Perception method and device

Abstract

The invention discloses a sensing method and device. The first device inputs first compression information to the decompression model to obtain second sensing information output by the decompression model, the first compression information is related to first sensing information, and the first sensing information comprises information indicating first power corresponding to at least one spatial position; the second perception information comprises information indicating second power corresponding to at least one spatial position. The first equipment updates parameters of the compression model and / or the decompression model according to a loss function, the loss function comprises a distortion function between the first perception information and the second perception information, and the distortion function is related to a power difference value corresponding to at least one spatial position and the maximum first power indicated by the first perception information; the power difference value corresponding to one spatial position in the at least one spatial position refers to the difference value of the first power and the second power. According to the embodiment of the invention, the distortion function enables the power recovery of the receiving end to be more accurate, and facilitates the improvement of the sensing precision.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of perception, and particularly relates to a perception method and device. BACKGROUND

[0002] For a perception service, a reflection, scattering or diffraction of a signal sent by a user equipment (UE) or a base station on a perception target when the signal propagates in space can be utilized to perceive a position or shape of the perception target in an environment. Taking a scenario in which the UE and the base station participate in perception as an example, the UE can measure the signal reflected, scattered or diffracted by the perception target, and report a measurement result to the base station, so that the base station implements perception of the perception target.

[0003] However, a data volume of the measurement result is large, and reporting the measurement result by the UE can cause large transmission overhead. SUMMARY

[0004] Embodiments of the present application provide a perception method and device, which are used to reduce transmission overhead. The perception method and device can also be regarded as a communication method and device, or a perception-communication integrated method and device, or a model training method and device.

[0005] In a first aspect, a first perception method is provided, which can be applied to a first device. The first device can be, for example, a first apparatus, or another apparatus including a function of the first apparatus, or a circuit, or a chip system. The first device can be, for example, a terminal-side device, which can also be referred to as a terminal device. The terminal device can be, for example, a terminal apparatus, or another apparatus including a function of the terminal apparatus, or a circuit, or a chip system (or a chip, such as a modem chip, also referred to as a baseband chip, or a system on chip (SoC) chip or a system in package (SIP) chip containing a modem core) or another functional module capable of realizing the function of the terminal apparatus, which can be arranged in the terminal apparatus. Alternatively, the first device can be a network-side device, which can also be referred to as a network device. The network device can be, for example, an access network apparatus, or another apparatus including a function of the access network apparatus, or a circuit, or a chip system (or a chip) or another functional module capable of realizing the function of the network apparatus, which can be arranged in the network apparatus. The access network apparatus can be a non-ORAN architecture or an ORAN architecture; alternatively, the access network apparatus can be an SU, a CU, a DU or an RU under the ORAN architecture. The access network apparatus can be located on the ground, or the access network apparatus can be a satellite, or located on a satellite. In the following description, the first device is taken as an example of the first apparatus. According to the above description, the first apparatus can be, for example, a terminal apparatus or an access network apparatus. The method includes: inputting first compressed information into a decompression model to obtain second perception information output by the decompression model, wherein the first compressed information is related to first perception information, the first perception information includes information indicating a first power corresponding to at least one spatial position, and the second perception information includes information indicating a second power corresponding to the at least one spatial position; and updating parameters of a compression model and / or the decompression model according to a loss function, wherein the loss function includes a distortion function between the first perception information and the second perception information, the distortion function is related to a power difference value corresponding to the at least one spatial position and a maximum first power indicated by the first perception information, and the power difference value corresponding to one of the at least one spatial position is a difference between the first power and the second power.

[0006] The embodiments of the present application can train a compression model and a decompression model, so that the first perception information can be compressed by using the compression model, and the compressed first perception information has a smaller data amount than the uncompressed first perception information, thereby reducing transmission overhead. The first perception information can include first power corresponding to at least one spatial position, and the loss function used for training in the embodiments of the present application can be related to a power difference corresponding to the at least one spatial position and a maximum power indicated by the first perception information. For example, in the first power corresponding to the at least one spatial position, the greater the first power, the smaller the error caused by compression, so that the recovery of the receiving end for the greater first power is more accurate, thereby making the determined position of the perception target more accurate, and helping to improve the perception accuracy.

[0007] In an optional embodiment, the distortion function includes a weighting coefficient corresponding to the at least one spatial position, and the weighting coefficient is related to the maximum first power indicated by the first perception information. The embodiments of the present application can correct the power error corresponding to the spatial position by using the weighting coefficient. For example, each spatial position can correspond to a weighting coefficient, so that different spatial positions can correct the power error by using the respective weighting coefficients, so that the correction granularity is finer.

[0008] In an optional embodiment, the distortion function satisfies the following relationship: wherein L d represents the value of the distortion function, p' k represents the second power corresponding to the kth spatial position indicated by the second perception information, p k represents the first power corresponding to the kth spatial position indicated by the first perception information, 0 < k < K, K represents the number of the at least one spatial position, w k represents the weighting coefficient corresponding to the kth spatial position. This is an embodiment of the distortion function, and other embodiments are also possible. In addition, the formula can also have other variations, for example, one or more constants can be added in the formula, and the present application is not limited in this regard.

[0009] In an optional implementation, the kth spatial position in the at least one spatial position corresponds to a kth weighting coefficient, the kth weighting coefficient being related to the first power corresponding to the kth spatial position indicated by the first perception information, and being related to the maximum first power and / or the minimum first power indicated by the first perception information. The weighting coefficient can be related to the maximum first power and / or the minimum first power indicated by the first perception information. For example, the weighting coefficient corresponding to the spatial position corresponding to the greater first power can be greater, and the power error corrected by the weighting coefficient can be smaller, so that the recovery of the receiving end for the greater first power is more accurate, thereby making the determined position of the perceived target more accurate, and facilitating the improvement of the perception accuracy.

[0010] In an optional implementation, the kth weighting coefficient satisfies the following relationship: wherein p k represents the first power corresponding to the kth spatial position indicated by the first perception information, p min represents the minimum first power indicated by the first perception information, p max represents the maximum first power indicated by the first perception information. This is an implementation of the weighting coefficient, and other implementations are also possible. In addition, the formula can also have other modifications, for example, one or more constants can be added to the formula, and the like, which are not limited.

[0011] In an optional implementation, the value of the kth weighting coefficient is the value corresponding to the power range of the first power corresponding to the kth spatial position, and the power range is determined according to the maximum first power and / or the minimum first power indicated by the first perception information. This is another implementation of the weighting coefficient, and other implementations are also possible.

[0012] In an optional implementation, the loss function further includes a compression rate function between the first compression information and the first perception information. In addition to the distortion function, the loss function can include one or more other functions, which are not limited.

[0013] In an optional implementation, the method further comprises: inputting the first perception information into the compression model to obtain the first compressed information output by the compression model; or, receiving the first compressed information. For example, the training process can be completed independently by the first device, which can be an offline training manner. In the offline training manner, the first device can first obtain the first perception information, and then obtain the first compressed information according to the first perception information. For example, the first perception information is obtained by the first device from a training sample library, and the first perception information can be a sample in the training sample library. Alternatively, the training process can be completed by the first device and the second device, or understood as being completed by the second device to assist the first device, which can be an online training manner. In the online training manner, for example, the second device can obtain the first perception information, and after obtaining the first compressed information according to the first perception information, the second device can send the first compressed information to the first device. It can be seen that the embodiments of the present application can adopt an offline training manner or an online training manner, and the training process is more flexible.

[0014] In an optional implementation, the first compressed information is received, and the method further comprises: receiving a first perception signal; and determining the first perception information according to the first perception signal. If the online training manner is adopted, the actual first perception information is obtained by the second device, and the second device obtains the first compressed information accordingly. The second device sends the first compressed information to the first device, and can not send the first perception information to the first device. Therefore, the first device can obtain the first perception information in a corresponding manner. For example, the first device can generate the first perception information according to the received first perception signal. Due to the reciprocity of the uplink and downlink channels, it can be considered that the first perception information generated by the first device is the same as the first perception information on the second device side, or understood as the first perception information generated by the first device can replace the first perception information on the second device side. In this way, the reporting amount of the second device can be reduced, and the transmission overhead is saved.

[0015] In an optional implementation, the method further comprises: sending information of an updated compression model. After the model training is completed, the first device can send the trained compression model to the second device, and the trained decompression model is maintained by the first device, for example, so that the first device and the second device can compress and decompress the perception information according to the trained compression model and decompression model.

[0016] In a second aspect, a second sensing method is provided, which can be applied to a second device. The second device can be a second apparatus, or another apparatus including a function of the second apparatus, or a circuit, or a chip system. The second device can be a terminal-side device, or a network-side device. The terminal-side device or the network-side device can refer to the description of the first aspect. The method includes: sending first compressed information, the first compressed information being used to determine a loss function, wherein the loss function includes a distortion function between first sensing information and second sensing information, the first sensing information and the second sensing information are related to the first compressed information, the first sensing information includes information indicating a first power corresponding to at least one spatial position, the second sensing information includes information indicating a second power corresponding to the at least one spatial position, the distortion function is related to a power difference corresponding to the at least one spatial position and a maximum first power included in the first sensing information, and the power difference corresponding to one spatial position in the at least one spatial position is a difference between the first power and the second power.

[0017] In an optional implementation, the distortion function includes a weighting coefficient corresponding to the at least one spatial position, and the weighting coefficient is related to the maximum first power indicated by the first sensing information.

[0018] In an optional implementation, the distortion function satisfies the following relationship: wherein L d represents a value of the distortion function, p' k represents the second power corresponding to the kth spatial position indicated by the second sensing information, p k represents the first power corresponding to the kth spatial position indicated by the first sensing information, 0 < k < K, K represents a number of the at least one spatial position, w k represents the weighting coefficient corresponding to the kth spatial position.

[0019] In an optional implementation, the kth spatial position in the at least one spatial position corresponds to a kth weighting coefficient, and the kth weighting coefficient is related to the first power corresponding to the kth spatial position indicated by the first sensing information, and the maximum first power and / or the minimum first power indicated by the first sensing information.

[0020] In an optional implementation, the kth weighting coefficient satisfies the following relationship: wherein p k represents the first power corresponding to the kth spatial position indicated by the first sensing information, p min represents the minimum first power indicated by the first sensing information, p maxa maximum first power indicated by the first perception information.

