Data processing method and device

Abstract

The embodiment of the invention discloses a data processing method and device.The method comprises the steps that configuration information is determined, the configuration information is used for indicating type information of priori knowledge, and the priori knowledge is obtained data or data obtained after the obtained data is processed; receiving the data of the priori knowledge sent by the network equipment, wherein the data of the priori knowledge corresponds to the type information; and processing local data based on the data of the priori knowledge. By configuring various types of information of priori knowledge, the network device sends data of priori knowledge corresponding to the type information to the terminal device, so that the terminal device can filter or compress data in different application scenarios or in different data types, the data transmission amount is effectively reduced, and the data transmission efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a data processing method and apparatus. Background Technology

[0002] In native data transmission scenarios of 6G mobile communication technology, such as artificial intelligence (AI) and sensing data, network devices can send prior knowledge information to terminal devices, and the terminal devices can process the transmitted data based on the knowledge (e.g., data filtering).

[0003] However, because the knowledge information sent by network devices is relatively fixed, terminal devices may not be able to process certain data based on this knowledge information, thus failing to reduce the amount of data transmission. Summary of the Invention

[0004] This application provides a data processing method and apparatus. This enables terminal devices to filter or compress data from different application scenarios or of different data types, effectively reducing data transmission volume and improving data transmission efficiency.

[0005] Firstly, embodiments of this application provide a communication method, which can be executed by a receiving device. Unless otherwise specified, "receiving device" in this application can refer to the receiving device itself (e.g., a network device, a terminal device), a component within the receiving device (e.g., a processor, a chip, or a chip system), or a logic module or software capable of implementing all or part of the functions of the receiving device. Taking the application of this method to a terminal device as an example, the method includes:

[0006] The system determines configuration information, which indicates the type of prior knowledge, wherein the prior knowledge is acquired data or data processed from the acquired data; it receives the prior knowledge data sent by the network device, wherein the prior knowledge data corresponds to the type information; and it processes the local data based on the prior knowledge data.

[0007] By configuring various types of prior knowledge information, network devices send prior knowledge data corresponding to the type information to terminal devices, enabling terminal devices to filter or compress data under different application scenarios or different data types, effectively reducing data transmission volume and improving data transmission efficiency.

[0008] In one possible design, the type information includes prior knowledge type and / or data format. By sending prior knowledge data corresponding to the prior knowledge type and / or data format to the terminal device, the terminal device can filter or compress data from different application scenarios or different data types, effectively reducing data transmission volume and improving data transmission efficiency.

[0009] In one possible design, the type information corresponds to an application scenario, which includes at least one of the following: channel data transmission, artificial intelligence (AI) data transmission, or sensory data transmission. By configuring type information for different application scenarios, the terminal device can filter or compress data in different scenarios, effectively reducing data transmission volume and improving data transmission efficiency.

[0010] In one possible design, the type information corresponds to the data type of the local data, which includes at least one of the following: AI data, sensor data, or channel data. By configuring the type information of prior knowledge corresponding to different data types, the terminal device can filter or compress data of different data types, effectively reducing the amount of data transmitted and improving data transmission efficiency.

[0011] In one possible design, the type information includes first-order type information and second-order type information, where the second-order type information is a subtype of the first-order type information. By configuring multi-order type information, the terminal device can use more or more refined prior knowledge to process local data, thereby improving the accuracy of data processing.

[0012] In one possible design, the prior knowledge type corresponding to the perceived data includes at least one of the following: dictionary, geometry, region partitioning, or semantics. The dictionary subtypes include multi-dimensional weighted and single-dimensional dictionaries, and the multi-dimensional weighted data format includes dictionary dimensions, dictionary data, and sparsity. The geometry subtype includes faces, and the face data format includes face parameters and scanned areas on the face. The region partitioning subtypes include octrees and voxels, and the octree data format includes octree data, while the voxel data format includes voxel data. The semantic subtype includes 3D bounding boxes, and the 3D bounding box data format includes the center position and range of the 3D bounding box, and / or the vertex coordinates of the 3D bounding box. By configuring the prior knowledge type information corresponding to the perceived data, the terminal device can use different types of prior knowledge data to process the perceived data, thereby effectively reducing the amount of perceived data transmitted and improving data transmission efficiency.

[0013] In one possible design, the prior knowledge type corresponding to the channel data includes at least one of the following: dictionary or region partitioning. The dictionary subtypes include multi-dimensional weighted and single-dimensional dictionaries, and the multi-dimensional weighted data format includes dictionary dimension, dictionary data, and sparsity. The region partitioning subtypes include bitmaps and quadtrees, and the bitmap data format includes bitmap data, while the quadtree data format includes quadtree data. By configuring the prior knowledge type information corresponding to the channel data, the terminal device can use different types of prior knowledge data to process the channel data, thereby effectively reducing the amount of channel data transmitted and improving data transmission efficiency.

[0014] In one possible design, the prior knowledge types corresponding to the AI ​​data include dictionaries and pre-trained models. The subtypes of the dictionaries include multi-dimensional weighted dictionaries and single-dimensional dictionaries. The data format corresponding to the multi-dimensional weighted dictionaries includes dictionary dimensions, dictionary data, and sparsity. The data format corresponding to the pre-trained models includes model parameters. By configuring the type information of the prior knowledge corresponding to the AI ​​data, the terminal device can use different types of prior knowledge data to process the AI ​​data, thereby effectively reducing the amount of AI data transmitted and improving data transmission efficiency.

[0015] In one possible design, the system receives or sends indication information from the network device; or sends indication information to the network device; wherein the indication information is used to indicate the type information. By sending or receiving indication information, the type information of prior knowledge is determined, so that the network device can distribute the prior knowledge data corresponding to the type information. This enables the terminal device to filter or compress local data based on the prior knowledge data, effectively reducing the amount of data transmitted and improving data transmission efficiency.

[0016] In one possible design, the indication information includes an application scenario or data type, or the indication information includes a first index, which is used to indicate at least one type of information in a pre-configured prior knowledge type mapping table, wherein the prior knowledge type mapping table includes mapping relationships between multiple types of information and the index.

[0017] In one possible design, the network device sends a first indication message, which indicates at least one type of prior knowledge information supported by the network device; and receives a second indication message from the network device, which indicates a type of information selected from the at least one type of information. That is, the network device and the terminal device negotiate to determine the type of prior knowledge information that meets the capability requirements of the terminal device.

[0018] In one possible design, a third indication message is sent to the network device, indicating the type of prior knowledge information required by the device; a fourth indication message is received from the network device, indicating whether prior knowledge data corresponding to the type information exists. That is, the network device and the terminal device determine the type of prior knowledge information required by the terminal device through negotiation.

[0019] In one possible design, the network device receives a fifth indication message, which indicates that the network device supports at least one type of prior knowledge information; and sends a sixth indication message to the network device, which indicates a type of information selected from the at least one type of information. That is, the network device and the terminal device determine the type of prior knowledge information that the network device can support through negotiation.

[0020] In one possible design, the terminal device receives a seventh indication message from the network device, which indicates the type information of the prior knowledge; and sends an eighth indication message to the network device, which indicates whether it supports processing the prior knowledge data corresponding to the type information. That is, the network device and the terminal device negotiate to determine the type information of the prior knowledge that the terminal device supports processing.

[0021] In one possible design, the type information is updated according to a preset period. By periodically updating the type information, the integrity and real-time nature of the type information are ensured, enabling the terminal device to process local data more accurately and reducing data transmission volume.

[0022] In one possible design, the type information is updated when a trigger condition is met. This trigger condition includes a change in at least one of the following: the application scenario, the prior knowledge data, or the local data. By periodically updating the type information, the integrity and real-time nature of the type information are ensured, enabling the terminal device to process local data more accurately and reducing data transmission volume.

[0023] Secondly, embodiments of this application provide a communication method, which can be executed by a sending device. Unless otherwise specified, "sending device" in this application can refer to the sending device itself (e.g., a network device, a terminal device), a component within the sending device (e.g., a processor, a chip, or a chip system), or a logic module or software capable of implementing all or part of the functions of the sending device. Taking the application of this method to a network device as an example, the method includes:

[0024] The configuration information is determined, which indicates the type information of prior knowledge, wherein the prior knowledge is acquired data or data processed from the acquired data; the prior knowledge data is sent to the terminal device, wherein the prior knowledge data corresponds to the type information, and the prior knowledge data is used to process the local data of the terminal device.

[0025] By configuring various types of prior knowledge information, network devices send prior knowledge data corresponding to the type information to terminal devices, enabling terminal devices to filter or compress data under different application scenarios or different data types, effectively reducing data transmission volume and improving data transmission efficiency.

[0026] In one possible design, the type information includes prior knowledge type and / or data format. By sending prior knowledge data corresponding to the prior knowledge type and / or data format to the terminal device, the terminal device can filter or compress data from different application scenarios or different data types, effectively reducing data transmission volume and improving data transmission efficiency.

[0027] In one possible design, the type information corresponds to an application scenario, which includes at least one of the following: channel data transmission, artificial intelligence (AI) data transmission, or sensory data transmission. By configuring type information for different application scenarios, the terminal device can filter or compress data in different scenarios, effectively reducing data transmission volume and improving data transmission efficiency.

[0028] In one possible design, the type information corresponds to the data type of the local data, which includes at least one of the following: AI data, sensor data, or channel data. By configuring the type information of prior knowledge corresponding to different data types, the terminal device can filter or compress data of different data types, effectively reducing the amount of data transmitted and improving data transmission efficiency.

[0029] In one possible design, the type information includes first-order type information and second-order type information, where the second-order type information is a subtype of the first-order type information. By configuring multi-order type information, the terminal device can use more or more refined prior knowledge to process local data, thereby improving the accuracy of data processing.

[0030] In one possible design, the prior knowledge type corresponding to the perceived data includes at least one of the following: dictionary, geometry, region partitioning, or semantics. The dictionary subtypes include multi-dimensional weighted and single-dimensional dictionaries, and the multi-dimensional weighted data format includes dictionary dimensions, dictionary data, and sparsity. The geometry subtype includes faces, and the face data format includes face parameters and scanned areas on the face. The region partitioning subtypes include octrees and voxels, and the octree data format includes octree data, while the voxel data format includes voxel data. The semantic subtype includes 3D bounding boxes, and the 3D bounding box data format includes the center position and range of the 3D bounding box, and / or the vertex coordinates of the 3D bounding box. By configuring the prior knowledge type information corresponding to the perceived data, the terminal device can use different types of prior knowledge data to process the perceived data, thereby effectively reducing the amount of perceived data transmitted and improving data transmission efficiency.

