Data processing method and related equipment

Abstract

The invention provides a data processing method and related equipment, and relates to the technical field of communication. The method comprises: a terminal sends a model discovery request to a server, the model discovery request comprising a first identifier and a service demand, so that the server determines a second identifier according to the first identifier and the service demand, and an artificial intelligence platform initializes an artificial intelligence model according to the service demand. And receiving model discovery response information sent by the server, and sending a data submission request to the server, so that the server establishes a data channel between the terminal and the artificial intelligence platform. According to the method, the to-be-processed data is processed by using the matched artificial intelligence model, so that the processing requirements of multiple types of feature data can be met. Besides, the to-be-processed data is transmitted by establishing a data channel between the terminal and the artificial intelligence platform, so that data congestion and blockage can be prevented, and the transmission speed of the data can also be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technologies, and in particular to a data processing method, device, electronic device, computer-readable storage medium, and computer program product. Background Art

[0002] Perception data processing and transmission refers to how, in network and communication technologies, data from the environment or physical world is collected through various perception devices (such as sensors, cameras, temperature and humidity sensors, etc.) and how this data is processed and transmitted.

[0003] In related technologies, centralized artificial intelligence (AI) deployed on the Internet or third-party platforms struggles to adapt to the personalized data of user terminals. Because different types of deep neural networks are required to process different data types, a single AI model cannot adapt to and meet the processing needs of multiple types of feature data when users upload personalized sensor data. Summary of the Invention

[0004] The present disclosure provides a data processing method and related equipment, which can meet the processing requirements of multiple types of feature data at least to a certain extent.

[0005] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by practice of the present disclosure.

[0006] According to one aspect of the present disclosure, there is provided a data processing method, which is applied to a terminal, and the data processing method comprises: sending a model discovery request to a server, the model discovery request comprising a first identifier and a business requirement, so that the server determines a second identifier based on the first identifier and the business requirement, and sending a model configuration request to an artificial intelligence platform, so that the artificial intelligence platform initializes the artificial intelligence model, the model configuration request comprising the first identifier, the second identifier and the business requirement, the first identifier being used to indicate a terminal that has completed registration with the server, and the second identifier being used to indicate an artificial intelligence model that matches the business requirement; receiving model discovery response information sent by the server, the model discovery response information The second identifier is carried in the information, the model discovery response information is sent by the server to the terminal after receiving the configuration completion information sent by the artificial intelligence platform, and the configuration completion information is sent by the artificial intelligence platform to the server after completing the initialization of the artificial intelligence model; a data submission request is sent to the server, and the data submission request includes the first identifier and the second identifier, so that the server establishes a data channel according to the first identifier and the second identifier; based on the data channel, the data to be processed is sent to the artificial intelligence platform, so that the artificial intelligence platform uses the artificial intelligence model corresponding to the second identifier to process the data to be processed; and the data analysis results sent by the artificial intelligence platform are received.

[0007] According to another aspect of the present disclosure, there is provided a data processing method, which is applied to a server, and the data processing method includes: receiving a model discovery request sent by a terminal, the model discovery request including a first identifier and a business requirement; determining a second identifier based on the first identifier and the business requirement; sending a model configuration request to an artificial intelligence platform, so that the artificial intelligence platform initializes the artificial intelligence model according to the model configuration request, the model configuration request including the first identifier, the second identifier and the business requirement; receiving configuration completion information sent by the artificial intelligence platform, the configuration completion information is sent by the artificial intelligence platform to the server after completing the initialization of the artificial intelligence model; sending model discovery response information to the terminal, the model discovery response information carrying the second identifier; receiving a data submission request sent by the terminal, the data submission request including the first identifier and the second identifier; establishing a data channel based on the data submission request, so that the terminal sends the data to be processed to the artificial intelligence platform based on the data channel, the artificial intelligence platform uses the artificial intelligence model corresponding to the second identifier to process the data to be processed, and sends the data analysis results to the terminal.

[0008] According to another aspect of the present disclosure, there is provided a data processing method, which is applied to an artificial intelligence platform, and the data processing method includes: receiving a model configuration request sent by a server, the model configuration request including a first identifier, a second identifier and a business requirement, the first identifier being used to indicate a terminal that has completed registration with the server, and the second identifier being used to indicate an artificial intelligence model that matches the business requirement; initializing the artificial intelligence model according to the model configuration request; sending configuration completion information to the server; receiving data to be processed sent by the terminal based on a data channel, the data channel being established by the server according to the first identifier and the second identifier; performing data processing on the data to be processed using the artificial intelligence model corresponding to the second identifier to obtain a data analysis result; and sending the data analysis result to the terminal.

[0009] According to another aspect of the present disclosure, there is provided a data processing device, which is applied to a terminal, comprising: a first sending module, configured to send a model discovery request to a server, wherein the model discovery request comprises a first identifier and a business requirement, so that the server determines a second identifier based on the first identifier and the business requirement, and sends a model configuration request to an artificial intelligence platform, so that the artificial intelligence platform initializes the artificial intelligence model, wherein the model configuration request comprises the first identifier, the second identifier and the business requirement, wherein the first identifier is used to indicate a terminal that has completed registration with the server, and the second identifier is used to indicate an artificial intelligence model that matches the business requirement; a first receiving module, configured to receive model discovery response information sent by the server, wherein the model discovery response information carries the second identifier, and the second identifier is used to indicate an artificial intelligence model that matches the business requirement; The model discovery response information is sent by the server to the terminal after receiving the configuration completion information sent by the artificial intelligence platform, and the configuration completion information is sent by the artificial intelligence platform to the server after completing the initialization of the artificial intelligence model; the first sending module is also used to send a data submission request to the server, and the data submission request includes the first identifier and the second identifier, so that the server establishes a data channel according to the first identifier and the second identifier; the first sending module is also used to send the data to be processed to the artificial intelligence platform based on the data channel, so that the artificial intelligence platform uses the artificial intelligence model corresponding to the second identifier to process the data to be processed; the first receiving module is also used to receive the data analysis results sent by the artificial intelligence platform.

[0010] According to another aspect of the present disclosure, a data processing device is provided, applied to a server, comprising: a second sending module, configured to receive a model discovery request sent by a terminal, the model discovery request including a first identifier and a business requirement; a determining module, configured to determine a second identifier based on the first identifier and the business requirement; the second sending module, further configured to send a model configuration request to an artificial intelligence platform, so that the artificial intelligence platform initializes an artificial intelligence model according to the model configuration request, the model configuration request including the first identifier, the second identifier, and the business requirement; a second receiving module, configured to receive configuration completion information sent by the artificial intelligence platform, the configuration completion information being sent by the artificial intelligence platform to the server after completing the initialization of the artificial intelligence model; the second sending module, further configured to send a model discovery response information to the terminal, the model discovery response information carrying the second identifier; the second receiving module, further configured to receive a data submission request sent by the terminal, the data submission request including the first identifier and the second identifier; and a channel establishing module, configured to establish a data channel based on the data submission request, so that the terminal sends to-be-processed data to the artificial intelligence platform based on the data channel, the artificial intelligence platform processes the to-be-processed data using the artificial intelligence model corresponding to the second identifier, and sends the data analysis results to the terminal.

[0011] According to another aspect of the present disclosure, there is provided a data processing device, which is applied to an artificial intelligence platform and includes: a third receiving module, which is used to receive a model configuration request sent by a server, the model configuration request including a first identifier, a second identifier and a business requirement, the first identifier being used to indicate a terminal that has completed registration with the server, and the second identifier being used to indicate an artificial intelligence model that matches the business requirement; an initialization module, which is used to initialize the artificial intelligence model according to the model configuration request; a third sending module, which is used to send configuration completion information to the server; the third receiving module is also used to receive the data to be processed sent by the terminal based on a data channel, the data channel being established by the server according to the first identifier and the second identifier; a processing module, which is used to perform data processing on the data to be processed using the artificial intelligence model corresponding to the second identifier to obtain a data analysis result; the third sending module is also used to send the data analysis result to the terminal.