[0021] In an optional implementation, a value of the kth weighting coefficient is a value corresponding to a power range in which a first power corresponding to the kth spatial position is located, and the power range is determined according to a maximum first power and / or a minimum first power indicated by the first perception information.

[0022] In an optional implementation, the loss function further includes a compression rate function between the first compression information and the first perception information.

[0023] In an optional implementation, the method further includes: receiving a second perception signal; generating the first perception information according to the second perception signal; and inputting the first perception information into a compression model to obtain the first compression information.

[0024] In an optional implementation, the method further includes: sending a first perception signal.

[0025] In an optional implementation, the method further includes: receiving information of an updated compression model.

[0026] As to the technical effects brought by the second aspect or various optional implementations, reference can be made to the introduction of the technical effects of the first aspect or corresponding implementations.

[0027] In a third aspect, an apparatus is provided. The apparatus can be the first apparatus of the first aspect. The apparatus has the functions of the first apparatus. For example, the apparatus has the functions of the first aspect. For example, the apparatus includes modules or units or means for performing the operations of the first aspect. The modules or units or means can be implemented in software or hardware, or a combination thereof. The apparatus is, for example, a terminal device, or another device with terminal device functions, or a chip system (or chip or circuitry) or another functional module that can implement the functions of the terminal device, e.g., arranged in the terminal device. Alternatively, the apparatus is, for example, a network device, or another device with network device functions, or a chip system (or chip or circuitry) or another functional module that can implement the functions of the network device, e.g., arranged in the network device. The network device includes, for example, one or more of the following: a core network device, an access network device, a SU, a CU, a DU, or a RU. In an optional implementation, the apparatus includes a baseband apparatus and a radio frequency apparatus. In another optional implementation, the apparatus includes a processing unit (also sometimes referred to as a processing module) and a transceiving unit (also sometimes referred to as a transceiving module). The transceiving unit can implement the transmitting function and the receiving function. When the transceiving unit implements the transmitting function, it can be referred to as a transmitting unit (also sometimes referred to as a transmitting module). When the transceiving unit implements the receiving function, it can be referred to as a receiving unit (also sometimes referred to as a receiving module). The transmitting unit and the receiving unit can be the same functional module, which is referred to as a transceiving unit. The transceiving unit can implement the transmitting function and the receiving function. Alternatively, the transmitting unit and the receiving unit can be different functional modules, and the transceiving unit refers to these functional modules in general.

[0028] In an optional implementation, the processing unit is configured to input the first compressed information into the decompression model to obtain second perceptual information output by the decompression model, where the first compressed information is related to the first perceptual information, the first perceptual information includes information indicating a first power corresponding to at least one spatial position, and the second perceptual information includes information indicating a second power corresponding to the at least one spatial position; and the processing unit is further configured to update parameters of the compression model and / or the decompression model according to a loss function, where the loss function includes a distortion function between the first perceptual information and the second perceptual information, the distortion function is related to a power difference value corresponding to the at least one spatial position and a maximum first power indicated by the first perceptual information, and the power difference value corresponding to one of the at least one spatial position is a difference between the first power and the second power.

[0029] In an alternative implementation, the apparatus further includes a storage unit (also referred to as a storage module), and the processing unit is configured to be coupled with the storage unit and to execute programs or instructions in the storage unit to enable the apparatus to perform the functions of the second apparatus of the second aspect.

[0030] In a fourth aspect, an apparatus is provided. The apparatus can be the second apparatus of the second aspect. The apparatus is enabled to perform the functions of the second apparatus. For example, the apparatus is enabled to perform the functions of the second aspect, e.g., the apparatus includes modules or units or means for performing the operations of the second aspect, which can be implemented in software, or in hardware, or in a combination of software and hardware. The apparatus can be, for example, a network device, or another device that includes the functionality of a network device, or a chip system (or chip or circuitry) or another functional module that is enabled to perform the functions of a network device, e.g., the chip system or functional module is included in a network device. The network device can include, for example, a core network device and / or an access network device. Optionally, the network device includes, for example, one or more of the following: a core network device, an access network device, a SU, a CU, a DU, or a RU. In an alternative implementation, the apparatus includes a baseband apparatus and a radio frequency apparatus. In another alternative implementation, the apparatus includes a processing unit (also referred to as a processing module) and a transceiver unit (also referred to as a transceiver module). The transceiver unit can be implemented as described in the third aspect.

[0031] In an alternative implementation, the transceiver unit (or the sending unit) is configured to send first compressed information, the first compressed information being used to determine a loss function, wherein the loss function includes a distortion function between first perception information and second perception information, the first perception information and the second perception information are related to the first compressed information, the first perception information includes information indicating a first power corresponding to at least one spatial position, the second perception information includes information indicating a second power corresponding to the at least one spatial position, the distortion function is related to a power difference corresponding to the at least one spatial position and a maximum first power included in the first perception information, wherein the power difference corresponding to one of the at least one spatial position is a difference between the first power and the second power.

[0032] In an alternative implementation, the apparatus further includes a storage unit (also referred to as a storage module), and the processing unit is configured to be coupled with the storage unit and to execute programs or instructions in the storage unit to enable the apparatus to perform the functions of the second apparatus of the second aspect.

[0033] In a fifth aspect, a device is provided, which includes a memory and one or more processors. The memory is configured to store part or all of the computer program or instructions necessary to implement the functions related to the first aspect or the second aspect described above. The one or more processors are configured to execute the computer program or instructions, which when executed cause the device to implement the method in any possible design or implementation of the first aspect or the second aspect described above.

[0034] In a possible design, the device can further include an interface circuit, where the processor is configured to communicate with other devices or components through the interface circuit.

[0035] In a possible design, the device can further include the memory.

[0036] The device described above can be a terminal, or a communication module in the terminal, or a chip responsible for communication functions in the terminal, such as a modem chip (also referred to as a baseband chip) or an SoC or SIP chip including a modem module.

[0037] In a sixth aspect, a device is provided, which includes a memory and one or more processors. The memory is configured to store part or all of the computer program or instructions necessary to implement the functions related to the first aspect or the second aspect described above. The one or more processors are configured to execute the computer program or instructions, which when executed cause the device to implement the method in any possible design or implementation of the first aspect or the second aspect described above.

[0038] In a possible design, the device can further include an interface circuit, where the processor is configured to communicate with other devices or components through the interface circuit.

[0039] In a possible design, the device can further include the memory.

[0040] The device described above can be a network device, or a communication module in the network device, or a chip responsible for communication functions in the network device, such as a modem chip (also referred to as a baseband chip) or an SoC or SIP chip including a modem module.

[0041] In a seventh aspect, a communication system is provided, which includes a first device. The first device is configured to perform the method performed by the first device described in the first aspect described above. For example, the first device can be implemented by the device described in the third aspect, the fifth aspect, or the sixth aspect.

[0042] Optionally, the communication system further includes a second device, which is configured to perform the method performed by the second device described in the second aspect described above. For example, the second device can be implemented by the device described in the fourth aspect, the fifth aspect, or the sixth aspect.

[0043] In an eighth aspect, a computer-readable storage medium is provided for storing a computer program or instructions, which when executed, cause the method performed by the first device or the second device in the above aspects to be implemented.

[0044] In a ninth aspect, a computer program product containing instructions, which when executed on a computer, cause the method in the above aspects to be implemented.

[0045] In a tenth aspect, a chip system is provided, comprising a processor and an interface, the processor being configured to call and execute instructions from the interface, so that the chip system implements the method in the above aspects. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 FIG. 1 is a schematic diagram of a structure of an access network device in an embodiment of the present application;

[0047] Figure 2A FIG. 2 is a schematic diagram of a single-station sensing mode;

[0048] Figure 2B FIG. 3 is a schematic diagram of a double-station sensing mode;

[0049] Figure 3 FIG. 4 is a schematic diagram of two application scenarios of an embodiment of the present application; Figure 4

[0050] Figure 5 FIG. 5 is a flowchart of two sensing methods provided by an embodiment of the present application; Figure 7

[0051] FIG. 6 is a schematic diagram of a compression model and a decompression model in an embodiment of the present application; Figure 6

[0052] FIG. 7 is a schematic diagram of at least one spatial position in an embodiment of the present application; Figure 8

[0053] FIG. 8 is a schematic diagram of a device provided by an embodiment of the present application; Figure 9

[0054] FIG. 9 is a schematic diagram of another device provided by an embodiment of the present application. Figure 10 DETAILED DESCRIPTION In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0055]

[0056] ​​In the embodiments of the present application, the number of nouns, unless otherwise specified, represents "a singular noun or a plural noun", that is, "one or more". "At least one" refers to one or more, and "multiple" refers to two or more. "And / or" describes the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B can represent: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects. For example, A / B represents: A or B. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c represents: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0057] The ordinal numbers "first", "second", and the like mentioned in the embodiments of the present application are used to distinguish a plurality of objects, and are not used to limit the size, content, order, time sequence, priority, or importance of the plurality of objects. In addition, the numbering of steps in each embodiment introduced in the present application is only to distinguish different steps, and is not used to limit the order of the steps.

[0058] In the following, some terms or concepts in the embodiments of the present application are explained and described to facilitate understanding by those skilled in the art.

[0059] In the embodiments of the present application, the terminal device is a device with wireless transceiving function, which can be a fixed device, a mobile device, a handheld device (for example, a mobile phone), a wearable device, a vehicle-mounted device, or a wireless device (for example, a communication module, a modem, or a chip system, etc.) built in the above devices. The terminal device is used to connect people, objects, machines, etc., and can be widely used in various scenarios, for example, including but not limited to the following scenarios: sensing scenarios, cellular communication, device-to-device (D2D) communication, vehicle to everything (V2X) communication, machine-to-machine / machine-type communications (M2M / MTC), internet of things (IoT), virtual reality (VR), augmented reality (AR), industrial control, self driving, remote medical, smart grid, smart furniture, smart office, smart wear, smart transportation, smart city, unmanned aerial vehicle, robot, indoor commercial scenarios (such as mobile phone screen projection, file sharing, mobile phone to VR glasses video transmission) and other scenarios. When the terminal device is applied to V2X, it can also be referred to as a V2X device, for example, a smart car, a digital car, an unmanned car, a self-driving car, a pure EV, a hybrid electric vehicle (HEV), a range extended EV (REEV), a plug-in HEV (PHEV), a new energy vehicle, a road site unit (RSU), etc. The terminal device can also be a device in D2D communication, for example, a water meter, a gas meter, etc.

