Terminal AI capability sharing method, device, system and network equipment

Abstract

The invention relates to the technical field of artificial intelligence, and provides a terminal AI capability sharing method, device and system and network equipment. The method comprises the following steps: receiving a target AI capability corresponding to a non-AI capability terminal sent by a media plane network element; determining a target AI capability terminal corresponding to the target AI capability; calling the target AI capability terminal to process AI service data corresponding to the non-AI capability terminal; the calling operation is used for sharing the target AI capability corresponding to the target AI capability terminal with the non-AI capability terminal. According to the embodiment of the invention, the AI capability can be shared among different terminals, the different terminals cooperate to complete the same service, an operator network AI intelligent ecology is established, and the terminal capability and the service experience are enhanced.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, system and network device for sharing terminal AI capabilities. Background Technology

[0002] With the rapid development of edge AI (Artificial Intelligence) technology, mobile terminals have acquired a variety of AI capabilities, such as natural language processing, image processing, and speech-to-text synthesis.

[0003] However, existing operator communication networks exhibit significant differences in terminal capabilities, and terminals exist in isolation. Furthermore, some terminals within these networks lack AI capabilities. During capability negotiation, service providers typically utilize terminals with lower capabilities, leading to substantial differences in the performance of the same service across terminals with varying capabilities, and resulting in low utilization of terminal AI capabilities. Summary of the Invention

[0004] This application provides a terminal AI capability sharing method, apparatus, system, and network device to solve the technical problem in the prior art that the same service has significantly different performance on terminals with different capabilities, and the utilization rate of terminal AI capabilities is low.

[0005] In a first aspect, embodiments of this application provide a terminal AI capability sharing method, applied to AI service network elements, including the following steps.

[0006] The target AI capability corresponding to the non-AI capability terminal received by the media plane network element; Identify the target AI capability terminal corresponding to the target AI capability; The target AI-capable terminal is invoked to process the AI ​​business data corresponding to the non-AI-capable terminal; the invocation operation is used to share the target AI capability corresponding to the target AI-capable terminal with the non-AI-capable terminal.

[0007] In one embodiment, according to the terminal AI capability sharing method provided in this application, determining the target AI capability terminal corresponding to the target AI capability includes: Identify candidate AI capability terminals that possess the target AI capability from among the registered AI capability terminals; Based on the overall device score corresponding to the target AI capability among the candidate AI capability terminals, the target AI capability terminal corresponding to the target AI capability is determined.

[0008] In one embodiment, according to the terminal AI capability sharing method provided in this application, before receiving the target AI capability corresponding to a non-AI capability terminal sent by a media plane network element, the method further includes: The AI ​​capability corresponding to at least one AI capability terminal received from the VoLTE network element; Determine the overall device score for the AI ​​capabilities corresponding to each of the aforementioned AI capability terminals.

[0009] In one embodiment, according to the terminal AI capability sharing method provided in this application, determining the device comprehensive score of the AI ​​capability corresponding to each AI capability terminal includes: Based on the load indicators, performance indicators, and historical execution statistics of each AI capability terminal, the overall device score of the AI ​​capability corresponding to each AI capability terminal is determined.

[0010] In one embodiment, according to the terminal AI capability sharing method provided in this application, the step of calling the target AI capability terminal to process the AI ​​business data corresponding to the non-AI capability terminal includes: Receive AI service data corresponding to non-AI capability terminals sent by the media plane network element; The AI ​​service data is sent to the target AI-capable terminal, or the target address corresponding to the target AI-capable terminal is sent to the media plane network element; the target address is used to instruct the media plane network element to send the AI ​​service data to the target AI-capable terminal.

[0011] Secondly, embodiments of this application provide a terminal AI capability sharing method, applied to media plane network elements, including the following steps.

[0012] Receive the target AI capabilities required by non-AI capable terminals; The target AI capability is sent to the AI ​​service network element, and the target AI capability is used to instruct the AI ​​service network element to determine the target AI capability terminal corresponding to the target AI capability; the target AI capability terminal is invoked to process the AI ​​service data corresponding to the non-AI capability terminal; the invocation operation is used to share the target AI capability corresponding to the target AI capability terminal with the non-AI capability terminal.

[0013] In one embodiment, a terminal AI capability sharing method according to an embodiment of this application further includes, before receiving the target AI capability required by a non-AI capability terminal: Based on the service type initiated by the non-AI capability terminal, determine the AI ​​capability recommendation data corresponding to the non-AI capability terminal; The AI ​​capability recommendation data is sent to the non-AI capability terminal; the AI ​​capability recommendation data includes at least the target AI capability.

[0014] In one embodiment, a terminal AI capability sharing method provided according to an embodiment of this application further includes: Receive AI service data sent by the non-AI capable terminal; Send the AI ​​service data to the AI ​​service network element; Upon receiving the target address corresponding to the target AI capability terminal sent by the AI ​​service network element, the AI ​​service data is sent to the target AI capability terminal based on the target address.

[0015] Thirdly, embodiments of this application provide a terminal AI capability sharing method applied to VoLTE network elements, including the following steps.

[0016] Receive registration signaling from at least one AI-capable terminal; The registration signaling is parsed to obtain the AI ​​capability field; the AI ​​capability field is used to characterize the AI ​​capability corresponding to each AI capability terminal. Based on the AI ​​capability fields, the AI ​​capabilities corresponding to each AI capability terminal are shared.

[0017] In one embodiment, a terminal AI capability sharing method according to an embodiment of this application, wherein sharing the AI ​​capabilities corresponding to each AI capability terminal based on the AI ​​capability field includes: Extract the AI ​​capabilities corresponding to each AI capability terminal from the AI ​​capability fields; Send the AI ​​capabilities corresponding to each AI capability terminal to the AI ​​service network element.

[0018] Fourthly, embodiments of this application provide a terminal AI capability sharing device, including the following modules.

[0019] The first receiving module is used to receive the target AI capability corresponding to the non-AI capability terminal sent by the media plane network element; The first determining module is used to determine the target AI capability terminal corresponding to the target AI capability; The invocation module is used to invoke the target AI capability terminal to process the AI ​​business data corresponding to the non-AI capability terminal; the invocation operation is used to share the target AI capability corresponding to the target AI capability terminal with the non-AI capability terminal.

[0020] Fifthly, embodiments of this application provide a terminal AI capability sharing device, including the following modules.

[0021] The second receiving module is used to receive the target AI capabilities required by non-AI capability terminals. The first sending module is used to send the target AI capability to the AI ​​service network element, wherein the target AI capability is used to instruct the AI ​​service network element to determine the target AI capability terminal corresponding to the target AI capability; to call the target AI capability terminal to process the AI ​​service data corresponding to the non-AI capability terminal; and to call the operation to share the target AI capability corresponding to the target AI capability terminal with the non-AI capability terminal.