[0031] In one possible design, the prior knowledge type corresponding to the channel data includes at least one of the following: dictionary or region partitioning. The dictionary subtypes include multi-dimensional weighted and single-dimensional dictionaries, and the multi-dimensional weighted data format includes dictionary dimension, dictionary data, and sparsity. The region partitioning subtypes include bitmaps and quadtrees, and the bitmap data format includes bitmap data, while the quadtree data format includes quadtree data. By configuring the prior knowledge type information corresponding to the channel data, the terminal device can use different types of prior knowledge data to process the channel data, thereby effectively reducing the amount of channel data transmitted and improving data transmission efficiency.

[0032] In one possible design, the prior knowledge types corresponding to the AI ​​data include dictionaries and pre-trained models. The subtypes of the dictionaries include multi-dimensional weighted dictionaries and single-dimensional dictionaries. The data format corresponding to the multi-dimensional weighted dictionaries includes dictionary dimensions, dictionary data, and sparsity. The data format corresponding to the pre-trained models includes model parameters. By configuring the type information of the prior knowledge corresponding to the AI ​​data, the terminal device can use different types of prior knowledge data to process the AI ​​data, thereby effectively reducing the amount of AI data transmitted and improving data transmission efficiency.

[0033] In one possible design, the system receives or sends indication information from the terminal device; or sends indication information to the terminal device; wherein the indication information is used to indicate the type information. By sending or receiving indication information, the type information of prior knowledge is determined, so that the network device can distribute the prior knowledge data corresponding to the type information. This enables the terminal device to filter or compress local data based on the prior knowledge data, effectively reducing the amount of data transmitted and improving data transmission efficiency.

[0034] In one possible design, the indication information includes an application scenario or data type, or the indication information includes a first index, which is used to indicate at least one type of information in a pre-configured prior knowledge type mapping table, wherein the prior knowledge type mapping table includes mapping relationships between multiple types of information and the index.

[0035] In one possible design, the network device receives first indication information sent by the terminal device, the first indication information indicating at least one type of prior knowledge information supported by the terminal device; and sends second indication information to the terminal device, the second indication information indicating type information selected from the at least one type of information. That is, the network device and the terminal device determine the type of prior knowledge information that can meet the capability requirements of the terminal device through negotiation.

[0036] In one possible design, the network device receives a third indication message from the terminal device, the third indication message indicating the type of prior knowledge information required by the terminal device; and sends a fourth indication message to the terminal device, the fourth indication message indicating whether prior knowledge data corresponding to the type information exists. That is, the network device and the terminal device determine the type of prior knowledge information required by the terminal device through negotiation.

[0037] In one possible design, a fifth indication message is sent to the terminal device, indicating that the network device supports at least one type of prior knowledge information; a sixth indication message is received from the terminal device, indicating the type of information selected from the at least one type of information. That is, the network device and the terminal device determine the type of prior knowledge information that the network device can support through negotiation.

[0038] In one possible design, a seventh indication message is sent to the terminal device, indicating the type information of the prior knowledge; and an eighth indication message is received from the terminal device, indicating whether processing the prior knowledge data corresponding to the type information is supported. That is, the network device and the terminal device determine the type information of the prior knowledge that the terminal device supports processing through negotiation.

[0039] In one possible design, the type information is updated according to a preset period. By periodically updating the type information, the integrity and real-time nature of the type information are ensured, enabling the terminal device to process local data more accurately and reducing data transmission volume.

[0040] In one possible design, the type information is updated when a trigger condition is met. This trigger condition includes a change in at least one of the following: the application scenario, the prior knowledge data, or the local data. By periodically updating the type information, the integrity and real-time nature of the type information are ensured, enabling the terminal device to process local data more accurately and reducing data transmission volume.

[0041] Thirdly, embodiments of this application provide a data processing apparatus that performs the functions described in the first aspect above. For example, the data processing apparatus includes modules, units, or means corresponding to the operations involved in the first aspect. These modules, units, or means can be implemented through software, hardware, or a combination of software and hardware. The apparatus includes:

[0042] A processing module is used to determine configuration information, wherein the configuration information is used to indicate the type information of prior knowledge, wherein the prior knowledge is acquired data or data processed from the acquired data;

[0043] A receiving module is used to receive the prior knowledge data sent by the network device, wherein the prior knowledge data corresponds to the type information;

[0044] The processing module is also used to process local data based on the prior knowledge data.

[0045] In one possible design, the type information includes prior knowledge types and / or data formats.

[0046] In one possible design, the type information corresponds to an application scenario, which includes at least one of the following: channel data transmission, artificial intelligence (AI) data transmission, or perception data transmission.

[0047] In one possible design, the type information corresponds to the data type of the local data, which includes at least one of the following: AI data, perception data, or channel data.

[0048] In one possible design, the type information includes first-order type information and second-order type information, wherein the second-order type information is a subtype of the first-order type information.

[0049] In one possible design, the prior knowledge type corresponding to the perceived data includes at least one of the following: dictionary, geometry, region partitioning, or semantics. The dictionary subtypes include multidimensional weighted and single-dimensional dictionaries, and the multidimensional weighted data format includes dictionary dimensions, dictionary data, and sparsity. The geometry subtype includes surfaces, and the surface data format includes surface parameters and scanned areas on the surface. The region partitioning subtypes include octrees and voxels, and the octree data format includes octree data, while the voxel data format includes voxel data. The semantic subtype includes 3D bounding boxes, and the 3D bounding box data format includes the center position and extent of the 3D bounding box, and / or the vertex coordinates of the 3D bounding box.

[0050] In one possible design, the prior knowledge type corresponding to the channel data includes at least one of the following: dictionary or region partitioning, wherein the subtypes corresponding to the dictionary include multidimensional weighted and single-dimensional dictionary, and the data form corresponding to the multidimensional weighted includes dictionary dimension, dictionary data and sparsity; the subtypes corresponding to the region partitioning include bitmap and quadtree, the data form corresponding to the bitmap includes bitmap data, and the data form corresponding to the quadtree includes quadtree data.

[0051] In one possible design, the prior knowledge types corresponding to the AI ​​data include dictionaries and pre-trained models. The subtypes corresponding to the dictionaries include multi-dimensional weighted dictionaries and single-dimensional dictionaries. The data forms corresponding to the multi-dimensional weighted dictionaries include dictionary dimensions, dictionary data, and sparsity. The data forms corresponding to the pre-trained models include model parameters.

[0052] In one possible design, the receiving module is further configured to receive indication information sent by the network device; or, the sending module is configured to send indication information to the network device; wherein the indication information is used to indicate the type information.

[0053] In one possible design, the indication information includes an application scenario or data type, or the indication information includes a first index, which is used to indicate at least one type of information in a pre-configured prior knowledge type mapping table, wherein the prior knowledge type mapping table includes mapping relationships between multiple types of information and the index.

[0054] In one possible design, the sending module is configured to send first indication information to the network device, the first indication information being used to indicate at least one type of information of the prior knowledge supported by the device itself.

[0055] A receiving module is configured to receive second indication information sent by the network device, the second indication information being used to indicate type information selected from the at least one type of information.

[0056] In one possible design, the sending module is configured to send third indication information to the network device, the third indication information being used to indicate the type information of the prior knowledge required by itself;

[0057] The receiving module is used to receive fourth indication information sent by the network device, the fourth indication information being used to indicate whether there is prior knowledge data corresponding to the type information.

[0058] In one possible design, a receiving module is configured to receive fifth indication information sent by the network device, the fifth indication information being used to indicate that the network device supports at least one type of information of the provided prior knowledge;

[0059] A sending module is configured to send a sixth indication information to the network device, the sixth indication information being used to indicate type information selected from the at least one type of information.

[0060] In one possible design, a receiving module is configured to receive a seventh indication information sent by the network device, the seventh indication information being used to indicate the type information of the prior knowledge;

[0061] The sending module is used to send an eighth indication message to the network device, the eighth indication message being used to indicate whether it supports processing the prior knowledge data corresponding to the type information.

[0062] In one possible design, the processing module is also used to update the type information according to a preset period.

[0063] In one possible design, the processing module is further configured to update the type information when a triggering condition is met, the triggering condition including at least one of the following changes: application scenario, prior knowledge data, or local data.

[0064] The operations performed by the data processing device and its beneficial effects can be found in the method described in the first aspect above, as well as its beneficial effects; repeated descriptions will not be repeated here.

[0065] Fourthly, embodiments of this application provide a data processing apparatus that performs the functions described in the second aspect above. For example, the data processing apparatus includes modules, units, or means corresponding to the operations involved in the second aspect. These modules, units, or means can be implemented through software, hardware, or a combination of software and hardware. The apparatus includes:

[0066] The processing module is used to determine configuration information, which is used to indicate the type information of prior knowledge, wherein the prior knowledge is acquired data or data processed from the acquired data;

[0067] The sending module is used to send the prior knowledge data to the terminal device. The prior knowledge data corresponds to the type information and is used to process the local data of the terminal device.

[0068] In one possible design, the type information includes prior knowledge types and / or data formats.

[0069] In one possible design, the type information corresponds to an application scenario, which includes at least one of the following: channel data transmission, artificial intelligence (AI) data transmission, or perception data transmission.

[0070] In one possible design, the type information corresponds to the data type of the local data, which includes at least one of the following: AI data, perception data, or channel data.

[0071] In one possible design, the type information includes first-order type information and second-order type information, wherein the second-order type information is a subtype of the first-order type information.

[0072] In one possible design, the prior knowledge type corresponding to the perceived data includes at least one of the following: dictionary, geometry, region partitioning, or semantics. The dictionary subtypes include multidimensional weighted and single-dimensional dictionaries, and the multidimensional weighted data format includes dictionary dimensions, dictionary data, and sparsity. The geometry subtype includes surfaces, and the surface data format includes surface parameters and scanned areas on the surface. The region partitioning subtypes include octrees and voxels, and the octree data format includes octree data, while the voxel data format includes voxel data. The semantic subtype includes 3D bounding boxes, and the 3D bounding box data format includes the center position and extent of the 3D bounding box, and / or the vertex coordinates of the 3D bounding box.