[0060] In addition, in the embodiments of the present application, the terminal device can also be a terminal device in an internet of things (IoT) system. The IoT is an important part of future information technology development. Its main technical feature is to connect objects to a network through communication technology, thereby realizing an intelligent network of human-machine interconnection and object-object interconnection.

[0061] As introduced above, various terminal devices can be considered as vehicle-mounted terminal devices if they are located on a vehicle (for example, placed in or installed in a vehicle), and the vehicle-mounted terminal device is also referred to as an on-board unit (OBU). The terminal device of the present application can also be a vehicle-mounted module, a vehicle-mounted module group, a vehicle-mounted component, a vehicle-mounted chip or a vehicle-mounted unit built in a vehicle as one or more components or units, and the vehicle can implement the method of the present application through the built-in vehicle-mounted module, vehicle-mounted module group, vehicle-mounted component, vehicle-mounted chip or vehicle-mounted unit.

[0062] The terminal device can also be referred to as a UE, a terminal, an access station, a UE station, a remote station, a wireless communication device, or a user device, etc.

[0063] In the embodiments of the present application, the device for implementing the function of the terminal device can be a terminal device, which can be a terminal device or a device capable of supporting the terminal device to implement the function, such as a chip system, which can be installed in the terminal device. In the technical solutions provided in the embodiments of the present application, the device for implementing the function of the terminal device is taken as an example of a terminal device to describe the technical solutions provided in the embodiments of the present application.

[0064] The network device in the embodiments of the present application, for example, includes an access network device (or an access network network element) and / or a core network device (or a core network network element). The access network device is a device with wireless transceiving function, used for communicating with the terminal device. The access network device includes but is not limited to a base station (a base transceiver station (BTS), a Node B, an evolved Node B (eNodeB) / eNB, or a next generation Node B (gNodeB) / gNB), a transceiving point (TRP), a base station evolved in the future of the 3rd generation partnership project (3GPP), an access node in a wireless fidelity (Wi-Fi) system, a wireless relay node, a wireless backhaul node, and the like. The base station can be a macro base station, a micro base station, a pico base station, a small station, a relay station, and the like. A plurality of base stations can support a network of the same access technology or a network of different access technologies. A base station can include one or more co-sited or non-co-sited transmission reception points. The access network device can also be a wireless controller, a centralized unit (CU), and / or a distributed unit (DU) in a cloud radio access network (CRAN) scenario. The access network device can also be a server and the like. For example, the network device in the V2X technology can be a road side unit (RSU). The access network device is described below by taking a base station as an example. The base station can communicate with the terminal device or communicate with the terminal device through a relay station. The terminal device can communicate with a plurality of base stations in different access technologies. The core network device is used to implement mobile management, data processing, session management, policy and charging, and the like. The names of devices implementing core network functions in systems of different access technologies can be different, and the embodiments of the present application do not limit this.Taking a 5th generation (5G) system as an example, the core network device includes, for example, an access and mobility management function (AMF), a session management function (SMF), a policy control function (PCF), a user plane function (UPF), and the like.

[0065] In the CU-DU architecture, or in an open RAN (ORAN) system, the access network device can include one or more of a central unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU), and the like. The CU and the DU can be separately arranged, or can be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, such as a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).

[0066] In different systems, the CU (or CU-CP and CU-UP), DU, or RU can also have different names, but those skilled in the art can understand their meanings. For example, in an ORAN system, the CU can also be referred to as an open CU (O-CU), the DU can also be referred to as an open DU (O-DU), the CU-CP can also be referred to as an open CU-CP (O-CU-CP), the CU-UP can also be referred to as an open CU-UP (O-CU-UP), and the RU can also be referred to as an open RU (O-RU). For the convenience of description, the CU, CU-CP, CU-UP, DU, and RU are taken as examples for description in the embodiments of the present application. Any one of the CU (or CU-CP, CU-UP), DU, and RU in the embodiments of the present application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0067] The CU and the DU can be configured according to protocol layer functions of a wireless network implemented thereby. For example, the CU is configured to implement functions of a packet data convergence protocol (PDCP) layer and above protocol layers (e.g., a radio resource control (RRC) layer and / or a service data adaption protocol (SDAP) layer, etc.); and the DU is configured to implement functions of a protocol layer below the PDCP layer (e.g., one or more of a radio link control (RLC) layer, a media access control (MAC) layer, or a physical (PHY) layer). For another example, the CU is configured to implement functions of a protocol layer above the PDCP layer (e.g., the RRC layer and / or the SDAP layer), and the DU is configured to implement functions of a protocol layer at or below the PDCP layer (e.g., one or more of the RLC layer, the MAC layer, or the PHY layer).

[0068] The above configuration of the CU and the DU is merely an example, and the CU and the DU can be configured to have other functions as needed. For example, the CU or the DU can be configured to have functions of more protocol layers, or the CU or the DU can be configured to have partial processing functions of a protocol layer. For example, partial functions of the RLC layer and functions of protocol layers above the RLC layer are configured in the CU, and remaining functions of the RLC layer and functions of protocol layers below the RLC layer are configured in the DU. For another example, functions of the CU or the DU can be divided according to a service type or other system requirements. For example, functions that need to meet a relatively low latency requirement in terms of processing time are configured in the DU, and functions that do not need to meet the latency requirement are configured in the CU.

[0069] The DU and the RU can cooperate to implement functions of the PHY layer. One DU can be connected to one or more RUs. The DU and the RU can be configured in various manners according to design. For example, the DU is configured to implement baseband functions, and the RU is configured to implement intermediate radio frequency functions. For another example, the DU is configured to implement high-layer functions in the PHY layer, and the RU is configured to implement low-layer functions in the PHY layer or to implement the low-layer functions and radio frequency functions. The high-layer functions in the PHY layer can include a part of functions of the PHY layer that are closer to the MAC layer, and the low-layer functions in the PHY layer can include another part of functions of the PHY layer that are closer to the intermediate radio frequency side.

[0070] In embodiments of the present application, the access network device can implement a sensing function. For a structure of the access network device, reference can be made to Figure 1 ,Figure 1 The structure shown can also be regarded as the structure of a sensing-fusion access network device. Under this structure, a module for implementing sensing-related functions is introduced in the access network device, for example, referred to as a sensing unit (SU), without limitation on the name. The SU can be a functional module or entity within the access network device; alternatively, the SU can not be disposed in the access network device, but in a functional module or entity outside the access network device. Figure 1 Take the case where the SU is located within the access network device. The SU can be connected (may be directly connected or indirectly connected) with a first core network element, for example, including a sensing function (SF) element, which can also be referred to as a sensing element; the SU can be connected with a second core network element or CU / DU / RU for transmitting sensing-related information or data, for example, including an AMF and / or UPF, etc.

[0071] When the UE reports sensing information to the access network device (it can be understood that the UE reports the sensing information to the SU in the access network device), the sensing information can be delivered by the UE to the DU, then delivered by the DU to the CU, and delivered by the CU to the SU; alternatively, the sensing information can be delivered by the UE to the DU and directly delivered by the DU to the SU; or the sensing information is directly delivered by the UE to the SU through an s-Uu interface, where the s-Uu interface is a communication interface between the UE and the SU. When the access network device transmits sensing information to a core network element (for example, the access network device transmits the sensing information to the SF), the SU can transmit the sensing information to the SF through the AMF or the UPF, or the CU can transmit the sensing information to the SF through the AMF or the UPF, or the SU or the CU can directly transmit the sensing information to the SF.

[0072] In the embodiments of the present application, the device for implementing the function of the network device can be referred to as a network device, which can be a network element or a network device, or a device capable of supporting the network device or the network element to implement the function, for example, a chip system, which can be installed in the network device. In the technical solutions provided in the embodiments of the present application, the device for implementing the function of the network device is taken as an example of the network device (for example, the device for implementing the function of the access network device is the access network device, and the device for implementing the function of the core network device is the core network device), and the technical solutions provided in the embodiments of the present application are described.

[0073] A sensing signal is a signal used for sensing (or detecting) a target (or target object). The sensing signal can also be referred to as a detection signal, a chirp signal, a radar signal, a radar sensing signal, a radar detection signal, or an environmental sensing signal, etc. The sensing signal can be a pulse signal or a signal in a wireless communication system. For example, the sensing signal can be an orthogonal frequency division multiplexing (OFDM) signal modulated on a subcarrier with a specific sequence, which can be any one of the following sequences: a Zadoff-Chu sequence (ZC sequence), a pseudo-random sequence, or a predefined sequence. The pseudo-random sequence includes any one of the following sequences: a maximum length linear feedback shift register sequence (m-sequence), or a Gold sequence. The predefined sequence is, for example, a random data symbol, for example, a random data symbol modulated by quadrature phase shift keying (QPSK) or 16 quadrature amplitude modulation (QAM).

[0074] A return signal is a signal reflected by a target from a sensing signal. The return signal and the sensing signal can reflect parameters of the target, for example, a time delay of the return signal relative to the sensing signal can reflect a distance of the target relative to a transmitter, and a Doppler frequency shift of the return signal relative to the sensing signal can reflect a speed of the target.

[0075] A communication-sensing fusion signal, also referred to as a communication-sensing fusion signal, a communication-sensing signal, or a communication-sensing integrated signal, is a signal used for both communication and sensing. The communication-sensing fusion signal is used for communication, which can be understood as the signal carrying communication data or a communication reference signal sequence that needs to be transmitted between communication devices. The communication-sensing fusion signal is used for sensing, which can be understood as the communication-sensing fusion signal being used for sensing (or detecting) a target.

[0076] For example, the signal used for sensing described herein can include a sensing signal and / or a communication-sensing fusion signal, etc.