[0022] Sixthly, embodiments of this application provide a terminal AI capability sharing device, including the following modules.

[0023] The third receiving module is used to receive registration signaling sent by at least one AI-capable terminal; The parsing module is used to parse the registration signaling to obtain the AI ​​capability field; the AI ​​capability field is used to characterize the AI ​​capability corresponding to each AI capability terminal; The sharing module is used to share the AI ​​capabilities corresponding to each AI capability terminal based on the AI ​​capability field.

[0024] Seventhly, embodiments of this application provide a terminal AI capability sharing system, including AI service network elements, media plane network elements, and VoLTE network elements, wherein: The AI ​​service network element is used to execute the terminal AI capability sharing method described in the first aspect; The media plane network element is used to execute the terminal AI capability sharing method described in the second aspect; The VoLTE network element is used to execute the terminal AI capability sharing method described in the third aspect.

[0025] Eighthly, embodiments of this application provide a network device, including a memory, a transceiver, and a processor; A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and executing the terminal AI capability sharing method described in the first, second, or third aspect.

[0026] Ninthly, embodiments of this application provide a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the terminal AI capability sharing method described in the first, second, or third aspects.

[0027] In a tenth aspect, embodiments of this application also provide a computer program product, including a computer program that, when executed by a processor, implements the terminal AI capability sharing method described in the first, second, or third aspects.

[0028] The terminal AI capability sharing method, apparatus, system, and network equipment provided in this application embodiment receive the target AI capability corresponding to a non-AI capability terminal sent by a media plane network element, determine the target AI capability terminal with the target AI capability, and call the target AI capability terminal to process the AI ​​service data that the non-AI capability terminal needs to process. In this application embodiment, by sharing the target AI capability corresponding to the target AI capability terminal with the non-AI capability terminal, the non-AI capability terminal without AI capability can use the target AI capability provided by the target AI capability terminal, realizing the sharing of AI capabilities among different terminals, and enabling different terminals to cooperate in completing the same service, establishing an AI intelligent ecosystem for operator networks, and enhancing terminal capabilities and service experience. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is one of the flowcharts illustrating the terminal AI capability sharing method provided in the embodiments of this application.

[0031] Figure 2 This is the second flowchart of the terminal AI capability sharing method provided in the embodiments of this application.

[0032] Figure 3 This is the third flowchart of the terminal AI capability sharing method provided in the embodiments of this application.

[0033] Figure 4 This is one of the structural schematic diagrams of the terminal AI capability sharing device provided in the embodiments of this application.

[0034] Figure 5 This is the second structural schematic diagram of the terminal AI capability sharing device provided in the embodiments of this application.

[0035] Figure 6 This is the third schematic diagram of the terminal AI capability sharing device provided in the embodiments of this application.

[0036] Figure 7 This is a schematic diagram of the signaling interaction of the terminal AI capability sharing system provided in the embodiments of this application.

[0037] Figure 8 This is a schematic diagram of the network device provided in the embodiments of this application. Detailed Implementation

[0038] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0039] To address the technical problem in existing technologies where the same service exhibits significantly different performance on terminals with varying capabilities, and where the utilization rate of terminal AI capabilities is low, this application provides a terminal AI capability sharing method applied to an AI service network element. This AI service network element is a service platform within the operator's network that manages terminal AI capabilities, responsible for the registration, scheduling, and resource coordination of terminal AI capabilities.

[0040] Figure 1 This is one of the flowcharts illustrating the terminal AI capability sharing method provided in this application embodiment, such as... Figure 1 As shown, the method includes steps 110 to 130.

[0041] Step 110: Receive the target AI capability corresponding to the non-AI capability terminal sent by the media plane network element.

[0042] The media plane network element is an end-to-end data transmission channel controller established based on IMS data channel (DC) technology, and the media plane network element is used to transmit media data, which may include video data, audio data, or text data, etc.

[0043] A non-AI-capable terminal is a terminal that is connected to the operator's network but does not have AI capabilities. This operator's network includes at least one non-AI-capable terminal and at least one AI-capable terminal, which is a terminal connected to the operator's network and possesses AI capabilities.

[0044] In this embodiment of the application, when a non-AI capability terminal needs to use AI capabilities to process corresponding AI service data, the AI ​​service network element can receive the target AI capabilities required by the non-AI capability terminal sent by the media plane network element after the non-AI capability terminal establishes a call with other terminals (for example, the non-AI capability terminal initiates a new 5G call service). This facilitates the AI ​​service network element to schedule a suitable AI capability terminal to provide AI capabilities to the non-AI capability terminal based on the target AI capabilities.

[0045] It should be noted that the target AI capability is transmitted from the AI ​​service network element to the media plane network element through a CDC channel established between the non-AI capability terminal and other terminals after a call is made. Furthermore, the other terminals communicating with the non-AI capability terminal can be either AI capability terminals or non-AI capability terminals; this application embodiment does not limit this.

[0046] Step 120: Determine the target AI capability terminal corresponding to the target AI capability.

[0047] Specifically, after determining the target AI capability, the AI ​​service network element identifies the target AI capability terminal that matches the target AI capability from all AI capability terminals accessing the operator's network, thereby enabling the scheduling of the AI ​​capability.

[0048] Step 130: Call the target AI capability terminal to process the AI ​​business data corresponding to the non-AI capability terminal; the call operation is used to share the target AI capability corresponding to the target AI capability terminal with the non-AI capability terminal.

[0049] Specifically, after identifying the target AI-capable terminal, the AI ​​service network element can call the target AI capabilities of the target AI-capable terminal to process the AI ​​service data that the non-AI-capable terminal needs to process, so that the non-AI-capable terminal without AI capabilities can use the target AI capabilities of the target AI-capable terminal, thereby empowering the non-AI-capable terminal.

[0050] Optionally, the AI ​​business data may include image data, audio data, or text data that non-AI-capable terminals need to process.

[0051] The terminal AI capability sharing method provided in this application embodiment receives the target AI capability corresponding to a non-AI capability terminal sent by a media plane network element, determines the target AI capability terminal with the target AI capability, and calls the target AI capability terminal to process the AI ​​service data that the non-AI capability terminal needs to process. In this application embodiment, by sharing the target AI capability corresponding to the target AI capability terminal with the non-AI capability terminal, the non-AI capability terminal without AI capability can use the target AI capability provided by the target AI capability terminal, realizing the sharing of AI capabilities among different terminals, and enabling different terminals to cooperate to complete the same service, establishing an AI intelligent ecosystem for operator networks, and improving the utilization rate of terminal AI capabilities and service experience.