[0073] In one possible design, the prior knowledge type corresponding to the channel data includes at least one of the following: dictionary or region partitioning, wherein the subtypes corresponding to the dictionary include multidimensional weighted and single-dimensional dictionary, and the data form corresponding to the multidimensional weighted includes dictionary dimension, dictionary data and sparsity; the subtypes corresponding to the region partitioning include bitmap and quadtree, the data form corresponding to the bitmap includes bitmap data, and the data form corresponding to the quadtree includes quadtree data.

[0074] In one possible design, the prior knowledge types corresponding to the AI ​​data include dictionaries and pre-trained models. The subtypes corresponding to the dictionaries include multi-dimensional weighted dictionaries and single-dimensional dictionaries. The data forms corresponding to the multi-dimensional weighted dictionaries include dictionary dimensions, dictionary data, and sparsity. The data forms corresponding to the pre-trained models include model parameters.

[0075] In one possible design, a receiving module is used to receive indication information sent by the terminal device; or, a sending module is used to send indication information to the terminal device; wherein the indication information is used to indicate the type information.

[0076] In one possible design, the indication information includes an application scenario or data type, or the indication information includes a first index, which is used to indicate at least one type of information in a pre-configured prior knowledge type mapping table, wherein the prior knowledge type mapping table includes mapping relationships between multiple types of information and the index.

[0077] In one possible design, a receiving module is configured to receive first indication information sent by the terminal device, the first indication information being used to indicate at least one type of information of the prior knowledge supported by the terminal device;

[0078] A sending module is configured to send second indication information to the terminal device, the second indication information being used to indicate type information selected from the at least one type of information.

[0079] In one possible design, a receiving module is configured to receive third indication information sent by the terminal device, the third indication information being used to indicate the type information of the prior knowledge required by the terminal device;

[0080] The sending module is used to send fourth indication information to the terminal device, the fourth indication information being used to indicate whether there is prior knowledge data corresponding to the type information.

[0081] In one possible design, a sending module is configured to send fifth indication information to the terminal device, the fifth indication information being used to indicate that the network device supports at least one type of information of the provided prior knowledge;

[0082] A receiving module is configured to receive a sixth indication information sent by the terminal device, the sixth indication information being used to indicate type information selected from the at least one type of information.

[0083] In one possible design, a sending module is configured to send a seventh indication information to the terminal device, the seventh indication information being used to indicate the type information of the prior knowledge;

[0084] The receiving module is used to receive the eighth indication information sent by the terminal device, the eighth indication information being used to indicate whether it supports processing the prior knowledge data corresponding to the type information.

[0085] In one possible design, the processing module is also used to update the type information according to a preset period.

[0086] In one possible design, the processing module is further configured to update the type information when a triggering condition is met, the triggering condition including at least one of the following changes: application scenario, prior knowledge data, or local data.

[0087] The operations performed by the data processing device and its beneficial effects can be found in the method described in the second aspect above, and the details will not be repeated here.

[0088] Fifthly, embodiments of this application provide a data processing apparatus, which includes a memory and one or more processors. The memory is used to store part or all of the computer program or instructions necessary for implementing the functions involved in the first aspect above. The one or more processors are capable of executing the computer program or instructions, which, when executed, cause the data processing apparatus to implement the methods in any possible design or implementation of the first aspect above.

[0089] In one possible design, the data processing device may further include an interface circuit, wherein the processor is used to communicate with other devices or components through the interface circuit.

[0090] In one possible design, the data processing device may also include the memory.

[0091] The aforementioned data processing device may be a terminal device, or a communication module in a terminal device, or a chip in a terminal device that is responsible for communication functions, such as a modem chip (also known as a baseband chip) or a SoC or SIP chip containing a modem module.

[0092] Sixthly, embodiments of this application provide a data processing apparatus, which includes a memory and one or more processors. The memory is used to store part or all of the computer program or instructions necessary to implement the functions involved in the second aspect above. The one or more processors are capable of executing the computer program or instructions, which, when executed, cause the data processing apparatus to implement the methods in any possible design or implementation of the second aspect above.

[0093] In one possible design, the data processing device may further include an interface circuit, wherein the processor is used to communicate with other devices or components through the interface circuit.

[0094] In one possible design, the data processing device may also include the memory.

[0095] The aforementioned data processing device may be a network device, a communication module in a network device, or a chip in a network device that is responsible for communication functions, such as a modem chip (also known as a baseband chip) or a SoC or SIP chip containing a modem module.

[0096] In a seventh aspect, this application provides a computer-readable storage medium for storing a computer program that, when executed, causes the method described in either the first or second aspect to be implemented.

[0097] Eighthly, this application provides a computer program product including a computer program that, when executed, causes the method described in either the first or second aspect to be implemented.

[0098] Ninthly, embodiments of this application provide a communication system including at least one terminal device and at least one network device, wherein the terminal device is used to perform the steps in the first aspect described above, and the network device is used to perform the steps in the second aspect described above.

[0099] In a tenth aspect, a chip is provided, the chip including a processor and a communication interface for communicating with external or internal devices, the processor for implementing the methods of the above aspects.

[0100] In one possible design, the chip may further include a memory storing computer programs or instructions, which the processor executes, either from the stored computer programs or instructions or derived from other programs or instructions. When the computer program or instructions are executed, the processor implements the methods described in the preceding aspects.

[0101] In one possible design, the chip can be integrated into a terminal device or a network device. Attached Figure Description

[0102] Figure 1 This is a schematic diagram of the architecture of a communication system provided in an embodiment of this application;

[0103] Figure 2 This is a flowchart illustrating a data processing method provided in an embodiment of this application;

[0104] Figure 3 This is a diagram illustrating how to process data using a dictionary.

[0105] Figure 4 It is a schematic diagram that uses geometry to process data;

[0106] Figure 5 This is a schematic diagram illustrating the use of an octree to process data.

[0107] Figure 6 This is a schematic diagram illustrating the use of semantic data processing.

[0108] Figure 7 This is a schematic diagram illustrating data processing using region partitioning.

[0109] Figure 8 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application;

[0110] Figure 9 This is a schematic diagram of another data processing device provided in an embodiment of this application;

[0111] Figure 10 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application;

[0112] Figure 11 This is a schematic diagram of the structure of a network device provided in an embodiment of this application. Detailed Implementation

[0113] like Figure 1 As shown, Figure 1This is a schematic diagram of the architecture of a communication system provided in an embodiment of this application. The communication system may include network device 110 and terminal devices 101 to 106. It should be understood that a communication system to which the methods of this application embodiment can be applied may include more or fewer network devices or terminal devices. In this communication system, network device 110 and terminal devices 101 to 106 form a communication system. Terminal devices 101 to 106 can send uplink data to network device 110, and network device 110 needs to receive the uplink data sent by terminal devices 101 to 106. Furthermore, terminal devices 104 to 106 can also form a communication system. In this communication system, the network device can send downlink information to terminal devices 101, 102, and 105, etc.; terminal device 105 can also send downlink information to terminal devices 104 and 106.

[0114] The technical solutions in this application embodiment can be applied to various communication systems, such as Universal Mobile Telecommunications System (UMTS), Wireless Local Area Network (WLAN), Wireless Fidelity (Wi-Fi) system, 4th generation (4G) mobile communication system, such as Long Term Evolution (LTE) system, 5th generation (5G) mobile communication system, such as New Radio (NR) system, and future evolution communication systems, such as 6th generation (6G) mobile communication system, etc.

[0115] Network devices can be devices or modules located on the network side of the aforementioned communication system and possessing corresponding communication functions. Network devices typically contain communication modules, circuits, or chips that perform the corresponding communication functions. They also contain program instructions for performing these functions, as well as corresponding program instructions. A network device is a device deployed in a radio access network to provide wireless communication functions for terminal devices. Network devices can include various forms of macro base stations, micro base stations (also called small stations), relay stations, access points, etc. In systems employing different radio access technologies, the name of the network device may differ, such as a base transceiver station (BTS) in a Global System for Mobile Communication (GSM) or Code Division Multiple Access (CDMA) network, an NB (NodeB) in Wideband Code Division Multiple Access (WCDMA), or an eNB or eNodeB (evolutionary nodeB) in Long Term Evolution (LTE). Network devices can also be radio controllers in cloud radio access network (CRAN) scenarios. Network equipment can also be base station equipment in future 5G networks or network equipment in future evolved PLMN networks. Network equipment can also be wearable devices or vehicle-mounted devices. Network equipment can also be transmission and reception points (TRPs).

[0116] Terminal devices can be devices or modules that access the aforementioned communication systems and possess corresponding communication functions. Terminal devices typically contain communication modules, circuits, or chips that perform the corresponding communication functions. They may also be configured with program instructions for performing these functions. Terminal devices can include various handheld devices, vehicle-mounted devices, wearable devices, computing devices, or other processing devices connected to a wireless modem that have wireless communication capabilities. Terminals can be mobile stations (MS), subscriber units, cellular phones, smartphones, wireless data cards, personal digital assistant (PDA) computers, tablet computers, wireless modems, handsets, laptop computers, machine-type communication (MTC) terminals, etc.

[0117] like Figure 2 As shown, Figure 2 This is a flowchart illustrating a data processing method provided in an embodiment of this application. The method mainly includes the following steps:

[0118] S201, the network device determines configuration information, the terminal device determines configuration information, and the configuration information is used to indicate the type information of prior knowledge.

[0119] In this context, prior knowledge refers to data already acquired by the network device or data processed from the acquired data, used to assist the terminal device in filtering or compressing local data. For example, the acquired data can be sensor data, and the prior knowledge can be data processed from the sensor data. The network device trains to obtain prior dictionary information based on the sensor data and sends the prior dictionary information to the terminal device, which then compresses the local data using the prior dictionary information. Alternatively, the network device divides the sensor data into regions to obtain multiple voxels, and then sends indication information to the terminal device. This indication information indicates whether each voxel contains a point, where 0 indicates that the voxel does not contain a point, and 1 indicates that the voxel contains a point; 0 or 1 can also indicate the opposite. The terminal device performs unequal compression processing on the voxels according to the indication information, dividing the data into multiple voxel regions.