[0077] A target can be any tangible object in an environment that can reflect electromagnetic waves, such as mountains, forests, or buildings, etc. The target can also include movable objects such as vehicles, unmanned aerial vehicles, pedestrians, terminal devices, etc. The target can also be referred to as a sensing target, a detection target, a sensed target, a detected target, a sensed object, a detected object, or a sensed device, etc., which is not limited in the embodiments of the present application.

[0078] In sensing, based on the different sender and receiver of the sensing signal, sensing modes can be divided into two types: single-station sensing and dual-station sensing. Single-station sensing mode is also called self-transmitting and self-receiving mode, single-end sensing mode, or monocentric sensing mode, etc. This means that the device transmitting the sensing signal and the device receiving the echo signal reflected from the target are the same device, such as... Figure 2A As shown, both the device transmitting the sensing signal and the device receiving the echo signal are device 1; the dual-station sensing mode, also known as A-transmit B-receive mode or self-transmit and other-receive mode, refers to a mode where the device transmitting the sensing signal and the device receiving the echo signal reflected from the target are different devices, such as... Figure 2B As shown, the device that sends the sensing signal is device 2, and the device that receives the echo signal is device 3. Figure 2A and Figure 2B The perceived target is always a vehicle. For example... Figure 2A In this context, device 1 is a base station or UE. In single-site sensing mode, device 1 transmits a sensing signal, and device 1 receives the sensing signal through sensing targets in the environment (e.g., Figure 2A The echo signals generated by reflection, scattering, or diffraction of vehicles (in the environment) are used for environmental perception. For example, Figure 2B In this dual-site sensing mode, device 2 is a base station or UE, and device 3 is a base station or UE. Device 1 sends a sensing signal, and device 2 receives the sensing signal through scattering objects in the environment (e.g., scattering objects). Figure 2B The system uses echo signals generated by reflection, scattering, or diffraction of signals from vehicles (in the environment) to perform environmental perception. The perception scenario in which the UE participates can also be called a UE-assisted perception scenario.

[0079] This application embodiment can train compression and decompression models, thereby compressing the first sensing information using the compression model. The compressed first sensing information has a smaller data volume compared to the uncompressed first sensing information, thus reducing transmission overhead. The first sensing information may include a first power corresponding to at least one spatial location. The loss function used for training in this application embodiment is related to the power difference corresponding to the at least one spatial location and the maximum power indicated by the first sensing information. For example, among the first powers corresponding to the at least one spatial location, the larger the first power, the smaller the error caused by compression, making the receiver more accurate in recovering larger first powers. This makes the determined location of the sensing target more accurate, which is beneficial to improving sensing accuracy.

[0080] For reference Figure 3 This is a schematic diagram of a potential perceptual network architecture. Figure 3 It is based on the 5G core network (5G core, 5GC). Figure 3 The network architecture shown can also be an application scenario of the embodiments of this application.

[0081] exist Figure 3 In the architecture shown, a new SF (Sensing Management Function) has been added. This SF can be a device or component that provides network awareness capabilities; it can also be called a sensing management function (SMF), or have other names. This SF can be deployed on the core network side or the RAN side. Figure 3 Taking deployment in the core network as an example. Figure 3 In the network architecture shown, the SF can reuse the interfaces between the location management function (LMF) and other 5GC network elements such as AMF, network exposure function (NEF), unified data management (UDM), network data analytics function (NWDAF), and PCF for sensing interaction. Sensing signaling between the SF and the radio access network (RAN) or UE can be transmitted through the AMF; sensing measurement data acquired by the RAN or UE can be transmitted to the SF via the control plane, for example, by reusing the Long Term Evolution (LTE) positioning protocol (LPP) or the New Radio (NR) Positioning Protocol Annex (NRPPa) protocol, or it can be transmitted via the user plane, forwarded to the SF through the UPF, or directly transmitted to the SF.

[0082] The newly added SF in this network architecture can realize basic sensing functions, such as sensing authorization, sensing control, sensing measurement data processing, or result output. Specifically, interfaces are set up and interaction is established between the SF and 5GC network elements such as AMF, NEF, UDM, NWDAF, PCF, LMF, and UPF, as defined below.

[0083] NS1: A new interface between SF and AMF, which can transmit sensing and control signaling. Additionally, this interface can also transmit sensing measurement data in scenarios where sensing measurement data is uploaded to the control plane.

[0084] NS2: A new interface between SF and NEF. This interface can transmit signaling messages between sensing network elements relayed through NEF and application functions (AF) on the service side, and at the same time open the sensing results to the AF.

[0085] NS3: A new interface between SF and UDM. This interface can be used for authentication or authorization, and to obtain UE-aware subscription information, service AMF information, or other information.

[0086] NS4: A new interface between SF and NWDAF. Through this interface, SF and NWDAF can jointly complete artificial intelligence (AI) processing related to perception services.

[0087] NS5: A new interface between SF and PCF. Through this interface, SF can transmit information such as sensing requirements, quality of service (QoS) requirements, or sensing results of sensing services to PCF. PCF can then make decisions to generate policy control and charging (PCC) policies related to sensing services.

[0088] NS6: A new interface between SF and LMF. Through this interface, SF can obtain location-related information, such as the sensing area, the RAN information of the sensing target, and the location information of the sensed UE.

[0089] NS7: A new interface between SF and UPF. Sensing measurement data can be directly transmitted from (R)AN to SF via UPF, or indirectly forwarded to SF via UPF. In scenarios where (R)AN performs sensing, forwarding via UPF can improve the functionality of UPF to support data transmission at the (R)AN granularity.

[0090] In addition to the newly added interfaces mentioned above, existing interfaces (such as N1, N2, N5, N8, N33, etc.) can also support the transmission of information related to sensing services, such as authentication information, sensing service type, sensing service quality requirements, sensing measurement data, or sensing results, etc.

[0091] Figure 3Taking the SF (Side Array) as an independent device as an example; alternatively, the SF and LMF (Location Management Array) can be co-located, meaning the network element used for handling sensing services and the network element used for handling positioning services can be the same network element; or the SF can be co-located with other core network elements, such as the AMF (Location Management Array). The LMF is the core network element in 5GC that provides control plane positioning, capable of calculating and feeding back location information in the 5G network, providing functions such as positioning process management, UE capability acquisition, auxiliary data provision, and UE location estimation. Optionally, if the SF and LMF are co-located, the LMF and the gateway mobile location center (GMLC) can be functionally enhanced to support basic sensing functions. The GMLC can be the first network element within the operator's network to process sensing requests, performing privacy checks or authorization functions, routing sensing requests to the AMF, or performing LMF selection, etc.

[0092] For example, if the SF and LMF are co-located, an additional interface can be added between the LMF and GMLC to transmit information related to awareness services, such as adding an NL9 interface. Additionally, interfaces related to the LMF and GMLC (such as one or more of the following: NL1 interface between AMF and LMF, NL2 interface between AMF and GMLC, NL5 interface between NEF and GMLC, or NL6 interface between UDM and GMLC) can also support the transmission of information related to awareness services, as detailed below.

[0093] N33: The interface between AF and NEF, through which information such as the type of sensing business, business requirements, and sensing results can be transmitted.

[0094] NL5: The interface between NEF and GMLC, through which information such as the type of sensing business, business requirements, and sensing results can be transmitted.

[0095] NL6: The interface between GMLC and UDM, through which privacy inspection data can be transferred.

[0096] NL2: The interface between NEF and AMF, through which information such as the perceived business type, business requirements, and perceived results can be transmitted.

[0097] NL1: The interface between AMF and LMF, through which information such as perceived business type, business requirements, and perceived results can be transmitted.

[0098] NL9: A new interface between GMLC and LMF, through which information such as the type of sensing business, business requirements, and sensing results can be transmitted.

[0099] Can be referenced again Figure 4 This is a schematic diagram of another potential perceptual network architecture. Figure 4It is based on 5GC. Figure 4 The network architecture shown can also be another application scenario of the embodiments of this application.

[0100] exist Figure 4 In the network architecture shown, the SF (Sensitive Detection) is relatively independent of the existing core network elements. The SF requires little or no interaction with the core network elements. For scenarios where sensing needs exist only in a specific area, or where sensing is the only requirement, this network architecture can provide sensing services without 5GC control or with only a few network elements involved in control. Furthermore, localized deployment of the SF ensures that sensing measurement data or results do not leave the campus, thus meeting enterprises' security and privacy requirements for sensing measurement data or results, and reducing sensing latency. This network architecture is relatively simple, flexible, efficient, has few transmission nodes, and is easy to deploy. Optionally, this network architecture can support UE-related sensing needs, and implementation schemes for functions such as authorization, mobility management, and billing can be considered as needed.

[0101] In this network architecture, the SF can directly establish a connection with the RAN node. Control plane sensing signaling and user plane sensing measurement data can be transmitted via the newly defined interface NS1. When the UE participates in sensing, control plane signaling can be forwarded to the SF via the AMF, and sensing measurement data can be transmitted via NS1. Furthermore, there can also be an interface between the SF and 5GC network elements (such as AMF, NEF, or NWDAF) to control the AF to provide sensing service requirements to the SF through core network functions. The interface between the SF and 5GC network elements is described below.

[0102] NS1: A new interface between the SF and (R)AN, which can transmit sensing control signaling or sensing measurement data. In one implementation, the SF can also be deployed on the RAN side; for example, the SF can be co-located with access network equipment (e.g., a base station), or the SF can be a standalone device within the access network.

[0103] NS2: A new interface that may be added between SF and AMF. This interface can receive awareness service requirements from UE, or transmit signaling between SF and other network elements in the core network, such as transmitting interaction messages between SF and UDM.

[0104] NS3: A potential new interface between SF and NEF. This interface can transmit signaling between SF and the service-side AF via NEF, and can also expose the sensing results to the AF. The interaction between SF and AF may not go through NEF. In actual deployment, NS2 and NS3 may be chosen as one of the two options. That is, the AF can send sensing service requests indirectly to SF or directly to SF (without NEF) via NS2 (NEF); or, the AF can send sensing service requests to SF via N33 (NEF) and NS2 (AMF).

[0105] NS4: A potential new interface between SF and NWDAF, through which SF and NWDAF can jointly perform intelligent analysis and prediction to generate perception results.