[0052] In one embodiment, determining the target AI capability terminal corresponding to the target AI capability includes: Identify candidate AI capability terminals that possess the target AI capability from among the registered AI capability terminals; Based on the overall device score corresponding to the target AI capability among the candidate AI capability terminals, the target AI capability terminal corresponding to the target AI capability is determined.

[0053] Registered AI-capable terminals can be terminals connected to an operator's network that possess AI capabilities and notify AI service network elements that they can share at least one AI capability. The types of AI capabilities possessed by registered AI-capable terminals can include image processing, natural language processing, and translation capabilities. Specifically, image processing subcategories can include image removal and image enhancement, natural language processing subcategories can include text optimization, intelligent reply, and semantic recognition, and translation capabilities can include the recognition and conversion of different languages. This application does not limit these specific capabilities.

[0054] In this embodiment, after determining the target AI capability, candidate AI capability terminals with the target AI capability can be selected from the registered AI capability terminals. Then, the overall device score for each candidate AI capability terminal in evaluating the target AI capability is obtained; the higher the overall device score, the better the performance of the target AI capability of the candidate AI capability terminal. All overall device scores are sorted in descending order, and the candidate AI capability terminal with the highest device score in the sorting results is determined as the target AI capability terminal.

[0055] It should be noted that the target AI capability is a subclass of at least one type of AI capability; that is, the target AI capability can include at least one subclass of AI capabilities. For example, the target AI capability could be image removal in image processing. Or, it could include text optimization and intelligent reply in natural language processing. Or, it could include language conversion in translation capabilities, and text optimization in natural language processing.

[0056] Furthermore, when the target AI capability includes at least two AI capability subcategories, the AI ​​service network element can determine the target AI capability terminal corresponding to each AI capability subcategory. The target AI capability terminals corresponding to all AI capability subcategories can be the same or different. When the target AI capability terminals corresponding to all AI capability subcategories are different, multiple target AI capability terminals can collaboratively process the AI ​​service data that non-AI capability terminals need to process, thereby enhancing terminal capabilities and service experience.

[0057] In one embodiment, before receiving the target AI capability corresponding to the non-AI capability terminal sent by the media plane network element, the method further includes: The AI ​​capability corresponding to at least one AI capability terminal received from the VoLTE network element; Determine the overall device score for the AI ​​capabilities corresponding to each of the aforementioned AI capability terminals.

[0058] Specifically, to facilitate the rational scheduling of AI capabilities by AI-capable terminals by AI service network elements, each AI-capable terminal can proactively send shareable AI capabilities to the VoLTE network element when idle, before receiving the target AI capabilities sent by the media plane network element. The VoLTE network element can then send these shareable AI capabilities to the AI ​​service network element. After receiving the shareable AI capabilities from each AI-capable terminal, the AI ​​service network element can store these capabilities in a database, thus registering each AI-capable terminal. Subsequently, each shareable AI capability of each AI-capable terminal can be evaluated to obtain a comprehensive device score for each AI capability, facilitating subsequent rational scheduling of these capabilities.

[0059] It should be noted that the overall device score corresponds one-to-one with the AI ​​capability. For example, when an AI-capable terminal can share two AI capabilities, the AI ​​service network element can evaluate each AI capability separately to obtain the overall device score corresponding to each of the two AI capabilities.

[0060] In one embodiment, determining the overall device score for the AI ​​capabilities of each AI-capable terminal includes: Based on the load indicators, performance indicators, and historical execution statistics of each AI capability terminal, the overall device score of the AI ​​capability corresponding to each AI capability terminal is determined.

[0061] Specifically, when evaluating various AI capabilities, the AI ​​service network element can obtain the load indicators corresponding to the AI ​​capability terminals, such as the current number of connections and the maximum number of connections, and use Equation (1) to calculate the load indicator score corresponding to the load indicator based on the load weight corresponding to the load indicator, the current number of connections, and the maximum number of connections. Equation (1) is: .

[0062] Among them, S load W represents the load metric score corresponding to the load metric. load This indicates the load weight corresponding to the load metric, curConnections represents the current number of connections, and maxConnections represents the maximum number of connections.

[0063] AI service network elements can also obtain the performance indicators of the AI ​​capabilities corresponding to the AI ​​capability terminals. Different types of AI capabilities result in different types and numbers of performance indicators. Using equation (2), the performance indicator score corresponding to the performance indicator is calculated based on the performance score, performance weight, indicator sub-weight, and maximum score of the different types of performance indicators corresponding to the AI ​​capability. Equation (2) is: .

[0064] Among them, S pre W represents the performance score corresponding to the performance indicator. pre P represents the performance weight corresponding to the performance metric. i This represents the performance score of the i-th performance metric corresponding to the AI ​​capability, where n represents the total number of different types of performance metrics corresponding to the AI ​​capability. For example, when the AI ​​capability is image processing, the corresponding performance metrics may include processing speed and resolution. In this case, n=2. A performance score of 100 points is given for processing a 4K image in 5 seconds. Based on this, a score standard corresponding to processing speed is defined, thus obtaining the performance score corresponding to processing speed. i MaxScore represents the sub-weights of different types of performance metrics. pre This represents the maximum score, i.e., the score when all performance metrics are at their maximum.

[0065] AI service network elements can also obtain historical execution statistics of the AI ​​capability terminal. Using equation (3), the historical execution statistics score corresponding to the historical execution statistics is calculated based on the historical score, historical sub-weight, historical maximum score, and historical execution statistics weight of the AI ​​capability terminal. Equation (3) is: .

[0066] Among them, S his W represents the historical execution statistics score corresponding to the historical execution statistics indicator. his P represents the weight of the historical execution statistics indicator corresponding to the historical execution statistics indicator. j W represents the historical score corresponding to the j-th historical execution of this AI capability. j MaxScore represents the historical sub-weight corresponding to the j-th historical execution of this AI capability. his This represents the highest historical score among m executions of the AI ​​capability, where m represents the total number of times the AI ​​capability has been executed by the terminal in history.

[0067] After determining the load index score, performance index score, and historical execution statistics index score corresponding to the AI ​​capability, the AI ​​service network element can calculate the sum of the load index score, performance index score, and historical execution statistics index score. This sum is the device comprehensive score of the AI ​​capability corresponding to the AI ​​capability terminal.