[0120] The type information may include prior knowledge types. For example, type information may include prior knowledge types such as dictionaries, region partitions, or semantics. Alternatively, the type information may include data formats that implicitly indicate the corresponding prior knowledge type. For example, type information may include data formats such as dictionary dimensions, dictionary data, and sparsity; that is, if the type information does not include prior knowledge types, it implicitly indicates that the prior knowledge type is a dictionary. Alternatively, the type information may include prior knowledge types and their corresponding data formats. For example, type information may include a dictionary (prior knowledge type) and dictionary dimensions, dictionary data, and sparsity (data formats); type information may include region partitions (prior knowledge type) and voxel data (data formats).

[0121] The type information includes first-order type information (prior knowledge type) and second-order type information (prior knowledge subtype), where the second-order type information is a subtype of the first-order type information. For example, first-order type information includes dictionaries, region partitions, or semantics; second-order type information includes multi-dimensional weighted and single-dimensional dictionaries corresponding to dictionaries, octrees, voxels, bitmaps, and coordinates corresponding to region partitions, and 3D target information and semantic labels corresponding to semantics. Optionally, the type information may include first-order type information, second-order type information, and data format. For example, first-order type information includes dictionaries, region partitions, or semantics; second-order type information includes multi-dimensional weighted dictionaries, octrees, voxels, bitmaps, and coordinates corresponding to region partitions, and 3D target information and semantic labels corresponding to semantics; data format includes dictionary dimensions, dictionary data, and sparsity corresponding to multi-dimensional weighted dictionaries, and octree data corresponding to octrees.

[0122] It should be understood that type information may include multi-level type information, such as first-level type information, second-level type information, and third-level type information. Type information of level three and above is included within the scope of protection of this application.

[0123] The type information corresponds to an application scenario, which includes at least one of the following: channel data transmission, artificial intelligence (AI) data transmission, or perceptual data transmission. Furthermore, the application scenario and type information can have a one-to-one mapping relationship. For example, AI model transmission and type information have a one-to-one mapping relationship; the prior knowledge type corresponding to AI model transmission only includes dictionaries, and the data format corresponding to dictionaries includes dictionary dimensions and dictionary data. The application scenario and type information can also have a one-to-many mapping relationship. For example, perceptual data transmission and type information have a one-to-many mapping relationship; the prior knowledge type corresponding to perceptual data transmission can include geometry, region partitioning, and dictionaries; the data format corresponding to geometry includes two-point coordinates and three-point coordinates; the data format corresponding to region partitioning includes octree data and voxel data; and the data format corresponding to dictionaries includes dictionary dimensions and dictionary data.

[0124] The type information corresponds to the data type of the local data, which includes at least one of the following: AI data, perception data, or channel data. AI data may include AI model data, AI feature data, and AI inference data. Furthermore, the data type and type information can have a one-to-one mapping relationship. For example, AI model data and type information have a one-to-one mapping relationship, where the prior knowledge type corresponding to AI model data only includes dictionaries, and the data format corresponding to dictionaries includes dictionary dimensions and dictionary data. The data type and type information can also have a one-to-many mapping relationship. For example, perception data and type information have a one-to-many mapping relationship, where the prior knowledge type corresponding to perception data may include geometry, region partitioning, and dictionaries. The data format corresponding to geometry includes two-point coordinates and three-point coordinates, the data format corresponding to region partitioning includes octree data and voxel data, and the data format corresponding to dictionaries includes dictionary dimensions and dictionary data.

[0125] The following lists the type information for local data of different data types:

[0126] As shown in Table 1, Table 1 contains the type information corresponding to the perceptual data. The prior knowledge type corresponding to the perceptual data includes at least one of the following: dictionary, geometry, region partitioning, or semantics. Specifically, the subtypes corresponding to the dictionary include multidimensional weighted and single-dimensional dictionaries, and the data form corresponding to the multidimensional weighted dictionary includes dictionary dimensions, dictionary data, and sparsity. The subtype corresponding to the geometry includes a surface, and the data form corresponding to the surface includes surface parameters and scanned areas on the surface. The surface parameters can be expression parameters or multiple point data used to indicate a surface. The subtypes corresponding to the region partitioning include octrees and voxels, and the data form corresponding to the octree includes octree data. The data form corresponding to the voxel includes voxel data. The subtype corresponding to the semantics includes a 3D bounding box, and the data form corresponding to the 3D bounding box includes the center position and range of the 3D bounding box, and / or the vertex coordinates of the 3D bounding box.

[0127]

[0128] Table 1

[0129] As shown in Table 2, Table 2 contains the type information corresponding to the channel data. The prior knowledge type corresponding to the channel data includes at least one of the following: dictionary or region partitioning. The subtypes corresponding to the dictionary include multi-dimensional weighted and single-dimensional dictionaries. The data form corresponding to the multi-dimensional weighted includes dictionary dimension, dictionary data, and sparsity. The subtypes corresponding to the region partitioning include bitmap and quadtree. The data form corresponding to the bitmap includes bitmap data, and the data form corresponding to the quadtree includes quadtree data.

[0130]

[0131] Table 2

[0132] As shown in Table 3, Table 2 lists the type information corresponding to the AI ​​data. The prior knowledge types corresponding to the AI ​​data include dictionaries and pre-trained models. The subtypes corresponding to the dictionaries include multi-dimensional weighting, and the data formats corresponding to multi-dimensional weighting include dictionary dimensions, dictionary data, and sparsity. The data formats corresponding to the pre-trained models include model parameters. Optionally, the transmitted AI data can also be sensing data, channel data, etc., therefore, the AI ​​data can reuse the type information corresponding to sensing data or channel data.

[0133]

[0134] Table 3

[0135] Optionally, network devices or terminal devices may pre-configure a priori knowledge type mapping table, which includes mapping relationships between various types of information and indexes.

[0136] For example, as shown in Table 4, the prior knowledge type mapping table can include prior knowledge types, prior knowledge subtypes, and indices. When the prior knowledge type is geometry, the corresponding prior knowledge subtypes include lines, surfaces, and geometric solids; lines correspond to index 0, surfaces to index 1, and geometric solids to index 2. When the prior knowledge type is semantics, the corresponding prior knowledge subtypes include 2D target information, 3D target information, and semantic labels; 2D target information corresponds to index 0, 3D target information to index 1, and semantic labels to index 2. Other types are similar and will not be described in detail here.

[0137]

[0138] Table 4

[0139] For example, as shown in Table 5, the prior knowledge type mapping table can include prior knowledge type, prior knowledge subtype, data format, and index. Prior knowledge types include geometry, semantics, region partitioning, dictionary, and pre-trained model. When the prior knowledge type is geometry, the prior knowledge subtype corresponding to index 0 is line, and the data format is endpoint coordinates; the prior knowledge subtype corresponding to index 1 is polygon, and the data format is three-point coordinates; the prior knowledge subtype corresponding to index 2 is polygon, and the data format is polygon parameter expression. When the prior knowledge type is semantics, the prior knowledge subtype corresponding to index 0 is 3D target information, and the data format is the center position and range of the target box; the prior knowledge subtype corresponding to index 1 is semantic label, and the data format is each data category. Other types are similar and will not be described in detail here.

[0140]

[0141]

[0142] Table 5

[0143] For example, as shown in Table 6, the prior knowledge type mapping table can include application scenarios, prior knowledge types, data formats, and indexes. When the application scenario is AI data transmission, the prior knowledge type is dictionary, and the corresponding data format is dictionary dimensions and dictionary data, corresponding to index 0. When the application scenario is perceptual data transmission, the prior knowledge type corresponding to index 0 is geometry, and the corresponding data format is two point coordinates; the prior knowledge type corresponding to index 1 is geometry, and the corresponding data format is three point coordinates; the prior knowledge type corresponding to index 2 is region partitioning, and the corresponding data format is Octree data; the prior knowledge type corresponding to index 3 is region partitioning, and the corresponding data format is voxel data. Other similar cases will not be elaborated here.

[0144]

[0145] Table 6

[0146] For example, as shown in Table 7, the prior knowledge type mapping table can include data type, prior knowledge type, data format, and index. When the data type is AI data, the prior knowledge type is dictionary (corresponding to nested index 0), and the corresponding data format is dictionary dimension and dictionary data (corresponding to nested index 0). When the data type is perceptual data transmission, the prior knowledge type corresponding to index 0 is geometry (corresponding to nested index 0), and the corresponding data format is two point coordinates (corresponding to nested index 0); the prior knowledge type corresponding to index 1 is geometry (corresponding to nested index 0), and the corresponding data format is three point coordinates (corresponding to nested index 1); the prior knowledge type corresponding to index 2 is region partitioning (corresponding to nested index 1), and the corresponding data format is Octree data (corresponding to nested index 0); the prior knowledge type corresponding to index 3 is region partitioning (corresponding to nested index 1), and the corresponding data format is voxel data (corresponding to nested index 1). Other types are similar and will not be elaborated here.

[0147]

[0148] Table 7

[0149] Optionally, network devices or terminal devices can update the prior knowledge type mapping table according to a preset period. The prior knowledge type mapping table is periodically updated synchronously between network devices and terminal devices through signaling such as radio resource control (RRC) signaling or medium access control (MAC) signaling.

[0150] Alternatively, when a triggering condition is met, the network device or terminal device updates the prior knowledge type mapping table, wherein the triggering condition includes at least one of the following changes: application scenario, prior knowledge data, or local data. After updating the prior knowledge type mapping table, the network device can send the updated prior knowledge type mapping table to the terminal device. Alternatively, after updating the prior knowledge type mapping table, the terminal device can send the updated prior knowledge type mapping table to the network device.

[0151] For example, when the application scenario of the network device, the local data required by the terminal device, or the prior knowledge data that can be obtained changes, the network device updates the prior knowledge type mapping table and notifies the terminal device of the updated prior knowledge type mapping table. Alternatively, when the application scenario of the terminal device, the local data that can be provided, or the prior knowledge data required changes, the terminal device updates the prior knowledge type mapping table and notifies the network device of the updated prior knowledge type mapping table.

[0152] Furthermore, when updating the prior knowledge type mapping table, you can add prior knowledge types, data formats, and corresponding indexes to the prior knowledge type mapping table, or you can delete prior knowledge types, data formats, and corresponding indexes from the prior knowledge type mapping table, or you can modify prior knowledge types, data formats, and corresponding indexes from the prior knowledge type mapping table.