[0106] The technical solutions provided in this application can be applied to fourth-generation (4G) mobile communication systems, such as LTE systems, or to 5G systems, such as NR systems, or to next-generation mobile communication systems or other similar communication systems, such as future communication systems, or to existing satellite mobile communication technology systems; no specific limitations are imposed. For example... Figure 3 and Figure 4 All are based on 5GC. In addition, SF can also be deployed in other networks, such as 6G networks or other future communication networks.

[0107] The embodiments of this application can be applied to Figure 2B , Figure 3 or Figure 4 The scenario shown can also be used in other scenarios, such as any scenario involving sensing services.

[0108] The method provided in the embodiments of this application is described below with reference to the accompanying drawings. In various embodiments of this application, the signal used to implement the sensing function or sensing service is transmitted through reflection, scattering, or diffraction. The sensing device (e.g., a network device) can determine the relevant characteristics of the sensing target based on the received signal. For example, it can estimate the time delay, Doppler, or angular spectrum information based on the received signal to determine information such as the distance, angle, power, or speed of the sensing target. Optionally, the network device can also send measurement results to the sensing network element, such as the point cloud information, distance, angle, or speed of the sensing target. In the accompanying drawings corresponding to the various embodiments of this application, all steps indicated by dashed lines are optional steps.

[0109] The various embodiments described herein can train models (e.g., including compression and / or decompression models). After training, the trained models can be used to transmit perceptual information. This perceptual information transmission process can be applied to... Figure 2B , Figure 3 or Figure 4 The network architecture is shown. For example, the transmission of sensed information can be accomplished by a first device and a second device. For example, the first device could be... Figure 2B The device 2 shown can be... Figure 2B Device 3 is shown. For example, the first device could be... Figure 3 or Figure 4 The (R)AN shown, or (R)AN including SU or CU, etc.; the second device may be Figure 3 orFigure 4 The UE shown. For example, the first device could be... Figure 3 or Figure 4 The SF shown; the second device can be Figure 3 or Figure 4 The UE shown.

[0110] Furthermore, the training process of this model can be applied to... Figure 2A , Figure 2B , Figure 3 or Figure 4 The network architecture is shown. For example, the model training process can be completed by a first device, such as... Figure 2A The device 1 shown may be, or may be Figure 2B The device 2 shown may be, or may be Figure 3 or Figure 4 The (R)AN shown, or (R)AN including SU or CU, etc., or may be Figure 3 or Figure 4 The SF shown. For example, the model training process can be completed by a first device and a second device; for example, the first device could be... Figure 2B The device 2 shown can be... Figure 2B The device shown is 3; or the first device may be... Figure 3 or Figure 4 The second device may be (R)AN, or (R)AN including SU or CU, etc. Figure 3 or Figure 4 The UE shown; or the first device may be Figure 3 or Figure 4 The SF shown, the second device can be Figure 3 or Figure 4 The UE shown.

[0111] This application provides a sensing method, please refer to the embodiments therein. Figure 5 This is a flowchart of the method. Figure 5 In the illustrated embodiments, the model training process can be completed by a single node, such as by a first device. The training method provided in this application embodiment is, for example, an offline training method.

[0112] S501, the first device inputs first compression information into the decompression model and obtains second sensing information. The second sensing information is, for example, the output information of the decompression model.

[0113] The decompression model is the model to be trained. The decompression model and the compression model can be a pair, capable of compressing and decompressing perceptual information. For example, the decompression model and / or the compression model can be the models to be trained. The compression model can be, for example, an artificial intelligence (AI) model, with a structure such as a convolutional autoencoder or a generative adversarial neural network. The decompression model can also be an AI model, with a structure such as a convolutional autoencoder or a generative adversarial neural network. The structure of the compression model can be the same as or different from the structure of the decompression model. The compression model can be used to extract feature vectors or feature value codebooks of perceptual information (e.g., first perceptual information) to compress the first perceptual information; for example, the first compressed information may include the feature vectors or feature value codebooks. The decompression model can be used to inversely transform the feature vectors or feature value codebooks into perceptual information (e.g., second perceptual information), effectively decompressing the first compressed information.

[0114] Please refer to Figure 6 This is an example of the compression model and the decompression model. Figure 6 The model shown is, for example, a convolutional autoencoder. Figure 6 In this model, the compression model may include convolutional layers and activation functions, and the decompression model may also include convolutional layers and decompression functions. However, the positions of the convolutional layers and activation functions differ between the compression and decompression models. Figure 6 Taking the structural differences between the compression and decompression models as an example, the compression model compresses perceptual information to obtain compressed information. This process can be considered a dimensionality reduction process for the perceptual information; therefore, the number of parameters used to represent convolutional layers and activation functions in the compression model gradually decreases. The decompression model recovers the compressed information to obtain perceptual information; this process can be considered an dimensionality increase process for the compressed information. Therefore, the number of parameters used to represent convolutional layers and activation functions in the decompression model gradually increases. The input information of the compression model is, for example, first perceptual information. The compression model compresses this first perceptual information to obtain first compressed information. This first compressed information can be used as the input information of the decompression model. The decompression model processes the input first compressed information to obtain second perceptual information.

[0115] In S501, the first device can input the first compressed information into the decompression model. Alternatively, the first device can input the quantized first compressed information into the decompression model. For example, after obtaining the first compressed information, the first device can quantize the first compressed information and then input the quantized first compressed information into the decompression model. Alternatively, the first device can input the first compressed information after arithmetic encoding and decoding. For example, after obtaining the first compressed information, the first device can quantize the first compressed information, then perform arithmetic encoding and decoding on the quantized first compressed information, and then input the arithmetic-encoded and decoded first compressed information into the decompression model. Another example is that after obtaining the first compressed information, the first device can perform arithmetic encoding and decoding on the first compressed information, and then input the arithmetic-encoded and decoded first compressed information into the decompression model. By quantizing and / or arithmetic encoding and decoding the first compressed information, the data volume of the first compressed information can be further reduced.

[0116] Optionally, the method may further include S502, in which the first device obtains first compression information. The first compression information is related to the first sensing information. S502, for example, occurs before S501.

[0117] One optional method for the first device to obtain the first compressed information includes inputting the first sensing information into a compression model to obtain the first compressed information. Figure 5 S502 in the example is used here. The first compressed information is, for example, the output information of the compressed model. Optionally, in this way, the first sensing information may not be the sensing information obtained by the first device from the actual measurement of the signal used to realize the sensing function, but rather a training sample obtained by the first device. For example, the first device may store multiple training samples, or the first device may obtain multiple training samples from other devices, and the first sensing information is, for example, one of these multiple training samples.

[0118] The first sensing information, also known as sensing imaging information, power spectrum, or sensing power spectrum, may include at least one first indication information, each of which indicates a first power corresponding to a spatial location. This can be understood as the first sensing information including information indicating a first power corresponding to at least one spatial location (i.e., including at least one first indication information). For example, each first indication information may indicate a correspondence between a spatial location and a first power. Optionally, the spatial location may be represented by any two parameters selected from distance, horizontal angle, or vertical angle. That is, each of the at least one spatial location may correspond to any two parameters selected from a certain distance, a certain horizontal angle, or a certain vertical angle, and each spatial location may also correspond to a first power. Taking the spatial location as represented by three parameters—distance, horizontal angle, and vertical angle—as an example, the first sensing information may also be called a three-dimensional power spectrum or three-dimensional sensing power spectrum. Here, the distance may refer to the distance between the spatial location and the first or second device.

[0119] The first perceptual information is, for example, a matrix, and the first compressed information includes, for example, the eigenvectors or eigenvalue codebook of the matrix.

[0120] Each of the at least one spatial location is considered, for example, as a location grid, where each location grid may have a corresponding index or number, and the first sensing information includes at least one first indication information, where each first indication information may include a correspondence between a spatial location index and a first power.

[0121] In the at least one spatial location, the first power corresponding to different spatial locations may be the same or different. The larger the first power corresponding to a certain spatial location, the greater the power of the signal used to realize the sensing function reflected or scattered through that spatial location, and the greater the probability that a sensing target exists at that spatial location; or, the smaller the first power corresponding to a certain spatial location, the smaller the power of the signal used to realize the sensing function reflected or scattered through that spatial location, and the smaller the probability that a sensing target exists at that spatial location.

[0122] The second sensed information can be considered as recovered information of the first compressed information. For example, if the first sensed information is a power spectrum, then the second sensed information can also be a power spectrum, such as being called a recovered power spectrum. The second sensed information may include at least one second indication information, where each second indication information can indicate a second power corresponding to a spatial location. It can be understood that the second sensed information may include information indicating a second power corresponding to at least one spatial location (i.e., including at least one second indication information). For example, each second indication information can indicate a correspondence between a spatial location and a second power. Optionally, the spatial location can be represented by any two parameters among distance, horizontal angle, or vertical angle, that is, each of the at least one spatial location can correspond to any two parameters among a certain distance, a certain horizontal angle, or a certain vertical angle, and each spatial location can also correspond to a second power. Taking the spatial location as represented by the three parameters of distance, horizontal angle, and vertical angle as an example, the second sensed information can also be called a three-dimensional recovered power spectrum or a three-dimensional sensed recovered power spectrum, etc. Here, the distance can refer to the distance between the spatial location and the first device or the second device. The parameters used to characterize the spatial location of the second perceived information can be the same as those used to characterize the spatial location of the first perceived information. For example, the spatial location indicated by the first perceived information can be represented by three parameters: distance, horizontal angle, and vertical angle. Similarly, the spatial location indicated by the second perceived information can also be represented by three parameters: distance, horizontal angle, and vertical angle.

[0123] In the absence of compression error, the first and second sensing information can theoretically be identical; for example, the first and second powers corresponding to each spatial location in at least one spatial location may be the same. However, due to factors such as compression error, the first and second sensing information may be the same, completely different, or not completely identical. For example, the first and second powers corresponding to each spatial location in some or all of the at least one spatial location may be different.

[0124] S503, The first device updates the parameters of the compression model and / or the decompression model according to the loss function.

[0125] The first device can calculate a loss function based on the first and second sensing information, and then update the parameters of the compression model and / or the parameters of the decompression model based on the loss function.