[0068] In this embodiment, AI capabilities are comprehensively evaluated using indicators from different dimensions to ensure the reliability and accuracy of AI capability assessment, thereby improving the reliability of AI capability scheduling and management.

[0069] In one embodiment, the step of invoking the target AI-capable terminal to process the AI ​​business data corresponding to the non-AI-capable terminal includes: Receive AI service data corresponding to non-AI capability terminals sent by the media plane network element; The AI ​​service data is sent to the target AI-capable terminal, or the target address corresponding to the target AI-capable terminal is sent to the media plane network element; the target address is used to instruct the media plane network element to send the AI ​​service data to the target AI-capable terminal.

[0070] Specifically, after identifying the target AI-capable terminal, the AI ​​service network element can receive AI service data that non-AI-capable terminals need to process, forwarded by the media plane network element.

[0071] Subsequently, the first method involves the AI ​​service network element directly forwarding the AI ​​service data to the target AI capability terminal, using the target AI capability terminal to process the AI ​​service data, and after the target AI capability terminal finishes processing, receiving the processed AI service data sent by the target AI capability terminal, and forwarding the processed AI service data to the media plane network element, so that the media plane network element sends the processed AI service data to the non-AI capability terminal for confirmation.

[0072] The second method involves the AI ​​service network element obtaining the target address of the target AI capability terminal during registration. The AI ​​service network element can then send this target address to the media plane network element, enabling the media plane network element to directly send the AI ​​service data that the non-AI capability terminal needs to process to the target AI capability terminal. After processing by the target AI capability terminal, it can directly send the processed AI service data to the media plane network element, which then sends the processed AI service data to the non-AI capability terminal for confirmation. The AI ​​service network element does not participate in the forwarding of the processed AI service data.

[0073] This application also provides a terminal AI capability sharing method, applied to media plane network elements. Figure 2 This is a second flowchart illustrating the terminal AI capability sharing method provided in this application embodiment, as shown below. Figure 2 As shown, the method includes steps 210 and 220.

[0074] Step 210: Receive the target AI capabilities required by the non-AI capability terminal.

[0075] Specifically, when a non-AI-capable terminal needs to process AI business data, the media plane network element can receive the target AI capabilities required by the non-AI-capable terminal through the created CDC channel after the non-AI-capable terminal establishes a call with other terminals.

[0076] Step 220: Send the target AI capability to the AI ​​service network element, wherein the target AI capability is used to instruct the AI ​​service network element to determine the target AI capability terminal corresponding to the target AI capability; invoke the target AI capability terminal to process the AI ​​service data corresponding to the non-AI capability terminal; the invocation operation is used to share the target AI capability corresponding to the target AI capability terminal with the non-AI capability terminal.

[0077] Specifically, after receiving the target AI capability, the media face network element can send the target AI capability to the AI ​​service network element, so that the AI ​​service network element can determine the target AI capability terminal from the registered AI capability terminals according to the target AI capability, and then call the target AI capability of the target AI capability terminal to process the AI ​​service data that the non-AI capability terminal needs to process, thereby realizing the transfer of the AI ​​capability of the target AI capability terminal to the non-AI capability terminal, that is, empowering the non-AI capability terminal.

[0078] The terminal AI capability sharing method provided in this application sends the target AI capabilities required by a non-AI capability terminal to an AI service network element, instructing the AI ​​service network element to determine a target AI capability terminal with the target AI capabilities, and calling the target AI capability terminal to process the AI ​​service data that the non-AI capability terminal needs to process. In this application embodiment, the target AI capabilities corresponding to the target AI capability terminal are shared with non-AI capability terminals, enabling non-AI capability terminals that do not possess AI capabilities to use the target AI capabilities provided by the target AI capability terminal. This achieves AI capability sharing among different terminals, allowing different terminals to collaborate to complete the same service, establishing an AI intelligent ecosystem for the operator network, and improving the utilization rate of terminal AI capabilities and service experience.

[0079] In one embodiment, before receiving the target AI capability required by the non-AI-capable terminal, the method further includes: Based on the service type initiated by the non-AI capability terminal, determine the AI ​​capability recommendation data corresponding to the non-AI capability terminal; The AI ​​capability recommendation data is sent to the non-AI capability terminal; the AI ​​capability recommendation data includes at least the target AI capability.

[0080] Specifically, when a non-AI-capable terminal initiates a new 5G call and a file transfer service, the media plane network element can determine the recommended AI capabilities for the non-AI-capable terminal based on the service type corresponding to the call. This recommended AI capability data includes, but is not limited to: all AI capability types compatible with the service type corresponding to the call, the AI ​​capability subtypes corresponding to each AI capability type, and the description and cost of each AI capability subtype. The service type corresponding to the call can include video calls or voice calls. This recommended AI capability data can be in JSON or XML structure.

[0081] For example, in a scenario where the business type is video call and the AI ​​capability recommendation data is in JSON structure, this AI capability recommendation data can include image elimination and image enhancement from image processing, as well as text optimization and smart answer from natural language processing. Specifically, this AI capability recommendation data is represented as follows: { "image-processing": [{ "sub_type": "image elimination", "description": "Helps you remove image backgrounds and unwanted objects", "cost": "1RMB", },{ "sub_type": "image enhancement", "description": "Helps you enhance images, such as by changing the viewpoint, etc." "cost": "1RMB", }], “text-processing”: [{ "sub_type": "Text optimization", "description": "Helps you optimize your language", "cost": "1RMB", },{ "sub_type": "smart answer", "description": "Automatically replies to your text messages", "cost": "1RMB", }] }

[0082] After determining the AI ​​capability recommendation data, the media interface network element can send the AI ​​capability recommendation data to non-AI capability terminals through the CDC channel, so that the non-AI capability terminals can determine the target AI capability from the AI ​​capability recommendation data.

[0083] In one embodiment, the method further includes: Receive AI service data sent by the non-AI capable terminal; Send the AI ​​service data to the AI ​​service network element; Upon receiving the target address corresponding to the target AI capability terminal sent by the AI ​​service network element, the AI ​​service data is sent to the target AI capability terminal based on the target address.

[0084] Specifically, media plane network elements can receive AI service data that non-AI capability terminals need to process through the AI ​​service data CDC channel and forward the AI ​​service data to the AI ​​service network element. If the media plane network element receives the target address corresponding to the target AI capability terminal sent by the AI ​​service network element, it indicates that the AI ​​service network element has not sent the AI ​​service data to the target AI capability terminal. In this case, the media plane network element can directly send the AI ​​service data to the target AI capability terminal corresponding to the target address. If the media plane network element does not receive the target address corresponding to the target AI capability terminal sent by the AI ​​service network element, it indicates that the AI ​​service network element has sent the AI ​​service data to the target AI capability terminal.