[0153] Specifically, network devices or terminal devices can determine the type of prior knowledge information in the following ways:

[0154] In the first alternative, the network device sends indication information to the terminal device, or the terminal device sends indication information to the network device, wherein the indication information is used to indicate the type information of prior knowledge.

[0155] The indication information includes application scenarios or data types. For example, when there is a one-to-one mapping between application scenarios and type information, and the indication information includes AI model transmission, the prior knowledge type indicated by the indication information is a dictionary, and the data format corresponding to the dictionary includes dictionary dimensions and dictionary data. Optionally, the indication information may also include an index of the application scenario or an index of the data type. For example, the indication information may include an index of AI model transmission or an index of channel data.

[0156] The indication information may include prior knowledge types. For example, if the prior knowledge types are 3D target information and octrees, the terminal device or network device can send the indication information via RRC signaling or MAC signaling. The indication information may include "3D target information" and "octree," or it may include {"semantic", "3D target information"} and {"region division", "octree"} (nested form). Alternatively, the indication information may include data formats. For example, if the prior knowledge types are 3D target information and octrees, corresponding to target box vertices and octree data respectively, the terminal device or network device can send the indication information via RRC signaling or MAC signaling. The indication information may include "target box vertices" and "octree data." Alternatively, the indication information may also include prior knowledge types and data formats, similar to the above, and will not be elaborated further here.

[0157] The indication information may include a first index, which indicates at least one type of information in a pre-configured prior knowledge type mapping table. For example, as shown in Table 7, for perceptual data, the indication information may include index (0, 4), where (0, 4) indicates that the prior knowledge type is geometry and dictionary, and the data format is two-point coordinates and dictionary dimension and dictionary data, respectively. If a nested index is used, the indication information may include (0, 0) and (2, 0). (0, 0) indicates that the prior knowledge type is geometry, and the corresponding data format is two-point coordinates; (2, 0) indicates that the prior knowledge type is dictionary, and the corresponding data format is dictionary dimension and dictionary data.

[0158] In a second alternative approach, the terminal device sends a first indication message to the network device, the first indication message indicating at least one type of prior knowledge information supported by the terminal device; the terminal device receives a second indication message from the network device, the second indication message indicating a type of information selected from the at least one type of information. That is, the network device and the terminal device negotiate to determine the type of prior knowledge information that meets the terminal device's capability requirements.

[0159] In a third optional approach, the terminal device sends a third indication message to the network device, indicating the type information of the prior knowledge it needs. The terminal device then receives a fourth indication message from the network device, indicating whether prior knowledge data corresponding to the type information exists. Further, if the network device has prior knowledge data corresponding to the type information, the fourth indication message can be 0, and the network device sends the prior knowledge data corresponding to the type information to the terminal device. If the network device does not have prior knowledge data corresponding to the type information, the fourth indication message can be 1, and either the network device or the terminal device reconfigures the type information of the prior knowledge and updates it synchronously.

[0160] In a fourth optional manner, the terminal device receives a fifth indication message sent by the network device, the fifth indication message indicating that the network device supports at least one type of prior knowledge information; the terminal device then sends a sixth indication message to the network device, the sixth indication message indicating the type of information selected from the at least one type of information. That is, the network device and the terminal device determine the type of prior knowledge information that the network device can support through negotiation.

[0161] In a fifth optional method, the terminal device receives a seventh indication message sent by the network device, the seventh indication message indicating the type information of the prior knowledge; the terminal device then sends an eighth indication message to the network device, the eighth indication message indicating whether it supports processing the prior knowledge data corresponding to the type information. Further, if the terminal device supports processing the prior knowledge data corresponding to the type information, the eighth indication message can be 0, and the network device sends the prior knowledge data corresponding to the type information to the terminal device. If the terminal device does not support processing the prior knowledge data corresponding to the type information, the eighth indication message can be 1, and either the network device or the terminal device reconfigures the type information of the prior knowledge and updates it synchronously.

[0162] It should be noted that, in the second to fifth optional methods, the indication method in the first optional method can be used to indicate the type information of prior knowledge. For example, the type information of prior knowledge can be indicated by indicating the application scenario or data type, or by indicating the type information of prior knowledge by index.

[0163] Optionally, network devices or terminal devices can update the type information of prior knowledge according to a preset period. The network devices and terminal devices periodically synchronize and update the type information of prior knowledge through signaling such as RRC signaling or MAC signaling.

[0164] Alternatively, when a triggering condition is met, the network device or terminal device updates the type information of the prior knowledge, wherein the triggering condition includes at least one of the following changes: the application scenario, the data of the prior knowledge, or the local data. After updating the type information of the prior knowledge, the network device may send the updated type information of the prior knowledge to the terminal device. Alternatively, after updating the type information of the prior knowledge, the terminal device may send the updated type information of the prior knowledge to the network device.

[0165] For example, when the application scenario of the network device, the local data required by the terminal device, or the prior knowledge data that can be obtained changes, the network device updates the type information of the prior knowledge and notifies the terminal device of the updated type information of the prior knowledge. Alternatively, when the application scenario of the terminal device, the local data that can be provided, or the prior knowledge data required changes, the terminal device updates the type information of the prior knowledge and notifies the network device of the updated type information of the prior knowledge.

[0166] S202, the network device sends prior knowledge data to the terminal device, the prior knowledge data corresponding to the type information.

[0167] S203, the terminal device processes local data based on the prior knowledge data.

[0168] Specifically, the terminal device compresses or filters local data based on the prior knowledge data. This local data may include sensor data, channel data, or AI data. Optionally, after processing the local data, the terminal device can report the processed local data to the network device.

[0169] (1) For perceptual data, various types of prior knowledge information can be configured. Different types of prior knowledge data can be used to process the perceptual data. Examples are as follows:

[0170] Figure 3 This is a schematic diagram illustrating data processing using a dictionary. For perceived data, the prior knowledge type can be a dictionary, and the subtypes corresponding to dictionaries include multi-dimensional weighted and single-dimensional dictionaries. The data format corresponding to the multi-dimensional weighted method includes dictionary dimension, dictionary data, and sparsity. The base station can send the dictionary dimension (D, L), dictionary data, and sparsity k to the UE. The UE can compress the local perceived data based on the sent dictionary and report the compressed perceived data to the network device.

[0171] Figure 4 This is a schematic diagram illustrating geometric data processing. For perceived data, the prior knowledge type can be geometry, and the subtypes corresponding to geometry include surfaces. The data format corresponding to the surfaces includes surface parameters and scanned areas on the surfaces. The base station sends the parameters of existing surfaces in the environment and the scanned areas on the surfaces to the UE. The UE filters or performs low-precision compression on the local perceived data of the scanned surface areas, performs high-precision compression on other local perceived data, and finally reports the filtered / compressed local perceived data to the base station.

[0172] Figure 5 This is a schematic diagram illustrating data processing using an octree. For sensed data, the prior knowledge type can be region partitioning, and the subtype corresponding to region partitioning includes octrees. The data format corresponding to octrees includes octree data. The UE reports the sensed region R to the base station. Based on the sensed region R and environmental data, the base station determines the octree data and sends the octree data to the UE. The octree data is used to indicate the compression level of each leaf region. The UE performs unequal compression on the local sensed data within each leaf region according to the octree data, and finally reports the compressed local sensed data to the base station.

[0173] For sensed data, the prior knowledge type can be region division, and the subtypes corresponding to region division can also include voxels. The data format corresponding to voxels includes voxel data. The UE sends a sensed region R to the base station. The base station divides the data into grids based on the sensed region R and environmental data to obtain voxel data, and sends the voxel data to the UE. The voxel data is used to indicate the compression level of each voxel. The UE performs unequal compression on the local sensed data within each voxel according to the voxel data, and reports the compressed local sensed data to the base station.

[0174] Figure 6 This is a schematic diagram illustrating semantic data processing. For perceptual data, the prior knowledge type can be semantic, and the subtypes corresponding to semantics include 3D target boxes. The data format corresponding to the 3D target boxes includes the center position and range of the 3D target box, and / or the vertex coordinates of the 3D target box. The base station sends target information of existing targets in the environment to the UE, such as the position and range of the 3D box. The UE matches the sent target information with local target information to determine local target data, and filters or performs low-precision compression on the local target data, while other target data is compressed with high precision. Finally, the compressed target data is reported to the base station.

[0175] (2) For channel data, various types of prior knowledge information can be configured. Different types of prior knowledge data can be used to process local channel data. Examples are as follows:

[0176] For channel data, the prior knowledge type can be a dictionary. Subtypes of a dictionary include multi-dimensional weighted and single-dimensional dictionaries. The data format corresponding to the multi-dimensional weighted dictionary includes dictionary dimension, dictionary data, and sparsity. The base station can send the dictionary dimension (D, L), dictionary data, and sparsity k to the UE. The UE can compress its local channel data based on the sent dictionary and report the compressed local channel data to the base station.

[0177] For channel data, the prior knowledge type can be region partitioning, and the subtype corresponding to the region partitioning includes bitmaps. The data format corresponding to the bitmaps includes bitmap data. The base station sends a feedback mode map to the UE based on the bitmap format. The feedback mode map is used to indicate which feedback mode the UE should select in different regions of the map. As shown in Table 8, Table 8 is a feedback mode table, where index 1 corresponds to the Type II Codebook, index 2 corresponds to feedback neighbor grid points, and index 3 corresponds to feedback calibration multipath. The UE performs channel data feedback according to the feedback mode map.

[0178]

[0179]

[0180] Table 8

[0181] Figure 7 This is a schematic diagram illustrating data processing using region partitioning. For channel data, the prior knowledge type can be region partitioning, and the subtypes corresponding to region partitioning include quadtrees. The data format corresponding to the quadtrees includes quadtree data. Based on the quadtree format, the base station sends a compression map to the UE. The compression map indicates the compression level of the data in each region. The UE compresses the channel data according to the compression map and reports the compressed channel data to the base station.