[0012] According to another aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any of the above-mentioned data processing methods by executing the executable instructions.

[0013] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, any of the above-mentioned data processing methods is implemented.

[0014] According to another aspect of the present disclosure, a computer program product is provided, which includes a computer program or computer instructions, and the computer program or the computer instructions are loaded and executed by a processor to enable a computer to implement any of the above-mentioned data processing methods.

[0015] In an embodiment of the present disclosure, a terminal sends a model discovery request to a server. The model discovery request includes a first identifier and a business requirement, so that the server matches an artificial intelligence identifier (second identifier) that meets the terminal's business requirement and enables the artificial intelligence platform to initialize the artificial intelligence model according to the business requirement. A model discovery response message is received from the server, and a data submission request is sent to the server so that the server establishes a data channel between the terminal and the artificial intelligence platform. The present disclosure can meet the processing requirements of multiple types of feature data by using the matched artificial intelligence model to process the data to be processed. In addition, by establishing a data channel between the terminal and the artificial intelligence platform to transmit the data to be processed, data congestion and blockage can be prevented, and the data transmission speed can also be increased. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram illustrating the architecture of a data processing system in an embodiment of the present disclosure is shown.

[0017] Figure 2 A schematic diagram illustrating the architecture of a data processing system in another embodiment of the present disclosure.

[0018] Figure 3 A flow chart of a data processing method in an embodiment of the present disclosure is shown.

[0019] Figure 4 A flow chart of a data processing method in another embodiment of the present disclosure is shown.

[0020] Figure 5 A flow chart of a data processing method in another embodiment of the present disclosure is shown.

[0021] Figure 6 A signaling diagram illustrating a data processing method in an embodiment of the present disclosure is shown.

[0022] Figure 7 A signaling diagram illustrating a data processing method in another embodiment of the present disclosure.

[0023] Figure 8 A signaling diagram illustrating a data processing method in yet another embodiment of the present disclosure.

[0024] Figure 9 A signaling diagram illustrating a data processing method in yet another embodiment of the present disclosure.

[0025] Figure 10 A schematic diagram of a data processing device in an embodiment of the present disclosure is shown.

[0026] Figure 11 A schematic diagram of a data processing device in another embodiment of the present disclosure is shown.

[0027] Figure 12 A schematic diagram of a data processing device in another embodiment of the present disclosure is shown.

[0028] Figure 13 A structural block diagram of an electronic device in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0029] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0030] Some of the blocks shown in the drawings are functional entities, which do not necessarily correspond to physically or logically separate entities.

[0031] For ease of understanding, several terms involved in this disclosure are explained below: Data Sensing: Detects and senses the surrounding environment (e.g., target location, speed, and trajectory) through user devices (terminals) or base stations. This data is then stored locally or uploaded to the network for processing to obtain deeper insights. This technology is widely used in areas such as in-vehicle internet, drone control, smart homes, health monitoring, and large-scale IoT.

[0032] The Network Exposure Function (NEF) is part of the 5th Generation Mobile Network (5G) network architecture and is used to provide external applications with access to network capabilities and data.

[0033] The Network Data Analytics Function (NWDAF) is a key component in the 5G network architecture. It is responsible for collecting, analyzing, and processing data generated in the network, thereby providing various functions such as network performance optimization, fault detection, traffic management, and security monitoring.

[0034] The User Plane Function (UPF) is a key component in the 5G core network architecture, responsible for forwarding, routing, and processing user data.

[0035] The 3rd Generation Partnership Project (3GPP) is an international organization dedicated to developing global standards for wireless communication technologies. The 3GPP network system refers to the various wireless communication technologies and network architectures covered by the standards developed by 3GPP.

[0036] A MAC address (Media Access Control Address) is a network hardware address used to uniquely identify a network device. An IP address (Internet Protocol Address) is an address used to uniquely identify a device on a network.

[0037] The Session Management Function (SMF) is an important functional module in the 5G core network, responsible for session management. Its main responsibility is to handle control plane operations related to user sessions.

[0038] It should be pointed out that, in the absence of conflict, the embodiments of the present disclosure and the technical features therein may be combined with each other.

[0039] Related technologies suffer from three major flaws in sensory data processing and transmission. 1) For sensory data with simple structures and small data volumes, users can process it locally on the sensory device and then upload the results directly to the network, which does not significantly impact network load. However, when sensory data is diverse and large in volume, sudden bursts of large data traffic can cause congestion and latency in the sensory network, impacting overall network performance. In other words, as data volume increases, the network will encounter congestion and latency issues, limiting the efficient operation of the sensory system. 2) Centralized AI deployed on the network or third-party platforms struggles to adapt to the personalized data of user terminals. Because processing different types of data requires different AI models (such as deep neural networks), when users upload personalized sensory data, a single AI model is unable to process multiple types of feature data. 3) Sensory data cannot form a coordinated system for transmission, application, and network optimization. After uploading data to a third-party platform, the data perception system is unable to extract network information that can be used to improve the core network environment.

[0040] Based on at least one of the above problems, the embodiments of the present disclosure provide a data processing method that can be applied to data perception scenarios. For example, it can be applied to scenarios such as in-vehicle Internet, drone control, smart home and health monitoring, environmental monitoring, and large-scale Internet of Things. It can also be applied to local processing, transmission, and remote analysis of perception data in synaesthesia integration. In addition, it can also be applied to scenarios for network optimization based on perception data. The present disclosure can meet the processing requirements of multiple types of feature data by using the matched artificial intelligence model to process the data to be processed. In addition, by transmitting the data to be processed through a data channel established between the terminal and the artificial intelligence platform, data congestion and blockage can be prevented, and the data transmission speed can be increased.

[0041] The specific implementation of the embodiment of the present disclosure is described in detail below with reference to the accompanying drawings.

[0042] Figure 1 A schematic diagram showing the architecture of a data processing system in one embodiment of the present disclosure is provided. The system can apply the data processing method or data processing device in various embodiments of the present disclosure.

[0043] like Figure 1 As shown, the system architecture may include terminals, servers, and artificial intelligence platforms. The terminal is equipped with a sensing enabling client (SEC) for performing sensing functions. The SEC collects sensing data through sensors. The sensing data may be video, audio, images, electromagnetic waves, etc. The server may be a sensing enabling server (SES), which is used to support the execution of sensing tasks and data processing. The artificial intelligence platform may be an AI platform deployed on the core network itself or a trusted third-party platform connected to the core network. After sensing the surrounding environment, the terminal uploads the sensing data to the AI platform and issues instructions through generative AI, instructing the AI platform to process the data.

[0044] It should be noted that the data collected and processed by the AI platform can be made available to third parties, such as other users or third-party platforms, after being filtered. The server can be deployed on the core network, which can deploy and utilize dedicated data channels to transmit perception data. Alternatively, the server can be deployed outside the core network, with the server deploying and utilizing dedicated data channels to transmit perception data.

[0045] For example, the server is SES, and SEC is connected to SES through a network. SEC collects processing requirements for sensor data, feeds back to SES, and searches for the required AI model. Sensors perceive the surrounding multimodal environmental information, including images, videos, audio, etc., locally on the terminal, and transmit the information to the server through the network. Figure 2 The core network's data channel (DC) is shown as transmitting data to the AI model deployed on the AI platform. It should be noted that sensor data is compressed and encrypted locally on the terminal (device), and the compressed data and corresponding labels are provided to the AI model for fine-tuning and training. After fine-tuning, the AI model processes the sensor data (referred to below as "unprocessed data") to obtain the data required by users (such as data analysis results) and relevant information for network optimization (such as basic network information).

