Data processing method, first devices and storage medium

Abstract

Provided in the present disclosure are a data processing method, first devices and a storage medium. The method comprises: acquiring first data, wherein the first data is original channel measurement data for performing device sensing on a second device; removing noise from the first data to obtain second data; and on the basis of the second data, performing device sensing on the second device, and determining a device sensing result. In the present disclosure, the noise can be removed from the first data to obtain the second data, and device sensing is performed on the basis of the second data, thereby improving the reliability of device sensing, improving the availability of ISAC technology, and facilitating the promotion of the integrated development of communication, sensing and artificial intelligence.

Description

Data processing method, first device, and storage medium Technical Field

[0001] This disclosure relates to the field of data processing, and more particularly to data processing methods, a first device, and a storage medium. Background Technology

[0002] Integrated Sensing and Communication (ISAC) is a crucial research area in wireless communication. ISAC technology enables numerous application services, including detection, localization and tracking, environment reconstruction and target imaging, and gesture and posture recognition.

[0003] Summary of the Invention

[0004] To improve the reliability of integrated communication and sensing, embodiments of this disclosure provide a data processing method, a first device, and a storage medium.

[0005] According to a first aspect of the present disclosure, a data processing method is provided, comprising:

[0006] Acquire first data; wherein the first data is raw channel measurement data used for device sensing of the second device;

[0007] Remove noise from the first data to obtain the second data;

[0008] Based on the second data, device perception is performed on the second device to determine the device perception result.

[0009] According to a second aspect of the present disclosure, a first device is provided, comprising:

[0010] The processing module is configured to acquire first data; wherein the first data is raw channel measurement data used for device awareness of the second device;

[0011] The processing module is also configured to remove noise from the first data to obtain the second data;

[0012] The processing module is also configured to perform device perception on the second device based on the second data and determine the device perception result.

[0013] According to a third aspect of the present disclosure, a first device is provided, comprising:

[0014] One or more processors;

[0015] The processor is used to execute the data processing method described in any one of the first aspects.

[0016] According to a fourth aspect of the present disclosure, a storage medium is provided that stores instructions that, when executed on a communication device, cause the communication device to perform a data processing method as described in any one of the first aspects.

[0017] According to a fifth aspect of the present disclosure, a computer program is provided that, when run on a computer, causes the computer to perform the data processing method as described in any one of the first aspects.

[0018] In this embodiment of the disclosure, noise in the first data can be removed to obtain the second data, and device sensing can be performed based on the second data, which improves the reliability of device sensing, enhances the usability of ISAC technology, and is conducive to promoting the integrated development of communication, sensing and artificial intelligence.

[0019] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0021] Figure 1A is an exemplary schematic diagram of the architecture of a communication system provided according to an embodiment of the present disclosure.

[0022] Figure 1B is an exemplary scenario diagram of six sensing modes provided according to embodiments of the present disclosure.

[0023] Figure 1C is an exemplary schematic diagram of signal types in a communication and sensing channel model provided according to an embodiment of the present disclosure.

[0024] Figure 1D is an exemplary schematic diagram of determining the perception result based on the perception algorithm according to an embodiment of the present disclosure.

[0025] Figure 1E is an exemplary schematic diagram of obtaining perception results based on an artificial intelligence model according to an embodiment of the present disclosure.

[0026] Figure 2A is an exemplary interactive schematic diagram of a data processing method provided according to an embodiment of the present disclosure.

[0027] Figure 2B is an exemplary flowchart illustrating the training process of a first AI model provided according to an embodiment of the present disclosure.

[0028] Figure 2C is an exemplary flowchart illustrating the training process of a second AI model provided according to an embodiment of this disclosure.

[0029] Figure 3A is an exemplary flowchart of a data processing method provided according to an embodiment of the present disclosure.

[0030] Figure 3B is an exemplary flowchart of a data processing method provided according to an embodiment of the present disclosure.

[0031] Figure 3C is an exemplary flowchart of a data processing method provided according to an embodiment of the present disclosure.