[0182] (3) For AI data, various types of prior knowledge information can be configured. Different types of prior knowledge data can be used to process local data. Examples are as follows:

[0183] For AI data, the prior knowledge type can be a dictionary, and the subtypes of a dictionary include multi-dimensional weighted and single-dimensional dictionaries. The data format corresponding to the multi-dimensional weighted dictionary includes dictionary dimension, dictionary data, and sparsity. The base station can send the dictionary dimension (D, L), dictionary data, and sparsity k to the UE. The UE can compress the AI ​​data based on the sent dictionary and report the compressed AI data to the base station.

[0184] For AI data, the prior knowledge type can also be a pre-trained model. The data form corresponding to the pre-trained model includes model parameters. The base station sends the obtained pre-trained model to the UE. The UE fine-tunes or updates the pre-trained model and reports the fine-tuned or updated pre-trained model to the base station.

[0185] In this embodiment, by configuring various types of prior knowledge information, the network device sends prior knowledge data corresponding to the type information to the terminal device, enabling the terminal device to filter or compress data under different application scenarios or different data types, effectively reducing the amount of data transmission and improving data transmission efficiency.

[0186] It is understood that, in the above-described method embodiments, the methods and operations implemented by the terminal device can also be implemented by components (such as chips or circuits) that can be used in the terminal device, and the methods and operations implemented by the network device can also be implemented by components (such as chips or circuits) that can be used in the network device.

[0187] This application embodiment can divide terminal devices or network devices into functional modules according to the above method examples. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into one processing module. The integrated modules can be implemented in hardware or software functional modules. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. The following description uses the division of functional modules according to each function as an example.

[0188] The above, combined with Figure 2 The methods provided in the embodiments of this application are described in detail below. Figures 8 to 9 This application provides a detailed description of the data processing apparatus provided in its embodiments. It should be understood that the descriptions of the apparatus embodiments correspond to the descriptions of the method embodiments; therefore, any content not described in detail here will be referred to the method embodiments above, and for the sake of brevity, will not be repeated here.

[0189] Please see Figure 8 , Figure 8 This is a schematic diagram of a data processing apparatus provided in an embodiment of this application. The data processing apparatus can implement the steps or processes executed by the terminal device corresponding to the method embodiments described above. In one possible design, the data processing apparatus may include a receiving module 801, a processing module 802, and a sending module 803. Optionally, the data processing apparatus may further include a storage module for storing device program code and / or data.

[0190] The data processing device can be the terminal-side device in the above embodiments, such as a terminal device or a communication module in a terminal device, or a circuit or chip in a terminal that is responsible for communication functions.

[0191] Processing module 802 is used to determine configuration information, wherein the configuration information is used to indicate the type information of prior knowledge, wherein the prior knowledge is data that has been obtained or data after processing the data that has been obtained;

[0192] The receiving module 801 is used to receive the prior knowledge data sent by the network device, wherein the prior knowledge data corresponds to the type information;

[0193] The processing module 802 is also used to process local data based on the prior knowledge data.

[0194] Optionally, the type information includes prior knowledge type and / or data format.

[0195] Optionally, the type information corresponds to the application scenario, which includes at least one of the following: channel data transmission, artificial intelligence (AI) data transmission, or perception data transmission.

[0196] Optionally, the type information corresponds to the data type of the local data, and the data type includes at least one of the following: AI data, perception data, or channel data.

[0197] Optionally, the type information includes first-order type information and second-order type information, wherein the second-order type information is a subtype of the first-order type information.

[0198] Optionally, the prior knowledge type corresponding to the perceived data includes at least one of the following: dictionary, geometry, region partitioning, or semantics. The dictionary subtypes include multidimensional weighted and single-dimensional dictionaries, and the multidimensional weighted data format includes dictionary dimensions, dictionary data, and sparsity. The geometry subtype includes surfaces, and the surface data format includes surface parameters and scanned areas on the surface. The region partitioning subtypes include octrees and voxels, and the octree data format includes octree data, while the voxel data format includes voxel data. The semantic subtype includes 3D bounding boxes, and the 3D bounding box data format includes the center position and range of the 3D bounding box, and / or the vertex coordinates of the 3D bounding box.

[0199] Optionally, the prior knowledge type corresponding to the channel data includes at least one of the following: dictionary or region partitioning, wherein the subtypes corresponding to the dictionary include multi-dimensional weighted and single-dimensional dictionary, and the data form corresponding to the multi-dimensional weighted includes dictionary dimension, dictionary data and sparsity; the subtypes corresponding to the region partitioning include bitmap and quadtree, the data form corresponding to the bitmap includes bitmap data, and the data form corresponding to the quadtree includes quadtree data.

[0200] Optionally, the prior knowledge types corresponding to the AI ​​data include dictionaries and pre-trained models. The subtypes corresponding to the dictionaries include multi-dimensional weighted dictionaries and single-dimensional dictionaries. The data forms corresponding to the multi-dimensional weighted dictionaries include dictionary dimensions, dictionary data, and sparsity. The data forms corresponding to the pre-trained models include model parameters.

[0201] Optionally, the receiving module 801 is further configured to receive indication information sent by the network device; or, the sending module 803 is configured to send indication information to the network device; wherein the indication information is used to indicate the type information.

[0202] Optionally, the indication information includes an application scenario or data type, or the indication information includes a first index, which is used to indicate at least one type of information in a pre-configured prior knowledge type mapping table, wherein the prior knowledge type mapping table includes mapping relationships between multiple types of information and the index.

[0203] Optionally, the sending module 803 is configured to send first indication information to the network device, the first indication information being used to indicate at least one type of information of the prior knowledge supported by itself;

[0204] The receiving module 801 is configured to receive second indication information sent by the network device, the second indication information being used to indicate type information selected from the at least one type of information.

[0205] Optionally, the sending module 803 is used to send third indication information to the network device, the third indication information being used to indicate the type information of the prior knowledge required by itself;

[0206] The receiving module 801 is used to receive fourth indication information sent by the network device, the fourth indication information being used to indicate whether there is prior knowledge data corresponding to the type information.

[0207] Optionally, the receiving module 801 is configured to receive a fifth indication information sent by the network device, the fifth indication information being used to indicate that the network device supports at least one type of information of the provided prior knowledge;

[0208] The sending module 803 is used to send a sixth indication information to the network device, the sixth indication information being used to indicate type information selected from the at least one type of information.

[0209] Optionally, the receiving module 801 is configured to receive a seventh indication information sent by the network device, the seventh indication information being used to indicate the type information of the prior knowledge;

[0210] The sending module 803 is used to send an eighth indication message to the network device, the eighth indication message being used to indicate whether it supports processing the prior knowledge data corresponding to the type information.

[0211] Optionally, the processing module 802 is also used to update the type information according to a preset period.

[0212] Optionally, the processing module 802 is further configured to update the type information when a triggering condition is met, wherein the triggering condition includes at least one of the following changes: the application scenario, the prior knowledge data, or the local data.

[0213] In one possible design, when the data processing device is a terminal device or a communication module within a terminal device, the functionality of the processing module 802 can be implemented by one or more processors. Specifically, the processor may include a modem chip, or a system-on-a-chip (SoC) chip or a SIP chip containing a modem core. The functions of the receiving module 801 and the transmitting module 803 can be implemented by transceiver circuitry.

[0214] In one possible design, when the data processing device is a circuit or chip responsible for communication functions in a terminal device, such as a modem chip or a system-on-a-chip (SoC) or SIP chip containing a modem core, the function of the processing module 802 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processor cores. The functions of the receiving module 801 and the transmitting module 803 can be implemented by interface circuits or data transceiver circuits on the aforementioned chip.

[0215] It should be noted that the implementation of each module can also be referenced accordingly. Figure 2 The corresponding description of the method embodiments shown above describes the methods and functions performed by the terminal device in the above embodiments.

[0216] Please see Figure 9 , Figure 9 This is a schematic diagram of another data processing apparatus provided in an embodiment of this application. This data processing apparatus can implement the steps or processes executed by the network device corresponding to those described in the method embodiments above. In one possible design, the data processing apparatus may include a sending module 901, a processing module 902, and a receiving module 903. Optionally, the data processing apparatus may further include a storage module for storing device program code and / or data.

[0217] The data processing device can be a network-side device as described in the above embodiments, such as a network device or a communication module in a network device, or a circuit or chip in the network responsible for communication functions.

[0218] Processing module 902 is used to determine configuration information, wherein the configuration information is used to indicate the type information of prior knowledge, wherein the prior knowledge is acquired data or data processed from the acquired data;

[0219] The sending module 901 is used to send the prior knowledge data to the terminal device. The prior knowledge data corresponds to the type information and is used to process the local data of the terminal device.

[0220] Optionally, the type information includes prior knowledge type and / or data format.

[0221] Optionally, the type information corresponds to the application scenario, which includes at least one of the following: channel data transmission, artificial intelligence (AI) data transmission, or perception data transmission.

[0222] Optionally, the type information corresponds to the data type of the local data, and the data type includes at least one of the following: AI data, perception data, or channel data.

[0223] Optionally, the type information includes first-order type information and second-order type information, wherein the second-order type information is a subtype of the first-order type information.

[0224] Optionally, the prior knowledge type corresponding to the perceived data includes at least one of the following: dictionary, geometry, region partitioning, or semantics. The dictionary subtypes include multidimensional weighted and single-dimensional dictionaries, and the multidimensional weighted data format includes dictionary dimensions, dictionary data, and sparsity. The geometry subtype includes surfaces, and the surface data format includes surface parameters and scanned areas on the surface. The region partitioning subtypes include octrees and voxels, and the octree data format includes octree data, while the voxel data format includes voxel data. The semantic subtype includes 3D bounding boxes, and the 3D bounding box data format includes the center position and range of the 3D bounding box, and / or the vertex coordinates of the 3D bounding box.

[0225] Optionally, the prior knowledge type corresponding to the channel data includes at least one of the following: dictionary or region partitioning, wherein the subtypes corresponding to the dictionary include multi-dimensional weighted and single-dimensional dictionary, and the data form corresponding to the multi-dimensional weighted includes dictionary dimension, dictionary data and sparsity; the subtypes corresponding to the region partitioning include bitmap and quadtree, the data form corresponding to the bitmap includes bitmap data, and the data form corresponding to the quadtree includes quadtree data.