[0046] For example, Figure 2 As shown, the AI model analyzes the data being processed to obtain basic network information at the terminal's location. This information is then sent to the NWDAF network element via the server, enabling the NWDAF to optimize the network based on this information. It should be noted that before the AI model shares this basic network information with the 3GPP network system (such as the core network) via the NEF, it must obtain the terminal user's consent.

[0047] For example, the artificial intelligence platform and the terminal can directly transmit data. The artificial intelligence platform can also use the UPF network element to realize data transmission with the terminal, such as Figure 2 It should be noted that by establishing a data channel between the terminal and the artificial intelligence platform to transmit the data to be processed, data congestion and blockage can be prevented, and the data transmission speed can be increased.

[0048] The SEC and SES communicate via a network, which can be either a wired or wireless network. Optionally, the wireless or wired network utilizes standard communication technologies and / or protocols. The network is typically the Internet, but may also be any other network, including but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network, or any combination of a virtual private network. In some embodiments, data exchanged via the network is represented using technologies and / or formats such as Hypertext Markup Language (HTML) and Extensible Markup Language (XML).

[0049] A server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0050] The terminal may be, but is not limited to, an industrial robot, a service robot, a smart home device, an environmental monitoring terminal, a drone, smart glasses, a car, a smartphone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc. The terminal and the server may be connected directly or indirectly via wired or wireless communication, which is not limited in this application.

[0051] Those skilled in the art will know that Figure 1 The number of terminals and servers in the example is merely illustrative, and any number of terminals and servers may be used according to actual needs. This disclosure does not limit this.

[0052] This exemplary implementation is described in detail below with reference to the accompanying drawings and examples.

[0053] An embodiment of the present disclosure provides a data processing method, which can be executed by any electronic device with computing and processing capabilities.

[0054] Figure 3 A flow chart of a data processing method according to an embodiment of the present disclosure is shown as follows: Figure 3 As shown, applied to a terminal, the data processing method provided in the embodiment of the present disclosure includes the following S301 to S305.

[0055] S301. Send a model discovery request to the server, where the model discovery request includes a first identifier and business requirements, so that the server determines a second identifier based on the first identifier and business requirements, and send a model configuration request to the artificial intelligence platform, so that the artificial intelligence platform initializes the artificial intelligence model. The model configuration request includes a first identifier, a second identifier, and business requirements. The first identifier is used to indicate a terminal that has completed registration with the server, and the second identifier is used to indicate an artificial intelligence model that matches the business requirements.

[0056] In the disclosed embodiment, a terminal sends a registration request to a server. If the terminal meets the requirements, the server assigns a first identifier to the terminal. It should be noted that the terminal is configured with a perception-enabling client for performing perception functions. The terminal's perception-enabling client (SEC) collects the client's service requirements (for example, the user's raw perception data is video, audio, image, electromagnetic waves, etc., which requires identification, judgment, or classification by an AI model) and analyzes it to obtain the user's raw data type, the AI model's task type, data volume, and network status. It then sends a model discovery request to the server.

[0057] In the embodiments of this disclosure, a model discovery request is a request for the server to trigger the model discovery process. A business requirement refers to the need to process, analyze, identify, judge, or classify a user's raw sensory data (such as video, audio, images, electromagnetic waves, etc.) using an artificial intelligence model in a specific application scenario. The embodiments of this disclosure do not specifically define the specific nature of a business requirement.

[0058] For example, business requirements may include user model requirements, which may include one or more of the following: required model type, business type, software and hardware configuration, data resources, and data volume. The required model type may include perception, recognition, and prediction. The business type may include perception, recognition, and prediction. The software and hardware configuration may include the user's local computing resources and network status.

[0059] For example, business requirements may include the user's original data type, the AI model's task type, data volume, and network conditions.

[0060] In the embodiment of the present disclosure, after the artificial intelligence platform receives the model configuration request sent by the server, it initializes the artificial intelligence model according to the model configuration request.

[0061] S302, receiving the model discovery response information sent by the server, the model discovery response information carries the second identifier, the model discovery response information is sent by the server to the terminal after receiving the configuration completion information sent by the artificial intelligence platform, and the configuration completion information is sent by the artificial intelligence platform to the server after completing the initialization of the artificial intelligence model.

[0062] In the disclosed embodiment, the model discovery response information is used to indicate that the initialization of the artificial intelligence model is complete. When the terminal receives the model discovery response information sent by the server, it indicates that the artificial intelligence platform has completed the initialization of the artificial intelligence model that matches the business requirements.

[0063] S303: Send a data submission request to the server, where the data submission request includes a first identifier and a second identifier, so that the server establishes a data channel according to the first identifier and the second identifier.

[0064] In the disclosed embodiments, a data submission request may be used to indicate that a terminal is preparing to send data to an artificial intelligence platform. It should be noted that the server may be a server deployed on a core network. Based on a first identifier indicating the terminal and a second identifier indicating the artificial intelligence model, a data channel may be established between the terminal and the artificial intelligence model, or between the terminal and the artificial intelligence platform, to enable the transmission of perception data, thereby preventing data congestion and blocking and increasing data transmission speed.

[0065] S304: Send the data to be processed to the artificial intelligence platform based on the data channel, so that the artificial intelligence platform processes the data to be processed using the artificial intelligence model corresponding to the second identifier.

[0066] In the embodiment of the present disclosure, in order to improve the security of data, the data to be processed is encrypted before being sent.

[0067] For example, before sending the data to be processed to the artificial intelligence platform via the data channel, the data processing method provided by the present disclosure may further include: encrypting and / or compressing the data to be processed. By encrypting and / or compressing the data to be processed locally on the synaesthesia user, the present disclosure can ensure the confidentiality and security of the synaesthesia user's data.

[0068] S305: Receive data analysis results sent by the artificial intelligence platform.

[0069] In the embodiments of this disclosure, the data analysis result is the recognition result obtained by the artificial intelligence model after analyzing the data to be processed. The embodiments of this disclosure do not specifically limit the specific type of recognition result. For example, the recognition result can be the recognition result of the user's locally perceived image or the analysis result of the spectrum.

[0070] The disclosed embodiments utilize a matched AI model to process the data to be processed, meeting the processing requirements for multiple types of feature data. Furthermore, by establishing a data channel between the terminal and the AI platform to transmit the data to be processed, data congestion and blockage can be prevented, and data transmission speed can be increased.

[0071] It should be noted that the disclosed embodiments improve the application layer architecture of synaesthesia integration, encrypting and / or compressing the data to be processed locally on the synaesthesia user to prevent data leakage. In other words, the user device performs preliminary processing (such as compression and encryption) on the perception data, enhancing the confidentiality and security of the data.

[0072] The following describes how a terminal registers on a server through exemplary embodiments.

[0073] In an exemplary embodiment, before sending the model discovery request to the server, the data processing method provided by the present disclosure may further include the following steps A1 and A2.

[0074] Step A1: Send a registration request to the server, which carries terminal information and application information, so that the server responds that the terminal is a legitimate user, configures a first identifier and a user configuration table for the terminal, and sends a registration response message to the terminal.

[0075] In the embodiments of the present disclosure, terminal information refers to the hardware information of the terminal. For example, the hardware information may include the user's hardware configuration and / or MAC address. The hardware configuration may include the configuration of the terminal's hard disk, memory, etc. Application information may include software configuration information. For example, the software configuration information may include the IP address and / or application information.

[0076] In the embodiment of the present disclosure, the server determines whether the terminal is a legitimate user. If the terminal is a legitimate user, the server configures the first identifier and the user configuration table for the terminal. The embodiment of the present disclosure does not specifically limit how the server determines whether the terminal is a legitimate user.