[0085] This application also provides a terminal AI capability sharing method, applied to VoLTE network elements. Figure 3 This is the third flowchart illustrating the terminal AI capability sharing method provided in this application embodiment, as follows: Figure 3 As shown, the method includes steps 310 to 330.

[0086] Step 310: Receive a registration signaling message sent by at least one AI-capable terminal.

[0087] Specifically, the VoLTE network element can receive registration signaling sent by at least one AI-capable terminal. This registration signaling is an improved SIP NOTIFY signaling, which adds AI capabilities that can be shared by each AI-capable terminal.

[0088] Step 320: Parse the registration signaling to obtain the AI ​​capability field; the AI ​​capability field is used to characterize the AI ​​capability corresponding to each AI capability terminal.

[0089] Specifically, after receiving the registration signaling corresponding to each AI-capable terminal, the VoLTE network element first parses the registration signaling to obtain the AI ​​capability field carried in the registration signaling. This AI capability field includes at least one type of AI capability that can be shared by each AI-capable terminal, and at least one AI capability subclass within that AI capability. When the AI ​​capability field includes at least two types of AI capabilities, different types of AI capabilities, as well as different AI capability subclasses under the same type of AI capability, can be concatenated using separators such as commas or semicolons.

[0090] For example, when the AI ​​capability field includes image removal and image enhancement in image processing, the AI ​​capability field (X-Capability-AIAgent) can be represented as: X-Capability-AIAgent=image-processing[image elimination;imageenhancement].

[0091] For example, when the AI ​​capability field includes image removal in image processing and text optimization in natural language processing, the AI ​​capability field (X-Capability-AIAgent) can be represented as: X-Capability-AIAgent=image-processing[image elimination], text-processing[Text optimization].

[0092] Step 330: Based on the AI ​​capability fields, share the AI ​​capabilities corresponding to each AI capability terminal.

[0093] Specifically, after parsing the AI ​​capability field, the VoLTE network element can register the AI ​​capabilities corresponding to each AI capability terminal with the AI ​​service network element, and share the AI ​​capabilities corresponding to each AI capability terminal with other terminals in the operator network.

[0094] The terminal AI capability sharing method provided in this application embodiment receives registration signaling sent by at least one AI capability terminal, parses the registration signaling to obtain an AI capability field representing the AI ​​capabilities that each AI capability terminal can share, and shares the AI ​​capabilities corresponding to each AI capability terminal based on the AI ​​capability field. In this application embodiment, each AI capability terminal registers its shareable AI capabilities, and the AI ​​capability terminals are rationally scheduled to achieve the sharing of AI capabilities among different terminals. Furthermore, different terminals collaborate to complete the same service, establishing an AI intelligent ecosystem for the operator network and enhancing terminal capabilities and service experience.

[0095] In one embodiment, sharing the AI ​​capabilities corresponding to each AI capability terminal based on the AI ​​capability field includes: Extract the AI ​​capabilities corresponding to each AI capability terminal from the AI ​​capability fields; Send the AI ​​capabilities corresponding to each AI capability terminal to the AI ​​service network element.

[0096] Specifically, after extracting the AI ​​capabilities that can be shared by each AI capability terminal from the AI ​​capability field, the extracted AI capabilities can be sent to the AI ​​service network element via the northbound interface through HTTP (Hypertext Transfer Protocol). The AI ​​capabilities corresponding to each AI capability terminal are registered in the AI ​​service network element, which facilitates the scheduling of each AI capability terminal by the AI ​​service network element and realizes the sharing of AI capabilities in the operator network.

[0097] The terminal AI capability sharing device provided in the embodiments of this application is described below. The terminal AI capability sharing device described below can be referred to in correspondence with the terminal AI capability sharing method described above.

[0098] This application provides a terminal AI capability sharing device. Figure 4 This is one of the structural schematic diagrams of the terminal AI capability sharing device provided in the embodiments of this application, such as... Figure 4 As shown, the terminal AI capability sharing device 400 includes: a first receiving module 410, a first determining module 420, and a calling module 430.

[0099] The first receiving module 410 is used to receive the target AI capability corresponding to the non-AI capability terminal sent by the media plane network element.

[0100] The first determining module 420 is used to determine the target AI capability terminal corresponding to the target AI capability.

[0101] The calling module 430 is used to call the target AI capability terminal to process the AI ​​business data corresponding to the non-AI capability terminal; the calling operation is used to share the target AI capability corresponding to the target AI capability terminal with the non-AI capability terminal.

[0102] The terminal AI capability sharing device provided in this application embodiment receives the target AI capability corresponding to a non-AI capability terminal sent by a media plane network element, determines the target AI capability terminal with the target AI capability, and calls the target AI capability terminal to process the AI ​​service data that the non-AI capability terminal needs to process. In this application embodiment, by sharing the target AI capability corresponding to the target AI capability terminal with the non-AI capability terminal, the non-AI capability terminal without AI capability can use the target AI capability provided by the target AI capability terminal, realizing the sharing of AI capabilities among different terminals, and enabling different terminals to cooperate to complete the same service, establishing an AI intelligent ecosystem for operator networks, and improving the utilization rate of terminal AI capabilities and service experience.

[0103] Optionally, the first determining module 420 is specifically used for: Identify candidate AI capability terminals that possess the target AI capability from among the registered AI capability terminals; Based on the overall device score corresponding to the target AI capability among the candidate AI capability terminals, the target AI capability terminal corresponding to the target AI capability is determined.

[0104] Optionally, the terminal AI capability sharing device 400 also includes a scoring module, which is specifically used for: Before receiving the target AI capability corresponding to a non-AI capability terminal sent by the media plane network element, receive at least one AI capability corresponding to an AI capability terminal sent by the VoLTE network element. Determine the overall device score for the AI ​​capabilities corresponding to each of the aforementioned AI capability terminals.

[0105] Optionally, this scoring module is specifically used for: Based on the load indicators, performance indicators, and historical execution statistics of each AI capability terminal, the overall device score of the AI ​​capability corresponding to each AI capability terminal is determined.

[0106] Optionally, module 430 is invoked, specifically for: Receive AI service data corresponding to non-AI capability terminals sent by the media plane network element; The AI ​​service data is sent to the target AI-capable terminal, or the target address corresponding to the target AI-capable terminal is sent to the media plane network element; the target address is used to instruct the media plane network element to send the AI ​​service data to the target AI-capable terminal.