[0032] Figure 3D is an exemplary flowchart of a data processing method provided according to an embodiment of the present disclosure.

[0033] Figure 4A is an exemplary process diagram of a data processing method provided according to an embodiment of the present disclosure.

[0034] Figure 4B is an exemplary interactive schematic diagram of a data processing method provided according to an embodiment of the present disclosure.

[0035] Figure 5 is an exemplary block diagram of a first device provided according to an embodiment of the present disclosure.

[0036] Figure 6A is an exemplary block diagram of a communication device provided according to an embodiment of the present disclosure.

[0037] Figure 6B is an exemplary block diagram of a chip provided according to an embodiment of the present disclosure. Detailed Implementation

[0038] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0039] This disclosure provides a data processing method, a first device, and a storage medium.

[0040] In a first aspect, embodiments of this disclosure propose a data processing method, the method comprising: acquiring first data; wherein the first data is raw channel measurement data for device sensing of a second device; removing noise from the first data to obtain second data; and performing device sensing on the second device based on the second data to determine the device sensing result.

[0041] In the above embodiments, the first device can remove noise from the original data used for device sensing and perform device sensing based on the noise-removed data, thereby improving the reliability of device sensing.

[0042] In conjunction with some embodiments of the first aspect, in some embodiments, obtaining the first data includes: receiving the first data sent by a third device.

[0043] In the above embodiments, the first device can directly obtain the raw data for device sensing from the third device, thereby improving the usability of ISAC technology.

[0044] In conjunction with some embodiments of the first aspect, in some embodiments, obtaining the first data includes: receiving a second signal; wherein the second signal is determined based on the first signal; wherein the first signal is a signal used to initiate device sensing; and performing channel measurement based on the second signal to obtain the first data.

[0045] In the above embodiments, the first device can perform channel measurement based on the received second signal to obtain raw data for device sensing, thereby improving the availability of ISAC technology.

[0046] In conjunction with some embodiments of the first aspect, in some embodiments, removing noise from the first data to obtain the second data includes: using the first data as input to a first artificial intelligence (AI) model to obtain the second data output by the first AI model; wherein the first AI model is used to remove the noise.

[0047] In the above embodiments, noise in the raw data for device sensing can be removed by artificial intelligence models, which improves the reliability of device sensing and is conducive to promoting the integrated development of communication, sensing and artificial intelligence.

[0048] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes: inputting first sample data into a first initial AI model to obtain third data output by the first initial AI model; wherein the first sample data is raw sample channel measurement data used for device perception; determining a first loss function based on the difference between the third data and the fourth data; wherein the fourth data is data used for device perception and with the noise removed; training the first initial AI model based on the first loss function until a first stopping condition is met to stop training and obtain the first AI model.

[0049] In the above embodiments, a first AI model for noise removal can be trained through the above process. Subsequently, noise in the original data used for device perception can be directly removed through the first AI model, thereby improving the reliability of device perception and promoting the combined development of perception and artificial intelligence.

[0050] In conjunction with some embodiments of the first aspect, in some embodiments, the first stopping condition includes at least one of the following: reaching a first number of training epochs; the first loss function decreasing to a first tolerance range; and the noise removal accuracy of the first initial AI model reaching a first value.

[0051] In the above embodiments, when the training process of the first initial AI model meets the first stopping condition, the training can be stopped, thereby obtaining the first AI model. This improves the efficiency of training the first AI model and ensures the accuracy of noise removal, resulting in high usability.

[0052] In conjunction with some embodiments of the first aspect, in some embodiments, the step of performing device perception on the second device based on the second data and determining the device perception result includes: using the second data as the input value of the second AI model to obtain the device perception result output by the second AI model; wherein, the second AI model is used to perform device perception.

[0053] In the above embodiments, the device perception results can be obtained through the second AI model, which promotes the development of the combination of perception and artificial intelligence.

[0054] In conjunction with some embodiments of the first aspect, in some embodiments, the noise includes at least one of the following: Gaussian white noise; fifth data; wherein the fifth data is channel measurement data used for device awareness of a fifth device.