[0226] Optionally, the prior knowledge types corresponding to the AI ​​data include dictionaries and pre-trained models. The subtypes corresponding to the dictionaries include multi-dimensional weighted dictionaries and single-dimensional dictionaries. The data forms corresponding to the multi-dimensional weighted dictionaries include dictionary dimensions, dictionary data, and sparsity. The data forms corresponding to the pre-trained models include model parameters.

[0227] Optionally, the receiving module 903 is used to receive indication information sent by the terminal device; or, the sending module 901 is used to send indication information to the terminal device; wherein the indication information is used to indicate the type information.

[0228] Optionally, the indication information includes an application scenario or data type, or the indication information includes a first index, which is used to indicate at least one type of information in a pre-configured prior knowledge type mapping table, wherein the prior knowledge type mapping table includes mapping relationships between multiple types of information and the index.

[0229] Optionally, the receiving module 903 is configured to receive first indication information sent by the terminal device, wherein the first indication information is used to indicate at least one type of prior knowledge information supported by the terminal device;

[0230] The sending module 901 is used to send second indication information to the terminal device, the second indication information being used to indicate type information selected from the at least one type of information.

[0231] Optionally, the receiving module 903 is configured to receive third indication information sent by the terminal device, the third indication information being used to indicate the type information of the prior knowledge required by the terminal device;

[0232] The sending module 901 is used to send fourth indication information to the terminal device, the fourth indication information being used to indicate whether there is prior knowledge data corresponding to the type information.

[0233] Optionally, the sending module 901 is used to send fifth indication information to the terminal device, the fifth indication information being used to indicate that the network device supports at least one type of information of the prior knowledge provided;

[0234] The receiving module 903 is configured to receive a sixth indication information sent by the terminal device, the sixth indication information being used to indicate type information selected from the at least one type of information.

[0235] Optionally, the sending module 901 is used to send seventh indication information to the terminal device, the seventh indication information being used to indicate the type information of the prior knowledge;

[0236] The receiving module 903 is used to receive the eighth indication information sent by the terminal device, the eighth indication information being used to indicate whether it supports processing the prior knowledge data corresponding to the type information.

[0237] Optionally, the processing module 902 is also used to update the type information according to a preset period.

[0238] Optionally, the processing module 902 is further configured to update the type information when a triggering condition is met, wherein the triggering condition includes at least one of the following changes: the application scenario, the prior knowledge data, or the local data.

[0239] In one possible design, when the data processing device is a network device or a communication module within a network device, the functionality of the processing module 902 can be implemented by one or more processors. Specifically, the processor may include a modem chip, or a system-on-a-chip (SoC) or SIP chip containing a modem core. The functions of the transmitting module 901 and the receiving module 903 can be implemented by transceiver circuitry.

[0240] In one possible design, when the data processing device is a circuit or chip responsible for communication functions in a network device, such as a modem chip or a system-on-a-chip (SoC) or SIP chip containing a modem core, the functions of the transmitting module 901 and the receiving module 903 can be implemented by the interface circuitry or data transceiver circuitry on the aforementioned chip. The function of the processing module 902 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processor cores.

[0241] It should be noted that the implementation of each module can also be referenced accordingly. Figure 2 The corresponding description of the method embodiments shown indicates that the methods and functions performed by the network device in the above embodiments are executed.

[0242] Figure 10 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. This terminal device can be applied to, for example... Figure 1 In the system shown, the functions of the terminal device in the above method embodiments are executed, or the steps or processes executed by the terminal device in the above method embodiments are implemented.

[0243] like Figure 10 As shown, the terminal device includes a processor 1001 and a transceiver 1002. The transceiver 1002 includes a transmitter 1021, a receiver 1022, and an antenna 1023. The receiver 1022 can be used to receive transmission control information through the antenna 1023, and the transmitter 1021 can be used to send transmission feedback information to the network device through the antenna 1023. Optionally, the terminal device also includes a memory 1003. The processor 1001, transceiver 1002, and memory 1003 can communicate with each other through internal connection paths to transmit control and / or data signals. The memory 1003 is used to store computer programs, and the processor 1001 is used to call and run the computer programs from the memory 1003 to control the transceiver 1002 to transmit and receive signals. Optionally, the terminal device may also include an antenna for transmitting uplink data or uplink control signaling output by the transceiver 1002 via wireless signals.

[0244] The processor 1001 and memory 1003 can be integrated into a single processing device. The processor 1001 executes the program code stored in the memory 1003 to implement the aforementioned functions. In specific implementations, the memory 1003 can be integrated into the processor 1001 or independent of it. The processor 1001 can be combined with... Figure 8 The corresponding processing module in [the system / processing module].

[0245] The transceiver 1002 described above can be used with Figure 8 The receiving module and transmitting module in the transceiver 1002 correspond to each other and can also be called a transceiver unit or transceiver module. The transceiver 1002 may include a receiver (or receiver circuit) and a transmitter (or transmitter circuit). The receiver is used to receive signals, and the transmitter is used to transmit signals.

[0246] It should be understood that Figure 10 The terminal device shown can achieve Figure 2 The methods illustrated in the embodiments involve various processes of the terminal device. The operations and / or functions of each module in the terminal device are respectively for implementing the corresponding processes in the above method embodiments. For details, please refer to the descriptions in the above method embodiments; to avoid repetition, detailed descriptions are appropriately omitted here.

[0247] The processor 1001 described above can be used to execute the actions implemented internally by the terminal device as described in the preceding method embodiments, while the transceiver 1002 can be used to execute the actions described in the preceding method embodiments of sending data to or receiving data from the network device by the terminal device. Please refer to the descriptions in the preceding method embodiments for details, which will not be repeated here.

[0248] The processor 1001 can be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor 1001 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor and a microprocessor, etc. The terminal device may also include a communication bus, which can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The communication bus is used to realize the connection and communication between these components. In this embodiment, the transceiver 1002 is used for signaling or data communication with other node devices. The memory 1003 may include volatile memory, such as nonvolatile random access memory (NVRAM), phase change RAM (PRAM), magnetoresistive RAM (MRAM), etc., and may also include non-volatile memory, such as at least one disk storage device, electrically erasable programmable read-only memory (EEPROM), flash memory devices, such as NOR flash memory or NAND flash memory, semiconductor devices, such as solid-state disks (SSDs), etc. Optionally, the memory 1003 may also be at least one storage device located remotely from the aforementioned processor 1001. Optionally, the memory 1003 may also store a set of computer program code or configuration information. Optionally, the processor 1001 may also execute the program stored in the memory 1003. The processor can cooperate with the memory and transceiver to execute any of the methods and functions of the terminal device in the above-described embodiments.

[0249] Figure 11 This is a schematic diagram of the structure of a network device provided in an embodiment of this application. This network device can be applied to, for example... Figure 1 In the system shown, the functions of the network device in the above method embodiments are executed, or the steps or processes executed by the network device in the above method embodiments are implemented.

[0250] like Figure 11 As shown, the network device includes a processor 1101 and a transceiver 1102. The transceiver 1102 includes a transmitter 1121, a receiver 1122, and an antenna 1123. The transmitter 1121 can be used to send transmission control information to a terminal device via the antenna 1123, and the receiver 1122 can be used to receive transmission feedback information sent by the terminal device via the antenna 1123. Optionally, the network device also includes a memory 1103. The processor 1101, transceiver 1102, and memory 1103 can communicate with each other through internal connections to transmit control and / or data signals. The memory 1103 stores computer programs, and the processor 1101 calls and runs the computer program from the memory 1103 to control the transceiver 1102 to transmit and receive signals. Optionally, the network device may also include an antenna for transmitting uplink data or uplink control signaling output by the transceiver 1102 via wireless signals.

[0251] The aforementioned processor 1101 can be with Figure 9 The corresponding processing module is described above. The processor 1101 and the memory 1103 can be integrated into a single processing device. The processor 1101 executes the program code stored in the memory 1103 to achieve the above functions. In specific implementations, the memory 1103 can be integrated into the processor 1101 or independent of the processor 1101.

[0252] The transceiver 1102 described above can be used with Figure 9 The receiving module and transmitting module in the transceiver unit correspond to each other and can also be called a transceiver unit or transceiver module. The transceiver 1102 may include a receiver (or receiver circuit) and a transmitter (or transmitter circuit). The receiver is used to receive signals, and the transmitter is used to transmit signals.

[0253] It should be understood that Figure 11 The network device shown can achieve Figure 2 The methods illustrated in the embodiments involve various processes of the network device. The operations and / or functions of each module in the network device are respectively for implementing the corresponding processes in the above method embodiments. For details, please refer to the descriptions in the above method embodiments; to avoid repetition, detailed descriptions are appropriately omitted here.

[0254] The processor 1101 described above can be used to execute the actions implemented internally by the network device as described in the preceding method embodiments, while the transceiver 1102 can be used to execute the actions described in the preceding method embodiments of sending data from the network device to the terminal device or receiving data from the terminal device. Please refer to the descriptions in the preceding method embodiments for details, which will not be repeated here.

[0255] The processor 1101 can be any of the processors mentioned above. The network device may also include a communication bus, which can be a PCI bus (Peripheral Component Interconnect Standard) or an EISA bus (Extended Industry Standard Architecture). The bus can be divided into an address bus, a data bus, and a control bus. The communication bus is used to enable communication between these components. In this embodiment, the transceiver 1102 is used for signaling or data communication with other devices. The memory 1103 can be any of the memory types mentioned above. Optionally, the memory 1103 can also be at least one storage device located remotely from the processor 1101. The memory 1103 stores a set of computer program code or configuration information, and the processor 1101 executes the program in the memory 1103. The processor can cooperate with the memory and the transceiver to execute any of the methods and functions of the network device in the above embodiments.

[0256] This application also provides a chip system including a processor for supporting terminal devices or network devices to implement the functions involved in any of the above embodiments, such as generating or processing measurement results involved in the above methods.

[0257] In one possible design, the chip system may further include a memory for storing necessary computer programs and data for the terminal device or network device. The chip system may be composed of chips or may include chips and other discrete components. The inputs and outputs of the chip system correspond to the receiving and transmitting operations of the terminal device or network device in the method embodiment, respectively.

[0258] According to the method provided in the embodiments of this application, this application also provides a computer program product, which includes: a computer program that, when run on a computer, causes the computer to perform... Figure 2 The method of any one of the embodiments shown.

[0259] According to the method provided in the embodiments of this application, this application also provides a computer-readable medium storing a computer program, which, when run on a computer, causes the computer to perform... Figure 2 The method of any one of the embodiments shown.