[0107] This application provides a terminal AI capability sharing device. Figure 5 This is a second schematic diagram of the structure of the terminal AI capability sharing device provided in the embodiments of this application, as shown below. Figure 5 As shown, the terminal AI capability sharing device 500 includes: a second receiving module 510 and a first sending module 520.

[0108] The second receiving module 510 is used to receive the target AI capabilities required by the non-AI capability terminal.

[0109] The first sending module 520 is used to send the target AI capability to the AI ​​service network element, wherein the target AI capability is used to instruct the AI ​​service network element to determine the target AI capability terminal corresponding to the target AI capability; to call the target AI capability terminal to process the AI ​​service data corresponding to the non-AI capability terminal; and to call the terminal to share the target AI capability corresponding to the target AI capability terminal with the non-AI capability terminal.

[0110] The terminal AI capability sharing device provided in this application embodiment sends the target AI capability required by a non-AI capability terminal to the AI ​​service network element, instructing the AI ​​service network element to determine the target AI capability terminal with the target AI capability, and calling the target AI capability terminal to process the AI ​​service data that the non-AI capability terminal needs to process. In this application embodiment, the target AI capability corresponding to the target AI capability terminal is shared with the non-AI capability terminal, so that the non-AI capability terminal without AI capability can use the target AI capability provided by the target AI capability terminal, realizing the sharing of AI capabilities among different terminals, and different terminals cooperating to complete the same service, establishing an AI intelligent ecosystem for the operator network, and improving the utilization rate of terminal AI capabilities and service experience.

[0111] Optionally, the terminal AI capability sharing device 500 further includes a second determining module, which is specifically used for: Before receiving the target AI capabilities required by the non-AI capability terminal, AI capability recommendation data corresponding to the non-AI capability terminal is determined based on the service type initiated by the non-AI capability terminal. The AI ​​capability recommendation data is sent to the non-AI capability terminal; the AI ​​capability recommendation data includes at least the target AI capability.

[0112] Optionally, the terminal AI capability sharing device 500 further includes a second transmitting module, which is specifically used for: Receive AI service data sent by the non-AI capable terminal; Send the AI ​​service data to the AI ​​service network element; Upon receiving the target address corresponding to the target AI capability terminal sent by the AI ​​service network element, the AI ​​service data is sent to the target AI capability terminal based on the target address.

[0113] This application provides a terminal AI capability sharing device. Figure 6 This is the third structural schematic diagram of the terminal AI capability sharing device provided in the embodiments of this application, as shown below. Figure 6 As shown, the terminal AI capability sharing device 600 includes: a third receiving module 610, a parsing module 620, and a sharing module 630.

[0114] The third receiving module 610 is used to receive registration signaling sent by at least one AI-capable terminal.

[0115] The parsing module 620 is used to parse the registration signaling to obtain the AI ​​capability field; the AI ​​capability field is used to characterize the AI ​​capability corresponding to each AI capability terminal.

[0116] The sharing module 630 is used to share the AI ​​capabilities corresponding to each AI capability terminal based on the AI ​​capability field.

[0117] The terminal AI capability sharing device provided in this application embodiment receives registration signaling sent by at least one AI capability terminal, parses the registration signaling to obtain an AI capability field characterizing the AI ​​capabilities that each AI capability terminal can share, and shares the AI ​​capabilities corresponding to each AI capability terminal based on the AI ​​capability field. In this application embodiment, each AI capability terminal registers its shareable AI capabilities, and the AI ​​capability terminals are rationally scheduled to achieve the sharing of AI capabilities among different terminals. Furthermore, different terminals collaborate to complete the same service, establishing an AI intelligent ecosystem for the operator network and enhancing terminal capabilities and service experience.

[0118] Optionally, the shared module 630 is specifically used for: Extract the AI ​​capabilities corresponding to each AI capability terminal from the AI ​​capability fields; Send the AI ​​capabilities corresponding to each AI capability terminal to the AI ​​service network element.

[0119] This application provides a terminal AI capability sharing system, including AI service network elements, media plane network elements, and VoLTE network elements, wherein: The AI ​​service network element is used to execute the terminal AI capability sharing method as described in any of the above embodiments; The media plane network element is used to execute the terminal AI capability sharing method as described in any of the above embodiments; The VoLTE network element is used to execute the terminal AI capability sharing method as described in any of the above embodiments.

[0120] It should be noted that the terminal AI capability sharing system is a system corresponding to the operator's network, and the terminal AI capability sharing system also includes at least one non-AI capability terminal and at least one AI capability terminal.

[0121] For example, Figure 7 This is a schematic diagram of the signaling interaction of the terminal AI capability sharing system provided in the embodiments of this application, such as... Figure 7 As shown, taking the terminal AI capability sharing system as an example, in addition to AI service network elements, media plane network elements and VoLTE network elements, it also includes a non-AI capability terminal UE_A and two AI capability terminals, namely the first AI capability terminal UE_B and the second AI capability terminal UE_C. The AI ​​capability sharing process includes the following steps.

[0122] 1. After the first AI-capable terminal UE_B and the second AI-capable terminal UE_C are powered on, an X-Capability-AIAgent field can be added to the SIP NOTIFY signaling, and their respective shareable AI capabilities can be added to the X-Capability-AIAgent field to obtain the improved SIP NOTIFY signaling. The first AI-capable terminal UE_B and the second AI-capable terminal UE_C send their respective improved SIP NOTIFY signaling to the VoLTE network element.

[0123] 2. The VoLTE network element parses each SIP NOTIFY signaling, extracts the AI ​​capabilities that the first AI capability terminal UE_B and the second AI capability terminal UE_C can share from their respective X-Capability-AIAgent fields, and sends the extracted AI capabilities to the AI ​​service network element. The AI ​​service network element then updates the corresponding capabilities of the first AI capability terminal UE_B and the second AI capability terminal UE_C.

[0124] 3. The AI ​​service network element evaluation uses the device comprehensive score ScoreB for the AI ​​capabilities shared by the first AI capability terminal UE_B and the device comprehensive score ScoreC for the AI ​​capabilities shared by the second AI capability terminal UE_C.

[0125] 4. When the non-AI-capable terminal UE_A communicates with the first AI-capable terminal UE_B, the non-AI-capable terminal UE_A starts a file transfer applet.

[0126] 5. The media plane network element sends AI capability recommendation data to the non-AI capability terminal UE_A through the CDC channel, that is, notifies the non-AI capability terminal UE_A of the AI ​​capabilities that the file transfer applet launched can use, such as image removal.

[0127] 6. Non-AI-capable terminal UE_A selects an image as the AI ​​service data and determines the target AI capability as image removal, requesting the use of network AI capabilities to remove the background from the image to be processed. Non-AI-capable terminal UE_A sends the target AI capability to the media plane network element.