[0055] In the above embodiments, the noise involved in this disclosure may include, but is not limited to, Gaussian white noise during channel transmission, and may also include data used for device sensing of non-sensing targets. By removing the above noise, the obtained device sensing result is closer to the device sensing result corresponding to the sensing target itself, thereby improving the reliability of device sensing.

[0056] Secondly, embodiments of this disclosure provide a first device, comprising: a processing module configured to acquire first data; wherein the first data is raw channel measurement data for device sensing of a second device; the processing module is further configured to remove noise from the first data to obtain second data; the processing module is further configured to perform device sensing of the second device based on the second data and determine the device sensing result.

[0057] Thirdly, embodiments of this disclosure provide a first device comprising: one or more processors; wherein the processors are configured to perform the data processing method described in any one of the first aspects.

[0058] Fourthly, embodiments of this disclosure provide a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform the data processing method as described in any one of the first aspects.

[0059] Fifthly, embodiments of this disclosure provide a computer program that, when run on a computer, causes the computer to perform the method as described in the alternative implementation of the first aspect.

[0060] In a sixth aspect, embodiments of this disclosure provide a program product that, when executed by a communication device, causes the communication device to perform the method described in the optional implementation of the first aspect.

[0061] In a seventh aspect, embodiments of this disclosure provide a chip or chip system. The chip or chip system includes processing circuitry configured to perform the method described according to an optional implementation of the first aspect above.

[0062] It is understood that the aforementioned first device, storage medium, program product, computer program, chip, or chip system are all used to perform the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0063] This disclosure provides a data processing method, a first device, and a storage medium. In some embodiments, the terms "data processing method" can be used interchangeably with "information processing method," "device sensing method," "communication method," etc., and the terms "data processing device" can be used interchangeably with "information processing device," "device sensing device," "communication device," etc.

[0064] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0065] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0066] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0067] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0068] In the embodiments disclosed herein, "multiple" refers to two or more.

[0069] In some embodiments, the terms “at least one of”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0070] In some embodiments, the notation "at least one of A and B", "A and / or B", "A in one case, B in another", "in response to one case A, in response to another case B", etc., may include the following technical solutions depending on the situation: in some embodiments, A (execute A regardless of B); in some embodiments, B (execute B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); in some embodiments, A and B (both A and B are executed). The same applies when there are more branches such as A, B, C, etc.

[0071] In some embodiments, the notation "A or B" may include the following technical solutions, depending on the situation: in some embodiments, A (execution of A regardless of B); in some embodiments, B (execution of B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed). The same applies when there are more branches such as A, B, C, etc.

[0072] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the object being described is "information", then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0073] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0074] In some embodiments, devices, etc., can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as “device”, “equipment”, “circuit”, “network element”, “node”, “function”, “unit”, “section”, “system”, “network”, “chip”, “chip system”, “entity”, and “subject” can be used interchangeably.

[0075] In some embodiments, "device" may be interpreted as "network" or "terminal".

[0076] In some embodiments, "network" can be interpreted as devices included in a network (e.g., access network devices, core network devices, etc.).

[0077] In some embodiments, the terms "access network device (AN device)," "radio access network device (RAN device)," "base station (BS)," "radio base station," "fixed station," "node," "access point," "transmission point (TP)," "reception point (RP)," "transmission / reception point (TRP)," "panel," "antenna panel," "antenna array," "cell," "macro cell," "small cell," "femto cell," "pico cell," "sector," "cell group," "serving cell," "carrier," "component carrier," and "bandwidth part (BWP)" can be used interchangeably.

[0078] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", "subscriber station", "mobile unit", "subscriber unit", "wireless unit", "remote unit", "mobile device", "wireless device", "wireless communication device", "remote device", "mobile subscriber station", "access terminal", "mobile terminal", "wireless terminal", "remote terminal", "handset", "user agent", "mobile client", and "client" can be used interchangeably.