[0077] For example, the SEC is integrated with the terminal. When the terminal powers on and registers with the network, it provides the network with its identity information (such as its MAC address). The network then assigns the SEC a Subscription Concealed Identifier (SUCI). Thus, the SEC's identity information is bound to the SUCI assigned by the network. When the server verifies the legitimacy of the terminal, it searches the network for the SEC's identity information. If it finds the corresponding SUCI, the terminal is authenticated. Otherwise, the terminal is illegitimate. It should be noted that if the server verifies the terminal is legitimate, it sends a Registration Response message to the terminal. If the server verifies the terminal is illegitimate, it sends a Registration Failure message to the terminal.

[0078] In the embodiments of the present disclosure, the user configuration table is used to store and manage various user-related information. The embodiments of the present disclosure do not specifically limit the specific content included in the user configuration table. For example, the user configuration table includes software information and hardware information. Software information includes the software name, IP address, and network status. Hardware information may include the user's hardware configuration parameters and MAC address. Hardware information may also include information related to the user's local computing resources. For example, information such as the terminal's hard disk, memory, and processor performance.

[0079] Step A2: Receive a registration response message sent by the server, where the registration response message includes a first identifier.

[0080] In the embodiment of the present disclosure, a registration request is sent from a terminal to a server, so that the server determines whether the terminal is legitimate based on the information carried in the registration request. If the terminal is a legitimate user, a registration response message is sent to the terminal. The server determines whether the terminal is legitimate, which can effectively prevent the access of illegal terminals, ensure the security of the system, improve the user experience, and facilitate subsequent service optimization and system maintenance.

[0081] Based on the same inventive concept, the present disclosure also provides a data processing method, as described in the following embodiment. Since the principle of solving the problem in this method embodiment is similar to that in the above method embodiment, the repeated parts will not be repeated.

[0082] Figure 4 A flow chart of a data processing method according to another embodiment of the present disclosure is shown as follows: Figure 4 As shown, applied to a server, the data processing method provided in the embodiment of the present disclosure may include the following S401 to S407.

[0083] S401: Receive a model discovery request sent by a terminal, where the model discovery request includes a first identifier and a service requirement.

[0084] In an embodiment of the present disclosure, a model discovery request is a request for a server to trigger a model discovery process. Exemplarily, the model discovery request includes a first identifier and a business requirement. The business requirement may include one or more of the required model type, business type, user hardware and software configuration, data resources, and data volume. The required model type may include a regression model, a convolutional model, or a large-scale language model (LLM). Business types may include perception, recognition, and prediction. The user's hardware and software configuration may include the user's local computing resources and network status.

[0085] S402: Determine a second identifier based on the first identifier and business requirements.

[0086] In the embodiment of the present disclosure, the first identifier is used to indicate a terminal that has completed registration with the server, and the second identifier is used to indicate an artificial intelligence model that matches the business requirements.

[0087] In the embodiment of the present disclosure, information of all or part of the artificial intelligence model on the artificial intelligence platform is stored on the server. The business requirements of the terminal corresponding to the first identifier are matched with the information of the artificial intelligence model to obtain an identifier of the artificial intelligence model that is adapted to the business requirements (i.e., the second identifier).

[0088] The present disclosure does not limit the specific information about the AI model. For example, the AI model information may include one or more of the data type, data volume, data processing speed, task type, and network status that the AI model can process.

[0089] S403: Send a model configuration request to the artificial intelligence platform, so that the artificial intelligence platform initializes the artificial intelligence model according to the model configuration request. The model configuration request includes a first identifier, a second identifier, and business requirements.

[0090] In one embodiment, the artificial intelligence platform can determine the configuration parameters of the AI model based on business requirements and the second identifier, and the artificial intelligence platform initializes the artificial intelligence model based on the configuration parameters of the AI model.

[0091] It should be noted that the AI platform's initialization of the AI model based on the model configuration request may include one or more of content initialization, hardware initialization, and pre-trained parameter initialization. Content initialization refers to the initialization of the AI model's architecture. The same type of AI model may have different architectures. For example, a transformer model (a deep learning model) may stack multiple identical modules, with a variable number of modules. The resulting neural network structure varies, and the number of modules depends on the user's business needs. In other words, the configuration parameters of the AI model may include the number of modules.

[0092] S404, receiving the configuration completion information sent by the artificial intelligence platform. The configuration completion information is sent by the artificial intelligence platform to the server after completing the initialization of the artificial intelligence model.

[0093] S405: Send model discovery response information to the terminal, where the model discovery response information carries the second identifier.

[0094] S406: Receive a data submission request sent by the terminal, where the data submission request includes a first identifier and a second identifier.

[0095] In an embodiment of the present disclosure, the server may be a server deployed on a core network. Based on a first identifier for indicating a terminal and a second identifier for indicating an artificial intelligence model, a data channel may be established between the terminal and the artificial intelligence model, or a data channel may be established between the terminal and the artificial intelligence platform to enable the transmission of perception data, prevent data congestion and blockage, and increase the data transmission speed.

[0096] For example, through the close cooperation between SMF and UPF, the core network can dynamically establish and configure data channels to provide user equipment with high-speed, low-latency data transmission capabilities.

[0097] S407: Establish a data channel according to the data submission request, so that the terminal sends the data to be processed to the artificial intelligence platform based on the data channel. The artificial intelligence platform uses the artificial intelligence model corresponding to the second identifier to process the data to be processed and sends the data analysis results to the terminal.

[0098] In the disclosed embodiment, the server determines a second identifier based on the first identifier and the business requirements, thereby determining a matching artificial intelligence model based on the second identifier. The server then initializes the artificial intelligence model based on the business requirements and uses the initialized artificial intelligence model to process the data to be processed, thereby meeting the processing requirements for multiple types of feature data. Furthermore, by establishing a data channel between the terminal and the artificial intelligence platform to transmit the data to be processed, data congestion and blockage can be prevented, and data transmission speed can be increased.

[0099] The present disclosure is described below through several exemplary embodiments.

[0100] In an exemplary embodiment, before receiving the model discovery request sent by the terminal, the data processing method provided by the present disclosure may also include: receiving a registration request sent by the terminal, the registration request carrying terminal information and application information; determining whether the terminal is a legitimate user based on the registration request; in response to the terminal being a legitimate user, configuring a first identifier and a user configuration table for the terminal; and sending a registration response message to the terminal.

[0101] In the embodiment of the present disclosure, the server receives a registration request sent by a terminal, determines whether the terminal is legitimate based on the information carried in the registration request, and sends a registration response message to the terminal if the terminal is a legitimate user. By having the server determine whether the terminal is legitimate, it can effectively prevent illegal terminals from accessing the system, ensure the security of the system, improve the user experience, and help with subsequent service optimization and system maintenance.

[0102] In another exemplary embodiment, the data processing method provided by the present disclosure may include determining the second identifier according to the first identifier and business requirements, including the following steps B1 and B2.

[0103] Step B1: Use the first identifier to verify whether the terminal is legitimate.

[0104] In the disclosed embodiment, after receiving the first identifier carried in the model discovery request sent by the terminal, the server determines whether the first identifier is stored on the server. If so, it indicates that the terminal is legal and meets the requirements. Otherwise, if not, it indicates that the terminal is illegal and does not meet the requirements.

[0105] The embodiments of the present disclosure can prevent the terminal from being forged by verifying the identity of the terminal.

[0106] Step B2: In response to the terminal being legal, a second identifier is determined according to business requirements.

[0107] In the embodiment of the present disclosure, the identifier (second identifier) of the artificial intelligence model that matches the business requirements is queried based on the business requirements.

[0108] The disclosed embodiment determines whether a terminal is legitimate through a server, which can effectively prevent access by illegal terminals, ensure the security of the system, improve user experience, and facilitate subsequent service optimization and system maintenance.

