information corresponding to the business request of the service platform that was determined to execute the business request can be sent to that service platform. Alternatively, it can be determined whether the first or second service platform will execute the business request based on the first and second response information, for example, the first billing information determined from the account opening information of the first service platform and the second billing information from the account opening information of the second service platform, and then the response information corresponding to the business request of the service platform that was determined to execute the business request can be sent to that service platform.

[0183] The methods of the embodiments of this application have been described in detail above, and the apparatus of the embodiments of this application is provided below.

[0184] Please refer to Figure 7, which is a schematic diagram of a communication device provided in an embodiment of this application. The communication device may include a transceiver unit 701 and a processing unit 702. The transceiver unit 701 may be a device that has signal input (receiving) or output (transmitting) capabilities, used for signal transmission with other network devices or other components within the device.

[0185] The processing unit 702 can be a device with processing capabilities, and may include one or more processors. The processor can be a general-purpose processor or a dedicated processor. The processor can be a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control the device (e.g., a host node, relay node, or chip), execute software programs, and process data from the software programs.

[0186] The communication device may include a first network element, a second network element, or a device thereof.

[0187] When the communication device is the first network element, it includes:

[0188] The transceiver unit 701 is used to receive first information, which is used to indicate the business requirements of the non-declarative application programming interface (API) of the first service.

[0189] The transceiver unit 701 is further configured to obtain first interface vector information from the second network element. The first interface vector information is the interface vector information of the first interface of the first service provided by the first service platform. The first interface is a declarative API.

[0190] The processing unit 702 is used to call the multimodal large model to obtain the first response information of the business request based on the first interface vector information and the first information. The first response information includes the first conversion information of the non-declarative API to the first interface.

[0191] In some feasible examples, the processing unit 702 is used to obtain a first prompt word based on the first interface vector information and the first information;

[0192] The transceiver unit 701 is further configured to send a first request including the first prompt word to the multimodal large model, wherein the first request is used to obtain first response information of the business request;

[0193] The transceiver unit 701 is also used to receive the first response information from the multimodal large model.

[0194] In some feasible examples, the processing unit 702 is also used to obtain the first interface vector information based on the account opening information and resource configuration information of the first service platform;

[0195] The transceiver unit 701 is further configured to send a storage request for the first interface vector information to the second network element, the storage request being used to instruct the storage of the first interface vector information.

[0196] In some feasible examples, the first response information may also include first billing information of the business request, and the processing unit may further be used to determine the first billing information based on the account opening information of the first service platform.

[0197] In some feasible examples, the first interface vector information includes the first document vector information and the first example vector information of the first interface; the first transformation information is obtained by the multimodal large model transforming the business request based on the first document information and the first example information;

[0198] Wherein, the vector information of the first document information is the first document vector information, and the vector information of the first example information is the first example vector information.

[0199] In some feasible examples, the transceiver unit 701 is also used to send the first response information to the first service platform;

[0200] The transceiver unit 701 is also configured to receive a first confirmation response or a first error response from the first service platform in response to the first response information.

[0201] In some feasible examples, the transceiver unit 701 is further configured to send a second confirmation response to the service requesting device in response to the first confirmation response upon receiving the first confirmation response.

[0202] In some feasible examples, the transceiver unit 701 is further configured to obtain second interface vector information from the second network element upon receiving the first error response. The second interface vector information is the interface vector information of the second interface of the first service provided by the second service platform, and the second interface is a declarative API.

[0203] The processing unit 702 is further configured to call the multimodal large model to obtain the second response information of the business request based on the second interface vector information and the first information, wherein the second response information includes the second conversion information of the non-declarative API being converted into the second interface.

[0204] When the communication device is a second network element, it includes:

[0205] Storage unit 703 is used to store first interface vector information, which is the interface vector information of the first interface of the first service provided by the first service platform, and the first interface is a declarative application programming interface (API).

[0206] The transceiver unit 701 is used to receive a first acquisition request from a first network element, wherein the first acquisition request is used to indicate the acquisition of first interface vector information;

[0207] The transceiver unit 701 is also used to send the first interface vector information to the first network element.

[0208] In some feasible examples, the transceiver unit 701 is also configured to receive a storage request from the first network element, the storage request being used to instruct the storage of the first interface vector information.

[0209] In some feasible examples, storage unit 703 is also used to store second interface vector information, which is the interface vector information of the second interface of the first service provided by the second service platform, and the second interface is a declarative API;

[0210] The transceiver unit 701 is also configured to receive a second acquisition request from the first network element, wherein the second acquisition request is used to indicate the acquisition of the second interface vector information;

[0211] The transceiver unit 701 is also used to send the second interface vector information to the first network element.