[0079] In some embodiments, access network devices, core network devices, or network devices can be replaced by terminals. For example, embodiments of this disclosure can also be applied to structures where communication between access network devices, core network devices, or network devices and terminals is replaced by communication between multiple terminals (e.g., device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the structure can also be configured such that the terminal has all or part of the functions of the access network device. Furthermore, terms such as "uplink" and "downlink" can be replaced with terms corresponding to communication between terminals (e.g., "sidelink"). For example, uplink channel, downlink channel, etc., can be replaced with sidelink channel, and uplink link, downlink, etc., can be replaced with sidelink link.

[0080] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, core network device, or network device may also be configured to have all or some of the functions of the terminal.

[0081] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0082] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0083] Furthermore, each element, each row, or each column in the table of this disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0084] Figure 1A is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure.

[0085] As shown in Figure 1A, the communication system 100 includes a first device 101, a second device 102, a third device 103, and a fourth device 104.

[0086] In some embodiments, the first device 101 may be a device for performing device sensing and determining the results of device sensing.

[0087] In some embodiments, a second artificial intelligence (AI) model may be deployed on the first device 101 to perform device perception.

[0088] In some embodiments, the first device 101 may be a terminal or a network device, such as an access network device or a core network device. In some embodiments, the terminal includes, but is not limited to, at least one of the following: mobile phone, wearable device, Internet of Things device, car with communication function, smart car, tablet computer, computer with wireless transceiver function, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical surgery, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, and wireless terminal device in smart home.

[0089] In some embodiments, the access network device is, for example, a node or device that connects a terminal to a wireless network. The access network device may include, but is not limited to, at least one of the following in a 5G communication system: evolved Node B (eNB), next-generation eNB (ng-eNB), next-generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), radio backhaul device, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a Wi-Fi system.

[0090] In some embodiments, the first device 101 may be an autonomous driving device, an Internet of Things (IoT) device, an environmental IoT device, etc. Autonomous driving devices include, but are not limited to, driverless cars and drones. IoT devices include, but are not limited to, sensors using radio frequency identification (RFID), scanners, smart home devices, and robots. Environmental IoT devices include, but are not limited to, IoT devices that can obtain energy from the outside environment and be charged.

[0091] In some embodiments, the technical solutions of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0092] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the access network device. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0093] In some embodiments, the core network equipment can be a single device, including a first network element, a second network element, etc., or it can be multiple devices or a group of devices, each including all or part of the first network element, the second network element, etc. Network elements can be virtual or physical. The core network includes, for example, at least one of the Evolved Packet Core (EPC), 5G Core Network (5GCN), and Next Generation Core (NGC).

[0094] In some embodiments, the core network device is, for example, a Location Management Function (LMF).

[0095] In some embodiments, core network devices are used for device awareness, and the names are not limited to device awareness network elements or functions.

[0096] In some embodiments, the second device 102 may be a device that needs to be sensed.

[0097] In some embodiments, the second device 102 may be a sensing target device. A "sensing target" may refer to a device or terminal that is expected to determine the sensing results of its device.

[0098] In some embodiments, the first device 101 may be used to determine the device perception result of the second device 102.

[0099] In some embodiments, the second device 102 may be a terminal, or an autonomous driving device, an Internet of Things (IoT) device, an environmental IoT device, etc.

[0100] In some embodiments, the third device 103 may be a sensing signal receiving device.

[0101] In some embodiments, the third device 103 can obtain first data after performing channel measurements based on the received signal.

[0102] For example, the name of the received signal is not limited and can be interchanged with the second signal, the transmitted signal, etc.

[0103] In some embodiments, the first data may refer to data used for device awareness of the second device 102. Exemplarily, the first data may include, but is not limited to, channel state information (CSI).

[0104] For example, the name of the first data is not limited and can be interchanged with channel state information, device sensing data, etc.

[0105] In some embodiments, the third device 103 may be a terminal, a network device, an autonomous driving device, an IoT device, an environmental IoT device, etc. Specific details will not be elaborated further here.

[0106] In some embodiments, the fourth device 104 may be a device that transmits sensing signals, such as a sensing signal transmitting device.