[0109] In another exemplary embodiment, the data submission request may further include channel requirement information. In the data processing method provided by the present disclosure, establishing a data channel according to the data submission request may include: establishing the data channel according to the first identifier, the second identifier, and the channel requirement information.

[0110] In the embodiment of the present disclosure, the channel requirement information is information related to establishing a data channel. For example, the channel requirement information may include the type, amount, and rate requirement of the transmitted data.

[0111] The server matches the artificial intelligence model corresponding to the first identifier based on the second identifier. It should be noted that after each match, a data channel is established for training. After the service is completed, the data channel needs to be released, and a new data channel will be established for the next match. By releasing the data channel and re-establishing a new channel, the disclosed embodiment can maintain high efficiency, flexibility, and security, ensuring the rational use of resources and stable operation of the service.

[0112] In the embodiment of the present disclosure, the data channel established through the channel demand information better meets the requirements of the data transmission to be processed, thereby improving the speed of data transmission.

[0113] Based on the same inventive concept, the present disclosure also provides a data processing method, as described in the following embodiment. Since the principle of solving the problem in this method embodiment is similar to that in the above method embodiment, the implementation of this method embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0114] Figure 5 A flow chart of a data processing method according to another embodiment of the present disclosure is shown as follows: Figure 5 As shown, applied to an artificial intelligence platform, the data processing method provided in the embodiment of the present disclosure may include the following S501 to S506.

[0115] S501, receiving a model configuration request sent by the server, the model configuration request includes a first identifier, a second identifier and business requirements, the first identifier is used to indicate a terminal that has completed registration with the server, and the second identifier is used to indicate an artificial intelligence model that matches the business requirements.

[0116] S502: Initialize the artificial intelligence model according to the model configuration request.

[0117] Exemplarily, the data processing method provided by the present disclosure may include initializing the artificial intelligence model according to the model configuration request, which may include: determining the artificial intelligence model of the terminal corresponding to the first identifier according to the second identifier; and initializing the artificial intelligence model according to business needs.

[0118] In the embodiment of the present disclosure, the artificial intelligence platform can determine the configuration parameters of the AI model according to business needs, and the artificial intelligence platform initializes the artificial intelligence model according to the configuration parameters of the AI model.

[0119] The disclosed embodiment determines the AI model through the second identifier, determines the configuration parameters of the AI model through business requirements, completes the initialization of the AI model according to the configuration parameters, and processes the data to be processed by the initialized artificial intelligence model, which can further meet the processing requirements of multiple types of feature data.

[0120] S503: Send configuration completion information to the server.

[0121] S504: Receive the data to be processed sent by the terminal based on a data channel, where the data channel is established by the server according to the first identifier and the second identifier.

[0122] S505: Process the data to be processed using the artificial intelligence model corresponding to the second identifier to obtain a data analysis result.

[0123] S506: Send the data analysis result to the terminal.

[0124] In the disclosed embodiments, the artificial intelligence platform receives a model configuration request from a server, initializes the artificial intelligence model based on the model configuration request, and uses the initialized artificial intelligence model to process the data to be processed, thereby meeting the processing requirements of multiple types of feature data. Furthermore, by transmitting the data to be processed through a data channel established between the terminal and the artificial intelligence platform, data congestion and blockage can be prevented, and data transmission speed can be increased.

[0125] The present disclosure is further described below through two exemplary embodiments.

[0126] In an exemplary embodiment, before receiving the data to be processed sent by the terminal based on the data channel, the data processing method provided by the present disclosure may further include the following steps C1 to C3.

[0127] Step C1: receiving training data and labels sent by the terminal, where the labels are used to identify and classify the training data.

[0128] In the disclosed embodiments, training data refers to sensory data collected by the terminal. This training data is used to fine-tune the AI model. Labels refer to the classification or marking of each piece of training data. For example, in image recognition, it is necessary to mark the bounding boxes and classifications of multiple objects in an image. These bounding boxes and classifications are called labels.

[0129] It should be noted that training data refers to processed data, and labels also refer to processed labels. For example, the training data and labels may be compressed and / or encrypted. Because processed perception data is used for model training, both the processed data (training data) and labels must be uploaded. Data processing is used to maintain confidentiality, while labels are used to identify and classify data.

[0130] Step C2: fine-tune the model parameters of the artificial intelligence model based on the training data and labels.

[0131] The disclosed embodiments do not specifically limit how to fine-tune the AI model using training data and labels. For example, the model parameters of the AI model can be fine-tuned based on the training data and labels using a loss function. Repeated training is performed until the loss function value is less than a loss threshold, which is set based on the application scenario and specific application experience.

[0132] It's important to note that once the AI model is initialized, it can begin perception and recognition. However, since the data used for AI model training is large-scale, the distribution of the model may not match the user's local perception data. Therefore, fine-tuning is required based on the training data and labels uploaded by the user. Fine-tuning allows for detailed optimization of the AI model based on specific user data and labels, enabling it to more accurately handle specific tasks and improve the accuracy and reliability of data analysis results. It also plays a significant role in conserving computing resources and increasing efficiency.

[0133] It should be noted that the data submitted for fine-tuning the model refers to the training data and labels processed locally by the user.

[0134] It should be noted that users match and select customized AI models through the core network, and fine-tune the AI models using their local encrypted training data and labels to match the user's data distribution characteristics and gain the ability to analyze the user's encrypted data. In other words, the disclosed embodiments improve the AI model matching and selection process, while also fine-tuning the model based on the user's existing data (training data) and labels, enabling the AI platform to perform specific analysis on the data provided by the user.

[0135] Step C3: Send model fine-tuning completion information to the terminal, so that the terminal sends the data to be processed to the artificial intelligence platform based on the data channel.

[0136] The disclosed embodiment locally compresses and encrypts user perception data, and uploads existing training data and labels for fine-tuning and pre-training of remote AI models, which can improve the accuracy and reliability of data analysis results.

[0137] In another exemplary embodiment, the data processing method provided by the present disclosure may also include: using an artificial intelligence model to perform data analysis on the data to be processed to obtain network basic information of the terminal location; sending the network basic information to the network open function network element so that the network data analysis function network element optimizes the network according to the network basic information.

[0138] In the embodiments of the present disclosure, the present disclosure does not specifically limit the type of analysis performed by the artificial intelligence model on the data to be processed. For example, the data to be processed is configuration information submitted by the terminal, and the network status, data type, and data volume of the configuration information are analyzed.

[0139] In the embodiments of the present disclosure, network basic information refers to information related to the network. The embodiments of the present disclosure do not specifically limit what kind of information the network basic information is. For example, network basic information may include user density, data throughput, and channel conditions in a certain area.

[0140] In the disclosed embodiments, a server sends basic network information to an NEF network element, enabling the NWDAF network element to optimize the network based on this information. The NEF network element serves as a conduit for communication within and outside the core network. The core network needs to expose network information or collect application layer information through the NEF network element. For example, the NWDAF network element can use this basic network information to predict network data volume, user statistics and regression predictions, and network congestion predictions. This information can be used within the core network to provide early warning and avoidance of congestion.

[0141] It should be noted that the perception process in the related technology does not involve the extraction of network information. The embodiment of the present disclosure adds the analysis and extraction of basic network information. Therefore, the analyzed information can be submitted to the core network through the NEF network element to improve the network environment of this user or other users.

[0142] It should be noted that, in the embodiment of the present disclosure, the server can send network basic information to the network open function network element, so that the network data analysis function network element optimizes the network according to the network basic information.

[0143] The disclosed embodiments add a new process for AI model analysis of user data to optimize the network. The analyzed network basic information is shared with the network, realizing an integrated architecture and process for data perception transmission, network analysis, and network optimization. In other words, after the AI platform processes user perception data through a deep neural network, it also generates corresponding network basic information, which is fed back to the core network and base stations to optimize the network environment.