[0212] It should be noted that the implementation of each unit can also correspond to the description of any method embodiment in Figures 2, 3, or 6. The communication device can also be a service request device, a multimodal large model, a first service platform, or a second service platform, and one of the communication devices can include the units corresponding to the relevant steps in Figures 2, 3, or 6, which are not elaborated here.

[0213] Please refer to Figure 8, which is a schematic diagram of another communication device provided in an embodiment of this application. This communication device may be a first network element, a second network element, a service request device, or a multimodal large-scale model, or a device thereof, used to implement the method described in the method embodiments.

[0214] As shown in Figure 8, the communication device may include a processor 111 and a storage medium 112. The processor 111 may also be called a processing unit, which can implement certain control functions. The storage medium 112 may also be called a storage unit or a memory. Instructions 114 are stored on the storage medium 112. The instructions 114 can be executed on the processor 111, causing the communication device to perform any of the methods described in Figures 2, 3, or 6 of the embodiments of this application.

[0215] Optionally, the processor 111 may include instructions 113, which can be executed on the processor 111 to cause the communication device to perform any of the methods described in FIG2, FIG3 or FIG6 in the embodiments of this application.

[0216] The communication device described in the above embodiments may be a first device or a second device, but the scope of the device described in this application is not limited thereto. The communication device may be a standalone device or part of a larger device. For example, the communication device may be:

[0217] (1) An independent integrated circuit IC, or chip, or chip system or subsystem;

[0218] (2) A collection of one or more ICs, optionally, the collection of ICs may include a storage component for storing data and / or instructions;

[0219] (3) ASIC, such as modems;

[0220] (4) Modules that can be embedded in other devices.

[0221] This application also provides a computer-readable storage medium including instructions that, when executed by a processor, can implement the relevant steps in the communication method provided in the above-described method embodiments.

[0222] This application also provides a computer program product including instructions that, when executed by a computer (or a computer's processor), cause one or more steps of any of the aforementioned communication methods to be performed. If the constituent modules of the aforementioned devices are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.

[0223] This application provides a chip or chip system including at least one processor for calling and running instructions stored in a memory, causing a communication device with the chip installed to perform any of the above methods or to execute the steps of the processing unit 702.

[0224] This application embodiment also provides another chip, including a processor and a memory, wherein the processor is used to call and run instructions stored in the memory, causing a communication device with the chip installed to perform any of the above methods, or to perform the steps of the processing unit 702.

[0225] This application embodiment also provides another chip, including: an input interface, an output interface, and a processing circuit. The input interface, the output interface, and the processing circuit are connected via internal connection paths. The processing circuit is used to execute any of the methods described above. Optionally, the chip also includes a memory. The input interface, the output interface, the processor, and the memory are connected via internal connection paths. The processor is used to execute code in the memory. When the code is executed, the processor is used to execute any of the methods described above, or to execute the steps of processing unit 702.

[0226] This application also provides another chip system, including at least one processor and a communication interface. The communication interface and the at least one processor are interconnected via a line. The at least one processor is used to run a computer program or instructions to perform any of the methods described above, or to execute the steps of processing unit 702. This chip system may be composed of chips, or may include chips and other discrete devices.

[0227] This application also provides a communication system, which includes a terminal device and a network device. For a detailed description, please refer to Figures 2 and 3 or the methods shown.

[0228] The terminal device in this application embodiment can be a terminal as a final product, a component or module with terminal functions, or a communication chip (e.g., processor, baseband chip, or chip system) that can be applied in a terminal. The network device in this application embodiment can be a network device as a final product, a component or module with network device functions, or a communication chip (e.g., processor, baseband chip, or chip system) that can be applied in a network device.

[0229] It should be understood that the memory mentioned in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Non-volatile memory can be a hard disk drive (HDD), a solid-state drive (SSD), ROM, programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be RAM, which is used as an external cache. Memory is any other medium capable of carrying or storing desired program code having an instruction or data structure form and accessible by a computer, but is not limited thereto. The memory in the embodiments of this application can also be a circuit or any other device capable of implementing a storage function for storing program instructions and / or data.

[0230] It should also be understood that the processor mentioned in the embodiments of this application can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor, or any conventional processor, etc.

[0231] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, the memory (storage module) is integrated into the processor.