[0126] The loss function may include a distortion function between the first and second sensing information. This distortion function may be correlated with the power difference corresponding to the at least one spatial location and with the maximum power indicated by the first sensing information. The power difference corresponding to any one of the at least one spatial location may refer to the difference between the first power and the second power corresponding to that spatial location. The first power corresponding to that spatial location is included in the first sensing information, and the second power corresponding to that spatial location is included in the second sensing information. The maximum power indicated by the first sensing information refers to the largest value among the at least one first power indicated by the first sensing information corresponding to the at least one spatial location.

[0127] The distortion function is related to the maximum power indicated by the first sensing information. For example, one implementation includes weighting coefficients corresponding to the at least one spatial location, and these weighting coefficients are related to the maximum power indicated by the first sensing information. For instance, each of the at least one spatial location may correspond to a weighting coefficient, so the distortion function may include at least one weighting coefficient, and each of these weighting coefficients may be related to the maximum power indicated by the first sensing information. The distortion function may also be related to the power difference corresponding to the at least one spatial location. For example, if the distortion function includes the power difference corresponding to each of the at least one spatial location, then the distortion function may include at least one power difference. Optionally, in the distortion function, the at least one power difference and the at least one weighting coefficient may have a one-to-one correspondence. Each power difference can characterize the power error at the spatial location corresponding to that power difference, and the power error can be corrected through the weighting coefficients. Any of the at least one weighting coefficients may be greater than 0.

[0128] As an alternative implementation of this distortion function, the distortion function may be in the form of a weighted mean squared error (MSE). For example, this distortion function may satisfy the following relationship:

[0129]

[0130] Among them, L d This represents the value of the distortion function, w. k p represents the weighting coefficient corresponding to the k-th spatial location among at least one spatial location. k This represents the first power (p) corresponding to the k-th spatial location. k (can be indicated by the first perceived information), p′ k This represents the second power (p′) corresponding to the k-th spatial location. k(which can be indicated by the second sensing information), K represents the number of the at least one spatial position, where 0 < k < K. Among them, p′ k -p k represents the power difference corresponding to the k-th spatial position.

[0131] The weighting coefficient corresponding to any one of the at least one spatial position can be related to the first power corresponding to this one spatial position indicated by the first sensing information, and related to the maximum power and / or minimum power indicated by the first sensing information. For example, the k-th spatial position among the at least one spatial position corresponds to the k-th weighting coefficient, and the k-th weighting coefficient can be related to the first power corresponding to this k-th spatial position indicated by the first sensing information, and related to the maximum power and / or minimum power indicated by the first sensing information. Among them, the minimum power indicated by the first sensing information refers to the first power with the smallest value among the at least one first power corresponding to the at least one spatial position indicated by the first sensing information.

[0132] As an optional implementation manner, the k-th weighting coefficient satisfies the following relationship, for example:

[0133]

[0134] Among them, w k represents the k-th weighting coefficient. p k represents the first power corresponding to the k-th spatial position indicated by the first sensing information. p min represents the minimum power indicated by the first sensing information, and p max represents the maximum power indicated by the first sensing information.

[0135] According to Formula 2, it can be known that if p k is larger, then w k is larger. That is, in this implementation manner, a larger weighting coefficient can be configured for the spatial position with a larger corresponding first power, so that the power error corresponding to this spatial position can be reduced, and the recovery accuracy of the power corresponding to this spatial position can be improved. And the larger the first power corresponding to a certain spatial position is, it indicates that the reflected or scattered power of the signal used to implement the sensing function passing through this spatial position is larger, and the probability that there is a sensing target at this spatial position is greater. In the embodiment of the present application, the power error corresponding to the spatial position with a larger corresponding first power is reduced by the weighting coefficient, and the recovery accuracy of the power corresponding to this spatial position is improved, which helps to improve the accuracy of determining the position of the sensing target according to the power corresponding to this spatial position.

[0136] Alternatively, as another optional implementation, the value of the k-th weighting coefficient is, for example, the value corresponding to the power range of the first power corresponding to the k-th spatial location. This power range is, for example, called the first power range, and can be determined based on the maximum power indicated by the first sensing information and / or the minimum power indicated by the first sensing information. For example, multiple power ranges can be divided based on the maximum power indicated by the first sensing information and / or the minimum power indicated by the first sensing information, and the first power range can be one of these multiple power ranges. Each of the multiple power ranges can include at least one power, and each of the multiple power ranges can correspond to a weighting coefficient. For a given spatial location, the power range corresponding to that spatial location can be determined based on the first power indicated by the first sensing information, and the weighting coefficient corresponding to that power range is the weighting coefficient corresponding to that spatial location. For example, the power range to which the k-th weighting coefficient belongs can satisfy the following relationship:

[0137]

[0138] Among them, w k Let p represent the k-th weighting coefficient. min p represents the minimum power indicated by the first perceived information. max This represents the maximum power indicated by the first perceived information. For example, if p k ≥p max If the value is -25, then the k-th weighting coefficient is 1. The various values ​​in Formula 3 are merely examples and are not limited to these in practice. Formula 3 uses a division of three power ranges as an example, but is not limited to this in practice.

[0139] In this embodiment, the loss function between the first perceived information and the second perceived information may consist solely of the distortion function. For example, the loss function may satisfy the following relationship:

[0140] Loss = L d (Formula 4)

[0141] Where Loss represents the loss function, L d This represents the distortion function.

[0142] Alternatively, the loss function may include other information besides the distortion function. Optionally, the loss function may also include a compression ratio function between the first compressed information and the first perceived information. For example, if the number of bits in the first perceived information is A and the number of bits in the first compressed information is B, then the compression ratio function... Among them, L r This represents the compression ratio function. Alternatively, the compression ratio function can also be understood as the compression ratio function that entropy-encodes the first compressed information. For example, the loss function satisfies the following relationship:

[0143] Loss = L d +βL r (Formula 5)

[0144] Where Loss represents the loss function, L d L represents the distortion function. r Let represent the compression ratio function, and β represent the scaling factor. β can be a real number.

[0145] The first device can update the parameters of the compression model and / or decompression model based on the loss function. For example, each time the first device obtains a piece of second sensing information, it can calculate the value of the loss function and update the parameters of the compression model and / or decompression model based on the value of the loss function.

[0146] Training ends when the loss function converges; alternatively, training ends when the first set of training iterations is reached, which can be a pre-configured maximum number of training iterations. This first set of iterations may be configured by the first device or predefined by the protocol. Optionally, after training, the first device can send updated compressed model information to the second device, such as the parameters of the updated compressed model. The second device can then store the updated compressed model to perform compression based on it. The first device can also store an updated decompression model to perform decompression based on it. For example, during perception, the first and second devices can utilize this compressed and decompressed model to compress and decompress perceived information, thereby saving on the transmission overhead of perceived information.

[0147] This application embodiment can train compression and decompression models, thereby compressing the first sensing information using the compression model. The compressed first sensing information has a smaller data volume compared to the uncompressed first sensing information, thus reducing transmission overhead. The first sensing information may include a first power corresponding to at least one spatial location. The loss function used for training in this application embodiment is related to the power difference corresponding to the at least one spatial location and the maximum power indicated by the first sensing information. For example, among the first powers corresponding to the at least one spatial location, the larger the first power, the smaller the error caused by compression, making the receiver more accurate in recovering larger first powers. This makes the determined location of the sensing target more accurate, which is beneficial to improving sensing accuracy.

[0148] This application provides another sensing method, please refer to the embodiments therein. Figure 7 This is a flowchart of the method. Figure 7 In the illustrated embodiment, the model training process can be completed by multiple nodes, such as by the first device and the second device. Alternatively, it can be considered that...Figure 7 In the illustrated embodiment, the model training process is completed by a single node (e.g., a first device), while a second device can provide assistance. Figure 7 The training method provided in the illustrated embodiments is, for example, an online training method. It is evident that the compression and / or decompression models in the various embodiments of this application can be trained using either offline or online methods, offering considerable flexibility.

[0149] S701, the first device inputs first compression information into the decompression model and obtains second sensing information. The second sensing information is, for example, the output information of the decompression model.

[0150] For more information about S701, such as an introduction to the decompression and / or compression models, and an introduction to the first compression information, please refer to [link / reference needed]. Figure 5 S501 in the illustrated embodiment.

[0151] Optionally, the method may further include S702, in which the first device obtains first compression information. The first compression information is related to the first sensing information. S702 occurs, for example, before S701.

[0152] One optional implementation of the first device obtaining the first compressed information includes a second device sending the first compressed information and the first device receiving the first compressed information. Figure 7 S702 in this example is used as an example. In this implementation, the first compression information is determined by the second device and then sent by the second device to the first device. Optionally, the second device can first obtain the first sensing information and then input the first sensing information into the compression model to obtain the first compression information. The first compression information is, for example, the output information of the compression model. An optional implementation of the second device obtaining the first sensing information includes S703 and S704. S703 and S704 occur, for example, before S702.

[0153] S703, the first device sends a second signal. Correspondingly, the second device receives the second signal.

[0154] The second signal can be a signal used for sensing, such as a sensing signal or a fusion signal. This paper takes the example of the second signal being a sensing signal, and it can be referred to as the second sensing signal. The second sensing signal received by the second device can be a signal reflected, scattered, or diffracted by a sensing target in the environment after the second sensing signal sent by the first device has passed through it. The second device can obtain the first sensing information using algorithms such as back projection (BP) or discrete Fourier transform (DFT). Taking the first device as a network device and the second device as a UE as an example, the second sensing signal may include, for example, a channel state information reference signal (CSI-RS) and / or a synchronization signal and a physical broadcast channel (PBCH) block (SSB).

[0155] S704. The second device determines the first sensing information based on the second sensing signal.

[0156] Optionally, the second device can be configured with a first parameter, for example, the first parameter can be configured by the first device or other devices. The second device can determine at least one spatial location based on the first parameter, thereby determining the first sensing information. For example, the second device can determine the first sensing information based on the at least one spatial location and in conjunction with measurements of the second sensing signal.