[0128] 7. The media face network element sends the target AI capabilities to the AI ​​business network element, which then selects and allocates models and capabilities according to a certain strategy, choosing appropriate target AI capability terminals or edge devices.

[0129] 8. When both the first AI-capable terminal UE_B and the second AI-capable terminal UE_C have image removal capabilities, the AI ​​service network element calculates the first score ScoreB1 corresponding to the image removal capability in the first AI-capable terminal UE_B and the second score ScoreC1 corresponding to the image removal capability in the second AI-capable terminal UE_C. Since the second score ScoreC1 is higher than the first score ScoreB1, the second AI-capable terminal UE_C is determined as the target AI-capable terminal, thereby providing image removal capability to the non-AI-capable terminal UE_A.

[0130] 9. The AI ​​service network element notifies the second AI capability terminal UE_C to initialize the interface and prepare to execute the image removal capability.

[0131] 10. After receiving a notification from the AI ​​service network element, the media plane network element notifies the non-AI capability terminal UE_A that the image removal capability within the network is available and image removal service can be performed.

[0132] 11. Non-AI capable terminal UE_A sends the images that need to be processed to the media plane network element through CDC.

[0133] 12. The media-side network element sends the images that the non-AI capability terminal UE_A needs to process to the AI ​​service network element.

[0134] 13. The AI ​​service network element sends the images that the non-AI capability terminal UE_A needs to process to the selected second AI capability terminal UE_C.

[0135] 14. After performing image removal on the image that the non-AI capability terminal UE_A needs to process, the second AI capability terminal UE_C sends the image after image removal to the AI ​​service network element.

[0136] 15. The AI ​​service network element will send the image after image removal to the media plane network element.

[0137] 16. The media plane network element sends the image after image removal to the non-AI capability terminal UE_A for confirmation via CDC.

[0138] The AI-capable terminals and non-AI-capable terminals involved in the embodiments of this application can be devices that provide voice and / or data connectivity to users, handheld devices with wireless connectivity, or other processing devices connected to a wireless modem, etc. The names of the terminal devices may differ in different systems; for example, in a 5G system, the terminal device can be called User Equipment (UE).

[0139] Figure 8 This is a schematic diagram of the network device provided in the embodiments of this application, with reference to... Figure 8 This application embodiment also provides a network device, which may include: a memory 810, a transceiver 820, and a processor 830; The memory 810 is used to store computer programs; the transceiver 820 is used to send and receive data under the control of the processor 830; the processor 830 is used to read the computer program in the memory 810 and perform the following operations: The target AI capability corresponding to the non-AI capability terminal received by the media plane network element; Identify the target AI capability terminal corresponding to the target AI capability; The system invokes the target AI-capable terminal to process the AI ​​service data corresponding to the non-AI-capable terminal; the invocation operation is used to share the target AI capability corresponding to the target AI-capable terminal with the non-AI-capable terminal; or... Receive the target AI capabilities required by non-AI capable terminals; The target AI capability is sent to the AI ​​service network element, whereby the target AI capability instructs the AI ​​service network element to determine the target AI capability terminal corresponding to the target AI capability; the target AI capability terminal is invoked to process the AI ​​service data corresponding to the non-AI capability terminal; an invocation operation is used to share the target AI capability corresponding to the target AI capability terminal with the non-AI capability terminal; or... Receive registration signaling from at least one AI-capable terminal; The registration signaling is parsed to obtain the AI ​​capability field; the AI ​​capability field is used to characterize the AI ​​capability corresponding to each AI capability terminal. Based on the AI ​​capability fields, the AI ​​capabilities corresponding to each AI capability terminal are shared.

[0140] Among them, Figure 8In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits together, represented by one or more processors (processor 830) and memory (memory 810). The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 820 can be multiple elements, including transmitters and receivers, providing a unit for communicating with various other devices over a transmission medium. The processor 830 is responsible for managing the bus architecture and general processing, and the memory 810 can store data used by the processor 830 during operation.

[0141] It should be noted that the network device provided in this application embodiment can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.

[0142] On the other hand, embodiments of this application also provide a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the terminal AI capability sharing method provided by the above methods, which includes: The target AI capability corresponding to the non-AI capability terminal received by the media plane network element; Identify the target AI capability terminal corresponding to the target AI capability; The system invokes the target AI-capable terminal to process the AI ​​service data corresponding to the non-AI-capable terminal; the invocation operation is used to share the target AI capability corresponding to the target AI-capable terminal with the non-AI-capable terminal; or... Receive the target AI capabilities required by non-AI capable terminals; The target AI capability is sent to the AI ​​service network element, whereby the target AI capability instructs the AI ​​service network element to determine the target AI capability terminal corresponding to the target AI capability; the target AI capability terminal is invoked to process the AI ​​service data corresponding to the non-AI capability terminal; an invocation operation is used to share the target AI capability corresponding to the target AI capability terminal with the non-AI capability terminal; or... Receive registration signaling from at least one AI-capable terminal; The registration signaling is parsed to obtain the AI ​​capability field; the AI ​​capability field is used to characterize the AI ​​capability corresponding to each AI capability terminal. Based on the AI ​​capability fields, the AI ​​capabilities corresponding to each AI capability terminal are shared.

[0143] In another aspect, embodiments of this application also provide a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the terminal AI capability sharing method provided by the above methods, the method comprising: The target AI capability corresponding to the non-AI capability terminal received by the media plane network element; Identify the target AI capability terminal corresponding to the target AI capability; The system invokes the target AI-capable terminal to process the AI ​​service data corresponding to the non-AI-capable terminal; the invocation operation is used to share the target AI capability corresponding to the target AI-capable terminal with the non-AI-capable terminal; or... Receive the target AI capabilities required by non-AI capable terminals; The target AI capability is sent to the AI ​​service network element, whereby the target AI capability instructs the AI ​​service network element to determine the target AI capability terminal corresponding to the target AI capability; the target AI capability terminal is invoked to process the AI ​​service data corresponding to the non-AI capability terminal; an invocation operation is used to share the target AI capability corresponding to the target AI capability terminal with the non-AI capability terminal; or... Receive registration signaling from at least one AI-capable terminal; The registration signaling is parsed to obtain the AI ​​capability field; the AI ​​capability field is used to characterize the AI ​​capability corresponding to each AI capability terminal. Based on the AI ​​capability fields, the AI ​​capabilities corresponding to each AI capability terminal are shared.

[0144] The processor-readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to magnetic memory (e.g., floppy disk, hard disk, magnetic tape, magneto-optical disk (MO)), optical memory (e.g., CD, DVD, BD, HVD), and semiconductor memory (e.g., ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)).