[0232] It should be noted that the memories described herein are intended to include, but are not limited to, these and any other suitable types of memories.

[0233] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments provided herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0234] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0235] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0236] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0237] The steps in the methods of this application can be adjusted, combined, or deleted according to actual needs. Each step in each embodiment can be partially performed (for example, the terminal device may not perform the steps performed by the terminal device in the above embodiments). The execution order of different steps can be changed. The embodiments described herein can be combined with other embodiments, different embodiments can be combined with each other, and different steps of different embodiments herein can be combined.

[0238] The modules / units in the device of this application embodiment can be merged, divided, and deleted according to actual needs.

[0239] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments.

[0240] In this application, it may refer to a communication protocol or specification, such as the 3GPP communication protocol.

[0241] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the embodiments of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0242] In the embodiments of this application, "including" can refer to a relationship of inclusion or an equality relationship. For example, A includes B, which could mean that A includes other content besides B, or that A and B are the same content.

[0243] In the description of this application, unless otherwise stated, " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B can mean A or B. "And / or" in this application is merely a description of the relationship between the related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. Furthermore, in the description of this application, unless otherwise stated, "multiple" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0244] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

Claims

1. A communication system, characterized by It includes the first network element, the second network element, and the service request device, wherein: The second network element is used to store the first interface vector information, which is the interface vector information of the first interface of the first service provided by the first service platform. The first interface is a declarative application programming interface (API). The first network element is used to receive first information from the service requesting device, and the first information is used to indicate the service request of the non-declarative API of the first service. The first network element is also used to obtain the first interface vector information from the second network element; The first network element is also used to call a multimodal large model to obtain the first response information of the business request based on the first interface vector information and the first information. The first response information includes the first conversion information of the non-declarative API to the first interface.

2. The system of claim 1, wherein, Based on the first interface vector information and the first information, the multimodal large model is invoked to obtain the first response information of the business request, including: Based on the first interface vector information and the first information, obtain the first prompt word; Send a first request, including the first prompt word, to the multimodal large model. The first request is used to obtain first response information for the business request. Receive the first response information from the multimodal large model.

3. The system according to claim 1 or 2, characterized in that, The first network element is also used to obtain the first interface vector information based on the account opening information and resource configuration information of the first service platform; The first network element is also used to send a storage request for the first interface vector information to the second network element, the storage request being used to instruct the storage of the first interface vector information.

4. The system of any one of claims 1 to 3, wherein, The first response information also includes the first billing information for the business request; The first network element is also used to determine the first billing information based on the account opening information of the first service platform.

5. The system according to any one of claims 1 to 4, characterized in that, The first interface vector information includes the first document vector information and the first example vector information of the first interface; The first conversion information is obtained by the multimodal large model converting the business request based on the first document information and the first example information; Wherein, the vector information of the first document information is the first document vector information, and the vector information of the first example information is the first example vector information.

6. The system according to any one of claims 1 to 5, characterized in that, The first network element is also used to send the first response information to the first service platform; The first network element is also used to receive a first confirmation response or a first error response from the first service platform in response to the first response information.

7. The system according to claim 6, characterized in that, The first network element is also configured to send a second confirmation response to the service requesting device in response to the first information upon receiving the first confirmation response.

8. The system according to claim 6, characterized in that, The second network element is used to store the second interface vector information, which is the interface vector information of the second interface of the first service provided by the second service platform. The second interface is a declarative API. The first network element is also configured to obtain the second interface vector information from the second network element upon receiving the first error response; The first network element is also used to call the multimodal big model to obtain the second response information of the business request based on the second interface vector information and the first information. The second response information includes the second conversion information of the non-declarative API being converted into the second interface.

9. A communication method characterized by comprising: Applied to the first network element, the method includes: The device receiving the service request receives first information, which is used to indicate the service request of the non-declarative application programming interface (API) of the first service. Obtain the first interface vector information from the second network element. The first interface vector information is the interface vector information of the first interface of the first service provided by the first service platform. The first interface is a declarative API. Based on the first interface vector information and the first information, a multimodal large model is invoked to obtain the first response information of the business request. The first response information includes the first conversion information of the non-declarative API to the first interface.

10. The method of claim 9, wherein, Based on the first interface vector information and the first information, the multimodal large model is invoked to obtain the first response information of the business request, including: Based on the first interface vector information and the first information, obtain the first prompt word; Send a first request, including the first prompt word, to the multimodal large model. The first request is used to obtain first response information for the business request. Receive the first response information from the multimodal large model.