[0260] According to the method provided in the embodiments of this application, this application also provides a communication system, which includes one or more terminal devices and one or more network devices as described above.

[0261] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

Claims

1. A data processing method, characterized by, The method comprises: determining configuration information, the configuration information being used to indicate type information of prior knowledge, wherein the prior knowledge is obtained data or data processed from the obtained data; receiving data of the prior knowledge sent by a network device, the data of the prior knowledge corresponding to the type information; processing local data based on the data of the prior knowledge.

2. The method of claim 1, wherein, The type information comprises a prior knowledge type and / or a data form.

3. The method of claim 1 or 2, wherein, The type information corresponds to an application scenario, the application scenario comprising at least one of channel data transmission, artificial intelligence (AI) data transmission or perception data transmission.

4. The method of claim 1 or 2, wherein, The type information corresponds to a data type of the local data, the data type comprising at least one of AI data, perception data or channel data.

5. The method according to any one of claims 1 to 4, characterized in that, The type information comprises first-order type information and second-order type information, the second-order type information being a sub-type of the first-order type information.

6. The method of claim 4, wherein, The prior knowledge type corresponding to the perception data comprises at least one of a dictionary, geometry, region division or semantics, wherein the sub-type corresponding to the dictionary comprises multi-dimensional weighting and a single-dimensional dictionary, the data form corresponding to the multi-dimensional weighting comprising a dictionary dimension, dictionary data and sparsity; the sub-type corresponding to the geometry comprises a surface, the data form corresponding to the surface comprising a surface parameter and a scanned region on the surface; the sub-type corresponding to the region division comprises an octree and a voxel, the data form corresponding to the octree comprising octree data, the data form corresponding to the voxel comprising voxel data; the sub-type corresponding to the semantics comprises a 3D target box, the data form corresponding to the 3D target box comprising a center position and a range of the 3D target box and / or vertex coordinates of the 3D target box.

7. The method of claim 4, wherein, The prior knowledge type corresponding to the channel data comprises at least one of a dictionary or region division, wherein the sub-type corresponding to the dictionary comprises multi-dimensional weighting and a single-dimensional dictionary, the data form corresponding to the multi-dimensional weighting comprising a dictionary dimension, dictionary data and sparsity; the sub-type corresponding to the region division comprises a bitmap and a quadtree, the data form corresponding to the bitmap comprising bitmap data, the data form corresponding to the quadtree comprising quadtree data.

8. The method of claim 4, wherein, The prior knowledge type corresponding to the AI data comprises a dictionary and a pre-trained model, wherein the sub-type corresponding to the dictionary comprises multi-dimensional weighting and a single-dimensional dictionary, the data form corresponding to the multi-dimensional weighting comprising a dictionary dimension, dictionary data and sparsity; the data form corresponding to the pre-trained model comprising model parameters.

9. The method according to any one of claims 1 to 8, wherein, The determination of the configuration information comprises: receiving indication information sent by the network device; or, sending indication information to the network device, wherein the indication information is used to indicate the type information.

10. The method of claim 9, wherein, The indication information comprises an application scenario or a data type, or the indication information comprises a first index, the first index being used to indicate at least one type information in a pre-configured prior knowledge type mapping table, the prior knowledge type mapping table comprising a mapping relationship between multiple types of information and indexes.

11. The method of any one of claims 1-10, wherein, The determination of the configuration information comprises: sending first indication information to the network device, the first indication information being used for indicating at least one type of information of the prior knowledge supported by itself; receiving second indication information sent by the network device, the second indication information being used for indicating type information selected from the at least one type of information.

12. The method of any one of claims 1-10, wherein, The determination configuration information comprises: sending third indication information to the network device, the third indication information being used for indicating type information of the prior knowledge required by itself; receiving fourth indication information sent by the network device, the fourth indication information being used for indicating whether there is data of the prior knowledge corresponding to the type information.

13. The method of any one of claims 1-10, wherein, The determination configuration information comprises: receiving fifth indication information sent by the network device, the fifth indication information being used for indicating at least one type of information of the prior knowledge supported by the network device for providing; sending sixth indication information to the network device, the sixth indication information being used for indicating type information selected from the at least one type of information.

14. The method of any one of claims 1-10, wherein, The determination configuration information comprises: receiving seventh indication information sent by the network device, the seventh indication information being used for indicating type information of the prior knowledge; sending eighth indication information to the network device, the eighth indication information being used for indicating whether to support processing data of the prior knowledge corresponding to the type information.

15. The method of any one of claims 1-14, wherein, The method further comprises: updating the type information according to a preset period.

16. The method of any one of claims 1-14, wherein, The method further comprises: updating the type information when a trigger condition is met, the trigger condition comprising at least one of the following changing: an application scenario, data of the prior knowledge or the local data.

17. A data processing method, characterized by, The method comprises: determining configuration information, the configuration information being used for indicating type information of prior knowledge, wherein the prior knowledge is obtained data or data processed based on the obtained data; sending data of the prior knowledge to a terminal device, the data of the prior knowledge corresponding to the type information, and the data of the prior knowledge being used for processing local data of the terminal device.

18. The method of claim 17, wherein, The type information comprises a prior knowledge type and / or a data form.

19. The method of claim 17 or 18, wherein, The type information corresponds to an application scenario, and the application scenario comprises at least one of the following: channel data transmission, artificial intelligence (AI) data transmission or perception data transmission.

20. The method of claim 17 or 18, wherein, The type information corresponds to a data type of the local data, and the data type comprises at least one of the following: AI data, perception data or channel data.

21. The method of any one of claims 17-20, wherein, The type information comprises first-order type information and second-order type information, and the second-order type information is a sub-type of the first-order type information.

22. The method of claim 20, wherein, The prior knowledge type corresponding to the perception data comprises at least one of the following: a dictionary, geometry, region division or semantics, wherein the sub-type corresponding to the dictionary comprises multi-dimensional weighting and single-dimensional dictionary, the data form corresponding to the multi-dimensional weighting comprises dictionary dimension, dictionary data and sparsity; the sub-type corresponding to the geometry comprises a surface, and the data form corresponding to the surface comprises surface parameters and a scanned region on the surface; the sub-type corresponding to the region division comprises octree and voxel, the data form corresponding to the octree comprises octree data, and the data form corresponding to the voxel comprises voxel data; and the sub-type corresponding to the semantics comprises a 3D target box, and the data form corresponding to the 3D target box comprises a center position and range of the 3D target box and / or vertex coordinates of the 3D target box.

23. The method of claim 20, wherein, The prior knowledge type corresponding to the channel data comprises at least one of the following: a dictionary or region division, wherein the sub-type corresponding to the dictionary comprises multi-dimensional weighting and single-dimensional dictionary, the data form corresponding to the multi-dimensional weighting comprises dictionary dimension, dictionary data and sparsity; and the sub-type corresponding to the region division comprises a bit map and quadtree, the data form corresponding to the bit map comprises bit map data, and the data form corresponding to the quadtree comprises quadtree data.

24. The method of claim 20, wherein, The prior knowledge type corresponding to the AI data comprises a dictionary and a pre-trained model, wherein the sub-type corresponding to the dictionary comprises multi-dimensional weighting and single-dimensional dictionary, the data form corresponding to the multi-dimensional weighting comprises dictionary dimension, dictionary data and sparsity; and the data form corresponding to the pre-trained model comprises model parameters.

25. The method of any one of claims 17-24, wherein, The determination configuration information comprises: receiving indication information sent by the terminal device, or sending indication information to the terminal device, wherein the indication information is used to indicate the type information.

26. The method of claim 25, wherein, The indication information comprises an application scenario or a data type, or the indication information comprises a first index used to indicate at least one type information in a pre-configured prior knowledge type mapping table, and the prior knowledge type mapping table comprises a mapping relationship between multiple type information and indexes.

27. The method of any one of claims 17-26, wherein, The determination configuration information comprises: receiving first indication information sent by the terminal device, the first indication information being used to indicate at least one type information of the prior knowledge supported by the terminal device; sending second indication information to the terminal device, the second indication information being used to indicate type information selected from the at least one type information.

28. The method of any one of claims 17-26, wherein, The determination configuration information comprises: receiving third indication information sent by the terminal device, the third indication information being used to indicate type information of the prior knowledge required by the terminal device; sending fourth indication information to the terminal device, the fourth indication information being used to indicate whether there is data of the prior knowledge corresponding to the type information.

29. The method of any one of claims 17-26, wherein, The determination configuration information comprises: sending fifth indication information to the terminal device, the fifth indication information being used to indicate at least one type information of the prior knowledge supported by the network device for providing; receive sixth indication information sent by the terminal device, the sixth indication information being used to indicate type information selected from the at least one type of information.

30. The method of any one of claims 17-26, wherein, The determination configuration information comprises: send seventh indication information to the terminal device, the seventh indication information being used to indicate type information of the priori knowledge; receive eighth indication information sent by the terminal device, the eighth indication information being used to indicate whether to support processing data of the type information corresponding to the priori knowledge.

31. The method of any one of claims 17-30, wherein, The method further comprises: updating the type information according to a preset period.

32. The method of any one of claims 17-30, wherein, The method further comprises: updating the type information when a trigger condition is met, the trigger condition comprising at least one of the following changing: an application scenario, data of the priori knowledge, or the local data.

33. A data processing apparatus, characterized by: comprising a memory and a processor, the memory being used to store a computer program, and the processor being used to run the computer program to make the data processing apparatus execute the method in any one of claims 1-16.

34. A data processing apparatus, characterized in that, comprising a memory and a processor, the memory being used to store a computer program, and the processor being used to run the computer program to make the data processing apparatus execute the method in any one of claims 17-32.

35. A computer readable storage medium, characterized in that, The computer readable storage medium comprises a computer program, when the computer program is run by a processor, the method in any one of claims 1-16, or any one of claims 17-32 is implemented.

36. A chip, characterized by The chip comprises a processor and a communication interface, the communication interface being used to communicate with external devices or internal devices, and the processor being used to implement the method in any one of claims 1-16, or any one of claims 17-32.

37. A computer program product comprising instructions, wherein: When it is run on a computer, the computer is made to execute the method in any one of claims 1-16, or any one of claims 17-32.

Images