[0157] The first parameter may include one or more of the following: number of subcarriers N0, number of horizontal ports N1, number of vertical ports N2, subcarrier oversampling factor O0, horizontal oversampling factor O1, or vertical oversampling factor O2. The number of horizontal ports may refer to the number of horizontal ports of the antenna of the first device, and the number of vertical ports may refer to the number of vertical ports of the antenna of the first device. Taking each spatial location in at least one spatial location as characterized by three parameters—distance, horizontal angle, and vertical angle—as an example, the second device can determine N0O0 values ​​in the distance dimension, N1O1 values ​​in the horizontal angle dimension, and N2O2 values ​​in the vertical angle dimension based on the first parameter. Each spatial location in the at least one spatial location can be uniquely determined by a distance, a horizontal angle, and a vertical angle; therefore, the number of the at least one spatial location is N0O0N1O1N2O2. Each spatial location in the at least one spatial location can correspond to a first power P(s,m,n), where s∈[0,N0O0], m∈[0,N1O1], and n∈[0,N2O2].

[0158] For example, the at least one spatial location is a spatial range with the first device as the origin of the coordinate system, in the subcarrier dimension (or distance dimension), horizontal dimension, and vertical dimension, which can be determined by the distance R(s) to the second device in the subcarrier dimension, the horizontal angle θ(m) in the horizontal dimension, and the vertical angle θ(n) in the vertical dimension.

[0159] R(s) can satisfy the following relationship:

[0160]

[0161] Where c represents the speed of light. Δf represents the spacing between adjacent subcarriers used to transmit the second sensing signal. s represents the oversampled subcarrier index, and the value of s can be in the range [0, N0O0]. The "*" in the various embodiments of this application means multiplication, and will not be explained again below. θ(m)

[0162] θ(m) can satisfy the following relationship:

[0163]

[0164] Where λ represents the wavelength of the subcarrier. d1 represents the spacing between the antenna ports in the horizontal direction. m represents the oversampled horizontal index, and the value of m can be in the range [0, N1O1]. [x] represents rounding up x. w1 represents the spacing between the antenna ports in the horizontal direction.

[0165] θ(n) can satisfy the following relationship:

[0166]

[0167] Where λ represents the wavelength of the subcarrier. d2 represents the spacing between the antenna ports in the vertical direction. N represents the oversampled vertical index, and the value of n can be in the range [0, N2O2]. w2 represents the spacing between the antenna ports in the vertical direction.

[0168] Please refer to Figure 8 This is one example of the at least one spatial location. Each spatial location in the at least one spatial location can be considered, for example, as a location grid, where each location grid can be characterized by three dimensions: distance, horizontal angle, and vertical angle.

[0169] The second device, having received the first sensing information, can input it into a compression model to obtain the first compressed information. After obtaining the first compressed information, the second device can directly send it to the first device; alternatively, the second device can quantize the first compressed information and then send the quantized first compressed information to the first device; or, after obtaining the first compressed information, the second device can quantize it, then perform arithmetic encoding and decoding on the quantized first compressed information, and then send the arithmetic-encoded and decoded first compressed information to the first device. By quantizing and / or performing arithmetic encoding and decoding on the first compressed information, the data volume of the first compressed information can be further reduced, thereby reducing reporting overhead.

[0170] In this scenario, if the second device directly sends the first compressed information to the first device, the first device can input the first compressed information into the decompression model. Alternatively, if the second device sends quantized first compressed information, the first device can input the quantized first compressed information into the decompression model, or the first device can first recover the quantized first compressed information and then input the recovered first compressed information into the decompression model. Alternatively, if the second device sends arithmetic-encoded and arithmetic-decoded first compressed information, the first device can input this arithmetic-encoded and arithmetic-decoded first compressed information into the decompression model. Alternatively, if the second device sends arithmetic-encoded and arithmetic-decoded first compressed information, and the second device quantizes the first compressed information and then performs arithmetic encoding and decoding on the quantized first compressed information, the first device, after obtaining the arithmetic-encoded and arithmetic-decoded first compressed information, can recover the quantized first compressed information and then input the recovered first compressed information (e.g., arithmetic-encoded and arithmetic-decoded first compressed information) into the decompression model.

[0171] S705. The first device updates the parameters of the compression model and / or the decompression model according to the loss function.

[0172] The first device can calculate a loss function based on the first and second sensing information, and then update the parameters of the compression model and / or the parameters of the decompression model based on the loss function.

[0173] Through steps S701 to S704, the first device obtains the second sensing information, but has not yet obtained the first sensing information. Therefore, the first device still needs to obtain the first sensing information. Optionally, the first device can obtain the first sensing information through steps S706 and S707.

[0174] S706, The second device sends the first signal. Correspondingly, the first device receives the first signal.

[0175] The first signal can be a signal used for sensing, such as a sensing signal or a fusion signal. This paper takes the example of the first signal being a sensing signal, and it can be referred to as the first sensing signal. The first sensing signal received by the first device can be a signal reflected, scattered, or diffracted by a sensing target in the environment after the first sensing signal sent by the second device has passed through it. Taking the first device as a network device and the second device as a UE as an example, the first sensing signal may include, for example, a channel sounding reference signal (SRS).

[0176] Optionally, taking the example of the first device being a network device and the second device being a UE, the first sensing signal can be configured by the first device for the second device, and the second device can send the first sensing signal according to the configuration.

[0177] S707, The first device determines the third sensing information based on the first sensing signal.

[0178] If the first device receives the first sensing signal, it can determine the third sensing information based on the first sensing signal. Optionally, the method by which the first device determines the third sensing information can be similar to the method by which the second device determines the first sensing information, as described above, and will not be elaborated further.

[0179] Considering the dissimilarity of the downlink (DL) channel and the uplink (UL) channel, the third sensing information can be considered the same as the first sensing information, or the third sensing information can be considered as the first sensing information. That is, through S706 and S707, the first device obtains the third sensing information, which is also equivalent to obtaining the first sensing information. Therefore, in S705, the first device can calculate the loss function based on the third sensing information (or understood as the first sensing information) and the second sensing information, and then update the parameters of the compression model and / or the parameters of the decompression model according to the loss function.

[0180] For more information about the S705, please refer to [link / reference]. Figure 5 S503 in the illustrated embodiment will not be described in detail.

[0181] This application embodiment can train compression and decompression models, thereby compressing the first sensing information using the compression model. The compressed first sensing information has a smaller data volume compared to the uncompressed first sensing information, thus reducing transmission overhead. The first sensing information may include a first power corresponding to at least one spatial location. The loss function used for training in this application embodiment is related to the power difference corresponding to the at least one spatial location and the maximum power indicated by the first sensing information. For example, among the first powers corresponding to the at least one spatial location, the larger the first power, the smaller the error caused by compression, making the receiver more accurate in recovering larger first powers. This makes the determined location of the sensing target more accurate, which is beneficial to improving sensing accuracy. The training process of this application embodiment can be offline training or online training, which is quite flexible.

[0182] Figure 9 A schematic diagram of a device provided in an embodiment of this application is given. The device 900 may be... Figure 5 or Figure 7 The first device or its circuitry described in the illustrated embodiment is used to implement the method corresponding to the first device in the above method embodiments. Alternatively, the device 900 may be... Figure 7 The second device or its circuit system, as shown in the embodiments, is used to implement the method corresponding to the second device in the above method embodiments. For example, one type of circuit system is a chip system.

[0183] Since the device 900 in the embodiments of this application can implement the sensing method, the device 900 can also be called a sensing device. In implementation, the device 900 may have sensing function but no communication function, or it may have both sensing and communication functions. If the device 900 has communication function, it may also be called a communication device, etc., without limitation.

[0184] The device 900 includes at least one processor 901. The processor 901 can be used for internal processing within the device to implement certain control processing functions. Optionally, the processor 901 includes instructions. Optionally, the processor 901 can store data. Optionally, different processors can be independent devices, located in different physical locations, or located on different integrated circuits. Optionally, different processors can be integrated into one or more processors, for example, integrated on one or more integrated circuits.

[0185] Optionally, the device 900 includes one or more memories 903 for storing instructions. Optionally, the memories 903 may also store data. The processor and the memories may be separate or integrated together.

[0186] Optionally, the device 900 includes a communication line 902 and at least one communication interface 904. Since the memory 903, communication line 902, and communication interface 904 are all optional, therefore... Figure 9 All are represented by dashed lines.

[0187] Optionally, device 900 may further include a transceiver and / or an antenna. The transceiver can be used to send information to or receive information from other devices. The transceiver may be referred to as a transceiver unit, transceiver circuit, input / output interface, etc., and is used to realize the transmission and reception functions of device 900 via the antenna. Optionally, the transceiver includes a transmitter and a receiver. For example, the transmitter can be used to generate a radio frequency (RF) signal from a baseband signal, and the receiver can be used to convert the RF signal back into a baseband signal.

[0188] The processor 901 may include a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of programs according to the present application.

[0189] Communication line 902 may include a path for transmitting information between the aforementioned components.

[0190] Communication interface 904 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), wired access network, etc.

[0191] Memory 903 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory 903 may exist independently and be connected to processor 901 via communication line 902. Alternatively, memory 903 may be integrated with processor 901.

[0192] The memory 903 stores computer execution instructions for implementing the scheme of this application, and its execution is controlled by the processor 901. The processor 901 executes the computer execution instructions stored in the memory 903, thereby realizing... Figure 5 or Figure 7 The steps performed by the first or second device as described in the illustrated embodiments.

[0193] Optionally, the computer execution instructions in the embodiments of this application may also be referred to as application code, and the embodiments of this application do not specifically limit this.

[0194] In a specific implementation, as one example, the processor 901 may include one or more CPUs, for example... Figure 9 CPU0 and CPU1 in the CPU.

[0195] In a specific implementation, as one embodiment, device 900 may include multiple processors, for example... Figure 9 Processors 901 and 905 are mentioned. Each of these processors can be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, "processor" can refer to one or more devices, circuits, and / or processing cores used to process data (such as computer program instructions).

[0196] when Figure 9When the device shown is a chip, such as the chip of the first device or the chip of the second device, the chip includes a processor 901 (and may also include a processor 905), a communication line 902, and a communication interface 904. Optionally, it may include a memory 903. Specifically, the communication interface 904 may be an input interface, pins, or circuits, etc. The memory 903 may be a register, cache, etc. The processor 901 and processor 905 may be a general-purpose CPU, microprocessor, ASIC, or one or more integrated circuits for controlling the execution of a program for controlling the sensing method of any of the above embodiments.