[0144] The present disclosure is further described below through several embodiments.

[0145] In one embodiment, Figure 6 As shown, the data processing method provided by the present disclosure may include the following S601 to S604.

[0146] S601: The terminal sends a registration request to the server, which carries terminal information and application information.

[0147] S602: The server determines whether the terminal is a legitimate user according to the registration request.

[0148] S603: In response to the terminal being a legitimate user, configure a first identifier and a user configuration table for the terminal.

[0149] S604: The server sends a registration response message to the terminal.

[0150] The disclosed embodiment determines whether a terminal is legitimate through a server, which can effectively prevent access by illegal terminals, ensure the security of the system, improve user experience, and facilitate subsequent service optimization and system maintenance.

[0151] In another embodiment, Figure 7 As shown, the data processing method provided by the present disclosure may include the following S701 to S706.

[0152] S701: The terminal sends a model discovery request to the server, where the model discovery request includes a first identifier and a service requirement.

[0153] S702: The server determines a second identifier according to the first identifier and service requirements.

[0154] S703: The server sends a model configuration request to the artificial intelligence platform.

[0155] S704, the artificial intelligence platform initializes the artificial intelligence model according to the model configuration request.

[0156] S705, the artificial intelligence platform sends configuration completion information to the server.

[0157] S706: The server sends model discovery response information to the terminal, where the model discovery response information carries the second identifier.

[0158] The server of the embodiment of the present disclosure determines the second identifier based on the first identifier and business requirements, thereby determining a matching artificial intelligence model based on the second identifier, and initializes the artificial intelligence model according to business requirements to realize data processing of the data to be processed using the initialized artificial intelligence model, thereby meeting the processing requirements of multiple types of feature data.

[0159] In yet another embodiment, Figure 8 As shown, the data processing method provided by the present disclosure may include the following S801 to S808.

[0160] S801: The terminal compresses and encrypts the training data and labels to prevent leakage during data transmission. It should be noted that the training data is data pre-processed by the terminal.

[0161] S802: The terminal sends a data submission request to the server. The data submission request includes a first identifier and a second identifier.

[0162] S803: The server establishes a data channel according to the data submission request.

[0163] S804: The terminal sends the compressed and encrypted training data and labels to the artificial intelligence platform based on the data channel.

[0164] S805, the artificial intelligence platform fine-tunes the artificial intelligence model based on the training data and labels.

[0165] S806: The terminal sends the data to be processed to the artificial intelligence platform via the data channel. For example, after fine-tuning the artificial intelligence model, the terminal is notified to perform real-time data transmission. The terminal sends the data to be processed to the artificial intelligence platform via the data channel. The data to be processed is data that has been locally compressed and encrypted by the terminal.

[0166] S807: The artificial intelligence platform processes the data to be processed using the artificial intelligence model corresponding to the second identifier to obtain a data analysis result.

[0167] S808, the artificial intelligence platform sends the data analysis results to the terminal.

[0168] The disclosed embodiment fine-tunes the AI model through training data and labels to match the user's data distribution characteristics, thereby improving the accuracy and reliability of data analysis results, and also plays an important role in saving computing resources and improving efficiency.

[0169] In yet another embodiment, Figure 9 As shown, the data processing method provided by the present disclosure may include the following S901 and S902.

[0170] S901, using an artificial intelligence model to analyze the data to be processed to obtain basic network information of the terminal location.

[0171] S902: Send network basic information to the network open function network element (NEF network element) so that the network data analysis function network element optimizes the network according to the network basic information. It should be noted that the network open function network element and the network data analysis function network element are connected via a network.

[0172] The artificial intelligence platform of the disclosed embodiment shares the analyzed network basic information with the network, realizing an integrated architecture and process of synaesthesia data perception transmission, network analysis, and network optimization.

[0173] In another embodiment, the terminal is a drone and the server is SES. Users use drones to scan the environment and collect information in the air. The data sensed includes photography, infrared cameras, radio signals, etc. Users register with SES through the network and search and match the required AI models according to business needs. The user's terminal locally stores some training data and labels with existing analysis results. After compressing and encrypting this data locally, the processed training data and labels are uploaded to the AI model deployed on the AI platform through a channel (data channel) specifically allocated for the inter-sensory service, allowing the AI model to be fine-tuned and pre-trained to adapt to its own specific data distribution.

[0174] After fine-tuning the model, users transmit data in real time through their assigned data channels, transferring the processed data to the AI platform via these channels. The AI model also provides the user with data analysis results. With user consent, the AI model shares the resulting network basic information (such as the number of users in the area, data throughput, and traffic rate) with the base station and core network via the NEF network element, enabling optimization of the user's network and the surrounding area.

[0175] Based on the same inventive concept, the present disclosure also provides a data processing device, as described in the following embodiments. Since the principle of solving the problem in the device embodiment is similar to that in the above method embodiment, the implementation of the device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0176] Figure 10 A schematic diagram of a data processing device according to an embodiment of the present disclosure is shown. Figure 10As shown, applied to a terminal, the data processing device includes a first sending module 1001 and a first receiving module 1002. The first sending module 1001 can be used to send a model discovery request to the server, the model discovery request including a first identifier and a business requirement, so that the server determines the second identifier based on the first identifier and the business requirement, and sends a model configuration request to the artificial intelligence platform, so that the artificial intelligence platform initializes the artificial intelligence model. The model configuration request includes the first identifier, the second identifier and the business requirement, the first identifier is used to indicate a terminal that has completed registration with the server, and the second identifier is used to indicate an artificial intelligence model that matches the business requirement; the first receiving module 1002 can be used to receive model discovery response information sent by the server, the model discovery response information carries the second identifier, the model discovery response information is sent by the server to the terminal after receiving the configuration completion information sent by the artificial intelligence platform, and the configuration completion information is sent by the artificial intelligence platform to the server after completing the initialization of the artificial intelligence model; the first sending module 1001 can also be used to send a data submission request to the server, the data submission request including the first identifier and the second identifier, so that the server establishes a data channel based on the first identifier and the second identifier; the first sending module 1001 can also be used to send to-be-processed data to the artificial intelligence platform based on the data channel, so that the artificial intelligence platform uses the artificial intelligence model corresponding to the second identifier to process the to-be-processed data; the first receiving module 1002 can also be used to receive data analysis results sent by the artificial intelligence platform.

[0177] In one embodiment, before sending a model discovery request to the server, the first sending module 1001 can also be used to send a registration request to the server, which carries terminal information and application information, so that the server responds that the terminal is a legitimate user, configures a first identifier and a user configuration table for the terminal, and sends a registration response message to the terminal; the first receiving module 1002 can also be used to receive a registration response message sent by the server, which includes the first identifier.

[0178] In one embodiment, before sending the data to be processed to the artificial intelligence platform based on the data channel, the first sending module 1001 can also be used to encrypt and / or compress the data to be processed.

[0179] The data processing device disclosed in the embodiments of the present disclosure processes the data to be processed using a matched artificial intelligence model, meeting the processing requirements of multiple types of feature data. Furthermore, by transmitting the data to be processed through a data channel established between the terminal and the artificial intelligence platform, data congestion and blockage can be prevented, and data transmission speed can be increased.