[0145] The device embodiments described above are merely illustrative. 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 modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0146] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0147] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for sharing terminal AI capabilities, characterized in that, Applied to AI service network elements, the method includes: The target AI capability corresponding to the non-AI capability terminal received by the media plane network element; Identify the target AI capability terminal corresponding to the target AI capability; The target AI-capable terminal is invoked to process the AI ​​business data corresponding to the non-AI-capable terminal; the invocation operation is used to share the target AI capability corresponding to the target AI-capable terminal with the non-AI-capable terminal.

2. The terminal AI capability sharing method according to claim 1, characterized in that, The terminal for determining the target AI capability corresponding to the target AI capability includes: Identify candidate AI capability terminals that possess the target AI capability from among the registered AI capability terminals; Based on the overall device score corresponding to the target AI capability among the candidate AI capability terminals, the target AI capability terminal corresponding to the target AI capability is determined.

3. The terminal AI capability sharing method according to claim 1, characterized in that, Before receiving the target AI capability corresponding to the non-AI capability terminal sent by the media plane network element, the method further includes: The AI ​​capability corresponding to at least one AI capability terminal received from the VoLTE network element; Determine the overall device score for the AI ​​capabilities corresponding to each of the aforementioned AI capability terminals.

4. The terminal AI capability sharing method according to claim 3, characterized in that, The determination of the overall device score for the AI ​​capabilities of each AI-capable terminal includes: Based on the load indicators, performance indicators, and historical execution statistics of each AI capability terminal, the overall device score of the AI ​​capability corresponding to each AI capability terminal is determined.

5. The terminal AI capability sharing method according to any one of claims 1-4, characterized in that, The step of calling the target AI-capable terminal to process the AI ​​business data corresponding to the non-AI-capable terminal includes: Receive AI service data corresponding to non-AI capability terminals sent by the media plane network element; The AI ​​service data is sent to the target AI-capable terminal, or the target address corresponding to the target AI-capable terminal is sent to the media plane network element; the target address is used to instruct the media plane network element to send the AI ​​service data to the target AI-capable terminal.

6. A method for sharing terminal AI capabilities, characterized in that, Applied to media plane network elements, the method includes: Receive the target AI capabilities required by non-AI capable terminals; The target AI capability is sent to the AI ​​service network element, and the target AI capability is used to instruct the AI ​​service network element to determine the target AI capability terminal corresponding to the target AI capability; the target AI capability terminal is invoked to process the AI ​​service data corresponding to the non-AI capability terminal; the invocation operation is used to share the target AI capability corresponding to the target AI capability terminal with the non-AI capability terminal.

7. The terminal AI capability sharing method according to claim 6, characterized in that, Before receiving the target AI capabilities required by the non-AI-capable terminal, the method further includes: Based on the service type initiated by the non-AI capability terminal, determine the AI ​​capability recommendation data corresponding to the non-AI capability terminal; The AI ​​capability recommendation data is sent to the non-AI capability terminal; the AI ​​capability recommendation data includes at least the target AI capability.

8. The terminal AI capability sharing method according to claim 6, characterized in that, The method further includes: Receive AI service data sent by the non-AI capable terminal; Send the AI ​​service data to the AI ​​service network element; Upon receiving the target address corresponding to the target AI capability terminal sent by the AI ​​service network element, the AI ​​service data is sent to the target AI capability terminal based on the target address.

9. A method for sharing terminal AI capabilities, characterized in that, Applied to VoLTE network elements, the method includes: Receive registration signaling from at least one AI-capable terminal; The registration signaling is parsed to obtain the AI ​​capability field; the AI ​​capability field is used to characterize the AI ​​capability corresponding to each AI capability terminal. Based on the AI ​​capability fields, the AI ​​capabilities corresponding to each AI capability terminal are shared.

10. The terminal AI capability sharing method according to claim 9, characterized in that, The sharing of AI capabilities corresponding to each AI capability terminal based on the AI ​​capability field includes: Extract the AI ​​capabilities corresponding to each AI capability terminal from the AI ​​capability fields; Send the AI ​​capabilities corresponding to each AI capability terminal to the AI ​​service network element.

11. A terminal AI capability sharing device, characterized in that, include: The first receiving module is used to receive the target AI capability corresponding to the non-AI capability terminal sent by the media plane network element; The first determining module is used to determine the target AI capability terminal corresponding to the target AI capability; The invocation module is used to invoke the target AI capability terminal to process the AI ​​business data corresponding to the non-AI capability terminal; the invocation operation is used to share the target AI capability corresponding to the target AI capability terminal with the non-AI capability terminal.

12. A terminal AI capability sharing device, characterized in that, include: The second receiving module is used to receive the target AI capabilities required by non-AI capability terminals. The first sending module is used to send the target AI capability to the AI ​​service network element, wherein the target AI capability is used to instruct the AI ​​service network element to determine the target AI capability terminal corresponding to the target AI capability; to call the target AI capability terminal to process the AI ​​service data corresponding to the non-AI capability terminal; and to call the operation to share the target AI capability corresponding to the target AI capability terminal with the non-AI capability terminal.

13. A terminal AI capability sharing device, characterized in that, include: The third receiving module is used to receive registration signaling sent by at least one AI-capable terminal; The parsing module is used to parse the registration signaling to obtain the AI ​​capability field; the AI ​​capability field is used to characterize the AI ​​capability corresponding to each AI capability terminal; The sharing module is used to share the AI ​​capabilities corresponding to each AI capability terminal based on the AI ​​capability field.

14. A terminal AI capability sharing system, characterized in that, This includes AI service network elements, media plane network elements, and VoLTE network elements, among which: The AI ​​service network element is used to execute the terminal AI capability sharing method as described in any one of claims 1-5; The media plane element is used to execute the terminal AI capability sharing method as described in any one of claims 6-8; The VoLTE network element is used to execute the terminal AI capability sharing method as described in claim 9 or 10.

15. A network device, characterized in that, Includes memory, transceiver, and processor; Memory, used to store computer programs; Transceiver, used to send and receive data under the control of the processor; A processor is configured to read a computer program from the memory and execute the terminal AI capability sharing method as described in any one of claims 1-5, the terminal AI capability sharing method as described in any one of claims 6-8, or the terminal AI capability sharing method as described in claim 9 or 10.

16. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the terminal AI capability sharing method as described in any one of claims 1-5, the terminal AI capability sharing method as described in any one of claims 6-8, or the terminal AI capability sharing method as described in claim 9 or 10.

Images