[0197] This application embodiment can divide the device into functional modules according to the above method example. 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 as software functional modules. The module division in this application embodiment is illustrative and only represents one logical functional division; in actual implementation, other division methods may be used. For example, in the case of dividing the device into functional modules corresponding to each function... Figure 10 This is a schematic diagram of an apparatus. The apparatus 1000 can be the first or second device involved in the above-described method embodiments, or a chip in the first or second device. The apparatus 1000 includes a processing unit 1002 and a transceiver unit 1001. Since the apparatus 1000 in the embodiments of this application can implement a sensing method, the apparatus 1000 can also be called a sensing device. In implementation, the apparatus 1000 may have sensing functionality but no communication functionality, or it may have both sensing and communication functionality. If the apparatus 1000 has communication functionality, it can also be called a communication device, etc., without limitation.

[0198] It should be understood that the device 1000 can be used to implement the steps performed by the first device or the second device in the sensing method of the embodiments of this application, and the relevant features can be referred to above. Figure 5 or Figure 7 The embodiments shown are not described in detail here.

[0199] Optional, Figure 10 The functions / implementation process of the transceiver unit 1001 and the processing unit 1002 can be obtained through Figure 9 The processor 901 in the memory calls computer execution instructions stored in memory 903 to implement the function. Alternatively, Figure 10 The function / implementation process of the processing unit 1002 can be achieved through... Figure 9 The processor 901 in the memory calls computer execution instructions stored in the memory 903 to implement this. Figure 10 The function / implementation process of the transceiver unit 1001 can be obtained throughFigure 9 It is implemented using the 904 communication interface.

[0200] Optionally, when the device 1000 is a chip or circuit, the function / implementation process of the transceiver unit 1001 can also be implemented through pins or circuits, etc. Optionally, the transceiver unit 1001 may include a transmitting unit and / or a receiving unit, whereby the transmitting unit implements the transmitting function and the receiving unit implements the receiving function; or, the transceiver unit 1001 may be an integral module capable of implementing both transmitting and / or receiving functions. Optionally, the transceiver unit 1001 can be implemented using a transceiver.

[0201] This application also provides a computer-readable storage medium storing a computer program or instructions that, when executed, implement the methods performed by the first or second device in the aforementioned method embodiments. Thus, the functions described in the above embodiments can be implemented as software functional units and sold or used as independent products. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to it, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0202] This application also provides a computer program product comprising: computer program code, which, when run on a computer, causes the computer to perform the method executed by the first device or the second device in any of the foregoing method embodiments.

[0203] This application also provides a processing apparatus, including a processor and an interface; the processor is used to execute the method executed by the first device or the second device involved in any of the above method embodiments.

[0204] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program 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 website, computer, server, or data center 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 that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0205] The various illustrative logic units and circuits described in the embodiments of this application can be implemented or operate the described functions using a general-purpose processor, digital signal processor (DSP), ASIC, field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof. The general-purpose processor can be a microprocessor; alternatively, it can be any conventional processor, controller, microcontroller, or state machine. The processor can also be implemented using a combination of computing devices, such as a digital signal processor and a microprocessor, multiple microprocessors, one or more microprocessors combined with a digital signal processor core, or any other similar configuration.

[0206] The steps of the methods or algorithms described in the embodiments of this application can be directly embedded in hardware, software units executed by a processor, or a combination of both. The software units can be stored in RAM, flash memory, ROM, erasable programmable read-only memory (EPROM), EEPROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from the storage medium and write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and storage medium can be disposed in an ASIC, which can be disposed in the terminal device. Optionally, the processor and storage medium can also be disposed in different components of the terminal device.

[0207] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0208] The contents of the various embodiments of this application can be referenced to each other. Unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0209] It is understood that in the embodiments of this application, the first device and / or the second device may perform some or all of the steps in the embodiments of this application. These steps or operations are merely examples. In the embodiments of this application, other operations or variations of various operations may also be performed. Furthermore, the steps may be performed in different orders as presented in the embodiments of this application, and it is not necessary to perform all the operations in the embodiments of this application.

Claims

1. A perception method, comprising: The method comprises: inputting first compression information to a decompression model to obtain second perceptual information output by the decompression model, wherein the first compression information is related to first perceptual information, the first perceptual information comprises information indicating a first power corresponding to at least one spatial position, and the second perceptual information comprises information indicating a second power corresponding to the at least one spatial position; updating parameters of the compression model and / or the decompression model according to a loss function, wherein the loss function comprises a distortion function between the first perceptual information and the second perceptual information, the distortion function is related to a power difference value corresponding to the at least one spatial position and a maximum first power indicated by the first perceptual information, and the power difference value corresponding to one spatial position in the at least one spatial position is a difference value between the first power and the second power.

2. The method of claim 1, wherein, The distortion function comprises a weighting coefficient corresponding to the at least one spatial position, and the weighting coefficient is related to the maximum first power indicated by the first perceptual information.

3. The method according to claim 1 or 2, characterized in that, The distortion function satisfies the following relationship: wherein L d represents a value of the distortion function, p ′ k represents a second power corresponding to the kth spatial position indicated by the second perceptual information, p k represents a first power corresponding to the kth spatial position indicated by the first perceptual information, 0 < k < K, K represents a number of the at least one spatial position, w k represents a weighting coefficient corresponding to the kth spatial position.

4. The method according to claim 2 or 3, characterized in that, A kth spatial position in the at least one spatial position corresponds to a kth weighting coefficient, and the kth weighting coefficient is related to a first power corresponding to the kth spatial position indicated by the first perceptual information and a maximum first power and / or a minimum first power indicated by the first perceptual information.

5. The method of claim 4, wherein, The kth weighting coefficient satisfies the following relationship: wherein p k represents the first power indicated by the first perception information corresponding to the kth spatial position, p min represents the minimum first power indicated by the first perception information, p max represents the maximum first power indicated by the first perception information.

6. The method of claim 4, wherein, A value of the kth weighting coefficient is a value corresponding to a power range of the first power corresponding to the kth spatial position, and the power range is determined according to the maximum first power and / or the minimum first power indicated by the first perceptual information.

7. The method according to any one of claims 1 to 6, characterized in that, The loss function further comprises a compression rate function between the first compression information and the first perceptual information.

8. The method according to any one of claims 1 to 7, characterized in that, The method further comprises: inputting the first perceptual information to the compression model to obtain the first compression information output by the compression model; or receiving the first compression information.

9. The method of claim 8, wherein, The first compression information is received, and the method further comprises: receiving a first perceptual signal; determining the first perceptual information according to the first perceptual signal.

10. The method according to any one of claims 1 to 9, characterized in that, The method further comprises: sending information of the updated compression model.

11. A perception method comprising: The method comprises: sending first compression information, the first compression information being used to determine a loss function, wherein the loss function comprises a distortion function between first perceptual information and second perceptual information, the first perceptual information and the second perceptual information are related to the first compression information, the first perceptual information comprises information indicating a first power corresponding to at least one spatial position, the second perceptual information comprises information indicating a second power corresponding to the at least one spatial position, the distortion function is related to a power difference value corresponding to the at least one spatial position and a maximum first power included in the first perceptual information, and the power difference value corresponding to one spatial position in the at least one spatial position is a difference value between the first power and the second power.

12. The method of claim 11, wherein, The distortion function comprises a weighting coefficient corresponding to the at least one spatial position, the weighting coefficient being related to the maximum first power indicated by the first perception information.

13. The method according to claim 11 or 12, characterized in that, The distortion function satisfies the following relationship: wherein L d represents a value of the distortion function, p ′ k represents a second power corresponding to the kth spatial position indicated by the second perceptual information, p k represents a first power corresponding to the kth spatial position indicated by the first perceptual information, 0 < k < K, K represents a number of the at least one spatial position, w k represents a weighting coefficient corresponding to the kth spatial position.

14. The method according to claim 12 or 13, characterized in that, A kth spatial position in the at least one spatial position corresponds to a kth weighting coefficient, the kth weighting coefficient being related to a first power corresponding to the kth spatial position indicated by the first perception information, and to the maximum first power and / or the minimum first power indicated by the first perception information.

15. The method of claim 14, wherein, The kth weighting coefficient satisfies the following relationship: wherein p k represents the first power indicated by the first awareness information corresponding to the kth spatial location, p min represents the minimum first power indicated by the first awareness information, p max represents the maximum first power indicated by the first awareness information.

16. The method of claim 14, wherein, A value of the kth weighting coefficient is a value corresponding to a power range of the first power corresponding to the kth spatial position, the power range being determined according to the maximum first power and / or the minimum first power indicated by the first perception information.

17. The method according to any one of claims 11 to 16, characterized in that, The loss function further comprises a compression rate function between the first compressed information and the first perception information.

18. The method according to any one of claims 11 to 17, characterized in that, The method further comprises: receiving a second perception signal; generating the first perception information according to the second perception signal; inputting the first perception information into a compression model to obtain the first compressed information.

19. The method according to any one of claims 11 to 18, characterized in that, The method further comprises: sending a first perception signal.

20. The method according to any one of claims 11 to 19, characterized in that, The method further comprises: receiving information of an updated compression model.

21. An apparatus, comprising: The apparatus comprises a module for performing the method of any one of claims 1-10, or a module for performing the method of any one of claims 11-20.

22. An apparatus comprising: The apparatus comprises a processor configured to perform the method of any one of claims 1-10, or to perform the method of any one of claims 11-20.

23. A computer-readable storage medium, characterized in that, The computer-readable storage medium is configured to store a computer program, which, when executed on a computer, causes the method of any one of claims 1-10 to be performed, or causes the method of any one of claims 11-20 to be performed.

24. A computer program product, characterised in that, The computer program product comprises a computer program, which, when executed on a computer, causes the computer to perform the method of any one of claims 1-10, or causes the computer to perform the method of any one of claims 11-20.

25. A perception system, comprising: The perception system comprises a first apparatus and a second apparatus, wherein, the first apparatus is configured to perform the method of any one of claims 1-10; the second apparatus is configured to perform the method of any one of claims 11-20.

Images