[0180] Figure 11 A schematic diagram of a data processing device according to an embodiment of the present disclosure is shown. Figure 11As shown, applied to a server, the data processing device includes a second sending module 1101 , a determining module 1102 , a second receiving module 1103 and a channel establishing module 1104 . The second sending module 1101 can be used to receive a model discovery request sent by the terminal, the model discovery request including a first identifier and a business requirement; the determination module 1102 can be used to determine the second identifier based on the first identifier and the business requirement; the second sending module 1101 can also be used to send a model configuration request to the artificial intelligence platform, so that the artificial intelligence platform initializes the artificial intelligence model according to the model configuration request, the model configuration request including the first identifier, the second identifier and the business requirement; the second receiving module 1103 can be used to receive configuration completion information sent by the artificial intelligence platform, and the configuration completion information is sent by the artificial intelligence platform to the server after completing the initialization of the artificial intelligence model; the second sending module 1101 can also be used to send model discovery response information to the terminal, the model discovery response information carries the second identifier; the second receiving module 1103 can also be used to receive a data submission request sent by the terminal, the data submission request including the first identifier and the second identifier; the channel establishment module 1104 can be used to establish a data channel according to the data submission request, so that the terminal sends the data to be processed to the artificial intelligence platform based on the data channel, and the artificial intelligence platform uses the artificial intelligence model corresponding to the second identifier to process the data to be processed and sends the data analysis results to the terminal.

[0181] In one embodiment, before receiving the model discovery request sent by the terminal, the second receiving module 1103 can also be used to receive a registration request sent by the terminal, which carries terminal information and application information; determine whether the terminal is a legitimate user based on the registration request; in response to the terminal being a legitimate user, configure a first identifier and a user configuration table for the terminal; and send a registration response message to the terminal.

[0182] In one embodiment, the determination module 1102 may also be configured to use the first identifier to verify whether the terminal is legitimate; and in response to the terminal being legitimate, determine the second identifier according to business requirements.

[0183] In one embodiment, the data submission request further includes channel requirement information; the channel establishment module 1104 may also be configured to establish a data channel according to the first identifier, the second identifier, and the channel requirement information.

[0184] The data processing device disclosed in the embodiments of the present disclosure processes the data to be processed using a matched artificial intelligence model, meeting the processing requirements of multiple types of feature data. Furthermore, by transmitting the data to be processed through a data channel established between the terminal and the artificial intelligence platform, data congestion and blockage can be prevented, and data transmission speed can be increased.

[0185] Figure 12A schematic diagram of a data processing device according to an embodiment of the present disclosure is shown. Figure 12 As shown, the data processing device is applied to an artificial intelligence platform and includes a third receiving module 1201, an initialization module 1202, a third sending module 1203, and a processing module 1204. The third receiving module 1201 can be used to receive a model configuration request sent by a server, the model configuration request including a first identifier, a second identifier, and a business requirement, the first identifier being used to indicate a terminal that has completed registration with the server, and the second identifier being used to indicate an artificial intelligence model that matches the business requirement; the initialization module 1202 can be used to initialize the artificial intelligence model according to the model configuration request; the third sending module 1203 can be used to send configuration completion information to the server; the third receiving module 1201 can also be used to receive data to be processed sent by the terminal based on a data channel, the data channel being established by the server based on the first identifier and the second identifier; the processing module 1204 can be used to process the data to be processed using the artificial intelligence model corresponding to the second identifier to obtain a data analysis result; the third sending module 1203 can also be used to send the data analysis result to the terminal.

[0186] In one embodiment, the initialization module 1202 can also be used to determine the artificial intelligence model of the terminal corresponding to the first identifier based on the second identifier; and initialize the artificial intelligence model according to business needs.

[0187] In one embodiment, before receiving the data to be processed sent by the terminal based on the data channel, the data processing device also includes a fine-tuning module (not shown in the figure), which is used to receive training data and labels sent by the terminal, and the labels are used to identify and classify the training data; fine-tune the model parameters of the artificial intelligence model according to the training data and labels; and send model fine-tuning completion information to the terminal, so that the terminal sends the data to be processed to the artificial intelligence platform based on the data channel.

[0188] In one embodiment, the processing module 1204 can also be used to use an artificial intelligence model to perform data analysis on the data to be processed to obtain network basic information of the terminal location; and send the network basic information to the network open function network element so that the network data analysis function network element optimizes the network according to the network basic information.

[0189] The data processing device disclosed in the embodiments of the present disclosure processes the data to be processed using a matched artificial intelligence model, meeting the processing requirements of multiple types of feature data. Furthermore, by transmitting the data to be processed through a data channel established between the terminal and the artificial intelligence platform, data congestion and blockage can be prevented, and data transmission speed can be increased.

[0190] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods, or program products. Therefore, various aspects of the present disclosure may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, microcode, etc.), or in a combination of hardware and software, collectively referred to herein as "circuits," "modules," or "systems."

[0191] Refer to the following Figure 13 1300 according to this embodiment of the present disclosure will be described. Figure 13 The electronic device 1300 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0192] like Figure 13 As shown, electronic device 1300 is implemented as a general-purpose computing device. Components of electronic device 1300 may include, but are not limited to, the aforementioned at least one processing unit 1310, the aforementioned at least one storage unit 1320, and a bus 1330 connecting various system components (including storage unit 1320 and processing unit 1310).

[0193] The storage unit stores program codes, which can be executed by the processing unit 1310, so that the processing unit 1310 performs the steps described in the above “Exemplary Method” section of this specification according to various exemplary embodiments of the present disclosure.

[0194] The storage unit 1320 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 13201 and / or a cache memory unit 13202 , and may further include a read-only memory unit (ROM) 13203 .

[0195] The storage unit 1320 may also include a program / utility 13204 having a set (at least one) of program modules 13205, such program modules 13205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0196] Bus 1330 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0197] Electronic device 1300 can also communicate with one or more external devices 1340 (e.g., a keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with electronic device 1300, and / or any device that enables electronic device 1300 to communicate with one or more other computing devices (e.g., a router, modem, etc.). This communication can occur via input / output (I / O) interface 1350. Furthermore, electronic device 1300 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via network adapter 1360. As shown, network adapter 1360 communicates with other modules of electronic device 1300 via bus 1330. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with electronic device 1300, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0198] Through the description of the above embodiments, it will be readily understood by those skilled in the art that the example embodiments described herein can be implemented via software or via a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or mobile hard drive) or on a network and includes several instructions for enabling a computing device (such as a personal computer, server, terminal device, or network device) to execute the methods according to the embodiments of the present disclosure.

[0199] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is further provided, which may be a readable signal medium or a readable storage medium, storing a program product capable of implementing the above method of the present disclosure.

[0200] In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of various exemplary implementations of the present disclosure described in the above "Specific Implementation Methods" section of this specification.

[0201] More specific examples of computer-readable storage media in the present disclosure may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0202] In the present disclosure, a computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein a readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. Alternatively, the program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0203] In a specific implementation, the program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, and conventional procedural programming languages such as C or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0204] The present disclosure provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the data processing method provided in any of the various optional embodiments of the present disclosure.

Claims

1. A data processing method, characterized in that: Applied to a terminal, the data processing method includes: Sending a model discovery request to a server, the model discovery request including a first identifier and a business requirement, so that the server determines a second identifier based on the first identifier and the business requirement, and sending a model configuration request to an artificial intelligence platform, so that the artificial intelligence platform initializes an artificial intelligence model, the model configuration request including the first identifier, the second identifier, and the business requirement, the first identifier being used to indicate a terminal that has completed registration with the server, and the second identifier being used to indicate an artificial intelligence model that matches the business requirement; receiving a model discovery response message sent by the server, the model discovery response message carrying the second identifier, the model discovery response message being sent by the server to the terminal after receiving configuration completion information sent by the artificial intelligence platform, and the configuration completion information being sent by the artificial intelligence platform to the server after completing initialization of the artificial intelligence model; Sending a data submission request to the server, where the data submission request includes the first identifier and the second identifier, so that the server establishes a data channel according to the first identifier and the second identifier; sending the data to be processed to the artificial intelligence platform based on the data channel, so that the artificial intelligence platform processes the data to be processed using the artificial intelligence model corresponding to the second identifier; Receive the data analysis results sent by the artificial intelligence platform.