11. The method according to claim 9 or 10, characterized in that, Also includes: Based on the account opening information and resource configuration information of the first service platform, obtain the first interface vector information; Send a storage request for the first interface vector information to the second network element, wherein the storage request is used to instruct the storage of the first interface vector information.

12. The method according to any one of claims 9 to 11, characterized in that, The first response information also includes first billing information for the service request, and the method further includes: The first billing information is determined based on the account opening information of the first service platform.

13. The method according to any one of claims 9 to 12, characterized in that, The first interface vector information includes the first document vector information and the first example vector information of the first interface; The first conversion information is obtained by the multimodal large model converting the business request based on the first document information and the first example information; Wherein, the vector information of the first document information is the first document vector information, and the vector information of the first example information is the first example vector information.

14. The method according to any one of claims 9 to 13, characterized in that, Also includes: Send the first response information to the first service platform; Receive the first confirmation response or the first error response from the first service platform in response to the first response information.

15. The method of claim 14, wherein, Also includes: Upon receiving the first confirmation response, a second confirmation response for the first information is sent to the service requesting device.

16. The method of claim 14, wherein, Also includes: Upon receiving the first error response, the second interface vector information is obtained from the second network element. The second interface vector information is the interface vector information of the second interface of the first service provided by the second service platform. The second interface is a declarative API. Based on the second interface vector information and the first information, the multimodal large model is invoked to obtain the second response information of the business request. The second response information includes the second conversion information of the non-declarative API being converted into the second interface.

17. A communications device, characterized by include: A transceiver unit is used to receive first information, which is used to indicate the business requirements of the non-declarative application programming interface (API) of the first service. The transceiver unit is further configured to obtain first interface vector information from the second network element, wherein the first interface vector information is the interface vector information of the first interface of the first service provided by the first service platform, and the first interface is a declarative API; The processing unit is configured to invoke a multimodal large model to obtain first response information of the business request based on the first interface vector information and the first information. The first response information includes first conversion information of the non-declarative API being converted into the first interface.

18. The apparatus according to claim 17, characterized in that, The processing unit is used to obtain a first prompt word based on the first interface vector information and the first information; The transceiver unit is also configured to send a first request including the first prompt word to the multimodal large model, the first request being used to obtain first response information of the business request; The transceiver unit is also used to receive the first response information from the multimodal large model.

19. The apparatus according to claim 17 or 18, characterized in that, The processing unit is further configured to obtain the first interface vector information based on the account opening information and resource configuration information of the first service platform; The transceiver unit is further configured to send a storage request for the first interface vector information to the second network element, the storage request being used to instruct the storage of the first interface vector information.

20. The apparatus of any one of claims 17-19, wherein, The first response information also includes the first billing information of the business request, and the processing unit is further configured to determine the first billing information based on the account opening information of the first service platform.

21. The apparatus according to any one of claims 17 to 20, characterized in that, The first interface vector information includes the first document vector information and the first example vector information of the first interface; The first conversion information is obtained by the multimodal large model converting the business request based on the first document information and the first example information; Wherein, the vector information of the first document information is the first document vector information, and the vector information of the first example information is the first example vector information.

22. The apparatus according to any one of claims 17 to 21, characterized in that, The transceiver unit is also used to send the first response information to the first service platform; The transceiver unit is also configured to receive a first confirmation response or a first error response from the first service platform in response to the first response information.

23. The apparatus according to claim 22, characterized in that, The transceiver unit is further configured to send a second confirmation response to the first information to the service requesting device upon receiving the first confirmation response.

24. The apparatus according to claim 22, characterized in that, The transceiver unit is further configured to, upon receiving the first error response, obtain second interface vector information from the second network element, wherein the second interface vector information is the interface vector information of the second interface of the first service provided by the second service platform, and the second interface is a declarative API; The processing unit is further configured to call the multimodal large model to obtain the second response information of the business request based on the second interface vector information and the first information. The second response information includes the second conversion information of the non-declarative API being converted into the second interface.

25. A communication device, characterized in that, The communication device includes a processor and a storage medium storing instructions that, when executed by the processor, cause the method according to any one of claims 9 to 16 to be performed.

26. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes instructions that, when executed, cause the method of any one of claims 9 to 16 to be implemented.

27. A chip or chip system, characterized in that, Includes a processor for retrieving and executing instructions stored in a memory, causing a communication device with a chip mounted to perform the method as described in any one of claims 9 to 16.

Images