2. The data processing method according to claim 1, wherein: Before sending the model discovery request to the server, the method further includes: Sending a registration request to the server, where the registration request carries terminal information and application information, so that the server responds that the terminal is a legitimate user, configures the first identifier and user configuration table for the terminal, and sends a registration response message to the terminal; The registration response message sent by the server is received, where the registration response message includes the first identifier.

3. The data processing method according to claim 1, wherein: Before sending the data to be processed to the artificial intelligence platform based on the data channel, the method further includes: The data to be processed is encrypted and / or compressed.

4. A data processing method, characterized in that: Applied to a server, the data processing method includes: receiving a model discovery request sent by a terminal, where the model discovery request includes a first identifier and a service requirement; Determine a second identifier based on the first identifier and the business requirement; Sending a model configuration request to the artificial intelligence platform, so that the artificial intelligence platform initializes the artificial intelligence model according to the model configuration request, the model configuration request including the first identifier, the second identifier, and the business requirement; Receiving configuration completion information sent by the artificial intelligence platform, wherein the configuration completion information is sent by the artificial intelligence platform to the server after completing the initialization of the artificial intelligence model; Sending a model discovery response message to the terminal, where the model discovery response message carries the second identifier; receiving a data submission request sent by the terminal, where the data submission request includes the first identifier and the second identifier; A data channel is established according to the data submission request, so that the terminal sends the data to be processed to the artificial intelligence platform based on the data channel, and the artificial intelligence platform uses the artificial intelligence model corresponding to the second identifier to process the data to be processed and sends the data analysis results to the terminal.

5. The data processing method according to claim 4, characterized in that: Before receiving the model discovery request sent by the terminal, the method further includes: receiving a registration request sent by the terminal, wherein the registration request carries terminal information and application information; determining whether the terminal is a legitimate user according to the registration request; In response to the terminal being a legitimate user, configuring the first identifier and a user configuration table for the terminal; Sending a registration response message to the terminal.

6. The data processing method according to claim 4, characterized in that: The determining the second identifier according to the first identifier and the service requirement includes: Verifying whether the terminal is legitimate using the first identifier; In response to the terminal being legal, a second identifier is determined according to the service requirement.

7. The data processing method according to claim 4, characterized in that: The data submission request also includes channel requirement information; The step of establishing a data channel according to the data submission request includes: The data channel is established according to the first identifier, the second identifier, and the channel requirement information.

8. A data processing method, characterized in that: Applied to an artificial intelligence platform, the data processing method includes: Receive a model configuration request sent by a server, the model configuration request including a first identifier, a second identifier, and a business requirement, the first identifier being used to indicate a terminal that has completed registration with the server, and the second identifier being used to indicate an artificial intelligence model that matches the business requirement; Initializing the artificial intelligence model according to the model configuration request; Sending configuration completion information to the server; receiving, based on a data channel, data to be processed sent by the terminal, the data channel being established by the server according to the first identifier and the second identifier; Performing data processing on the data to be processed using the artificial intelligence model corresponding to the second identifier to obtain a data analysis result; Sending the data analysis result to the terminal.

9. The data processing method according to claim 8, characterized in that: Initializing the artificial intelligence model according to the model configuration request includes: Determining, based on the second identifier, an artificial intelligence model of the terminal corresponding to the first identifier; Initialize the artificial intelligence model according to the business requirements.

10. The data processing method according to claim 8, characterized in that: Before receiving the data to be processed sent by the terminal based on the data channel, the method further includes: receiving training data and a label sent by the terminal, wherein the label is used to identify and classify the training data; Fine-tuning model parameters of the artificial intelligence model based on the training data and labels; Send model fine-tuning completion information to the terminal, so that the terminal sends the data to be processed to the artificial intelligence platform based on the data channel.

11. The data processing method according to claim 8, characterized in that: The method further comprises: Performing data analysis on the data to be processed using the artificial intelligence model to obtain basic network information of the location of the terminal; The network basic information is sent to the network open function network element, so that the network data analysis function network element optimizes the network according to the network basic information.

12. A data processing device, characterized in that: Applied to terminals, including: A first sending module, configured to send a model discovery request to a server, the model discovery request including a first identifier and a business requirement, so that the server determines a second identifier based on the first identifier and the business requirement, and send a model configuration request to an artificial intelligence platform, so that the artificial intelligence platform initializes an artificial intelligence model, the model configuration request including the first identifier, the second identifier, and the business requirement, the first identifier being used to indicate a terminal that has completed registration with the server, and the second identifier being used to indicate an artificial intelligence model that matches the business requirement; a first receiving module, configured to receive a model discovery response message sent by the server, the model discovery response message carrying the second identifier, the model discovery response message being sent by the server to the terminal after receiving configuration completion information sent by the artificial intelligence platform, and the configuration completion information being sent by the artificial intelligence platform to the server after completing initialization of the artificial intelligence model; The first sending module is further configured to send a data submission request to the server, wherein the data submission request includes the first identifier and the second identifier, so that the server establishes a data channel according to the first identifier and the second identifier; The first sending module is further configured to send the data to be processed to the artificial intelligence platform based on the data channel, so that the artificial intelligence platform processes the data to be processed using the artificial intelligence model corresponding to the second identifier; The first receiving module is further used to receive the data analysis results sent by the artificial intelligence platform.

13. A data processing device, characterized in that: Applicable to servers, including: A second sending module is configured to receive a model discovery request sent by a terminal, where the model discovery request includes a first identifier and a service requirement; a determination module, configured to determine a second identifier based on the first identifier and the service requirement; The second sending module is further configured to send a model configuration request to the artificial intelligence platform, so that the artificial intelligence platform initializes the artificial intelligence model according to the model configuration request, wherein the model configuration request includes the first identifier, the second identifier, and the business requirement; a second receiving module, configured to receive configuration completion information sent by the artificial intelligence platform, wherein the configuration completion information is sent by the artificial intelligence platform to the server after completing initialization of the artificial intelligence model; The second sending module is further configured to send model discovery response information to the terminal, where the model discovery response information carries the second identifier; The second receiving module is further configured to receive a data submission request sent by the terminal, where the data submission request includes the first identifier and the second identifier; A channel establishment module is used to establish a data channel according to the data submission request, so that the terminal sends the data to be processed to the artificial intelligence platform based on the data channel, and the artificial intelligence platform uses the artificial intelligence model corresponding to the second identifier to process the data to be processed and send the data analysis results to the terminal.

14. A data processing device, characterized in that: Applied to artificial intelligence platforms, including: a third receiving module, configured to receive a model configuration request sent by the server, the model configuration request including a first identifier, a second identifier, and a business requirement, the first identifier being used to indicate a terminal that has completed registration with the server, and the second identifier being used to indicate an artificial intelligence model that matches the business requirement; An initialization module, configured to initialize the artificial intelligence model according to the model configuration request; A third sending module is used to send configuration completion information to the server; The third receiving module is further configured to receive the data to be processed sent by the terminal based on a data channel, where the data channel is established by the server according to the first identifier and the second identifier; a processing module, configured to process the data to be processed using the artificial intelligence model corresponding to the second identifier to obtain a data analysis result; The third sending module is further configured to send the data analysis result to the terminal.

15. An electronic device, characterized in that: include: processor; as well as a memory for storing executable instructions of the processor; The processor is configured to execute the data processing method according to any one of claims 1 to 11 by executing the executable instructions.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the data processing method according to any one of claims 1 to 11 is implemented.

17. A computer program product, characterized in that The method comprises computer instructions, which are stored in a computer-readable storage medium and implement the operation instructions of the data processing method according to any one of claims 1 to 11 when the computer instructions are executed by a processor.

Images