[0107] In some embodiments, the sensing signal is a signal that enables the second device 102 (i.e., the sensing target) to be sensed.

[0108] In some embodiments, the sensing signal may be a signal used to initiate device sensing.

[0109] In one example, after the fourth device 104 sends a sensing signal, the sensing signal is received by the third device 103 after being propagated through the second device 102 (i.e., the sensing target) or other objects through reflection, refraction and / or scattering. The signal received by the third device 103 is called the second signal.

[0110] For example, the name of the sensing signal is not limited and can be interchanged with the first signal, the transmitted signal, etc.

[0111] The aforementioned other objects may include, for example, network devices, vehicles, environmental IoT devices, IoT devices, etc., and this disclosure does not limit them.

[0112] In some embodiments, the sensing results include, but are not limited to, the distance (distance of the second device 102 relative to the specified object), speed (moving speed of the second device 102), angle (horizontal angle and / or zenith angle of the second device 102 relative to the specified object), etc.

[0113] For example, the horizontal angle refers to the angle obtained by projecting the lines connecting the second device 102 and the designated object from a reference point, such as the Earth's center or other designated location, onto the horizontal plane. The zenith angle refers to the angle of the line connecting the second device 102 and the designated object relative to the ground normal.

[0114] Specifically, determining the perception results of the second device can refer to determining the specific values ​​of the three parameters of the second device: distance, speed, and angle.

[0115] For example, if the first signal is sent by the second device 102 itself, and the second device 102 receives the second signal, the specified object can be other objects that propagate the first signal through the above-described propagation methods such as emission, refraction and / or scattering, such as network devices, vehicles, IoT devices, environmental IoT devices, etc.

[0116] For example, if the first signal is sent by a fourth device 104 (a device different from the second device 102), the designated object may refer to the second device 102.

[0117] In some embodiments, the second device 102, the third device 103, and the fourth device 104 may be the same device. For example, after the second device 102 sends a first signal, it receives a second signal after the propagation process of emission, refraction, and / or scattering through a first object (network device, vehicle, environmental IoT device, IoT device, etc.). At this time, the second device 102 needs to determine its own device sensing result.

[0118] Furthermore, if the second device 102 and the first device 101 are the same device, the second device 102 performs channel measurement based on the second signal to obtain the first data, and performs device perception on itself based on the first data to determine the device perception result. The device perception result may include, but is not limited to, the specific values ​​of parameters such as distance, speed and angle of the second device 102.

[0119] If the second device 102 and the first device 101 are different devices, the second device 102 performs channel measurement based on the second signal to obtain first data, and sends the first data to the first device 101. The first device 101 performs device perception on the second device 102 based on the first data and determines the device perception result of the second device 102. The device perception result may include, but is not limited to, specific values ​​of parameters such as distance, speed and angle of the second device 102.

[0120] In some embodiments, the second device 102, the third device 103, and the fourth device 104 may be different devices.

[0121] For example, the fourth device 104 sends a first signal, which is then transmitted through the second device 102 via emission, refraction, and / or scattering, and finally received by the third device 103.

[0122] Furthermore, if the third device 103 and the first device 101 are the same device, the third device 103 performs channel measurement based on the second signal to obtain first data, and performs device perception on the second device 102 based on the first data to determine the device perception result. The device perception result may include, but is not limited to, specific values ​​of parameters such as distance, speed and angle of the second device 102.

[0123] If the third device 103 and the first device 101 are different devices, the third device 103 performs channel measurement based on the second signal, obtains the first data, and sends the first data to the first device 101. The first device 101 performs device perception on the second device 102 based on the first data and determines the device perception result of the second device 102. The device perception result may include, but is not limited to, the specific values ​​of parameters such as distance, speed and angle of the second device 102.

[0124] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in this disclosure are also applicable to similar technical problems.

[0125] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1A, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1A are illustrative. The communication system may include all or some of the main bodies in FIG1A, or it may include other main bodies outside of FIG1A. The number and form of each main body are arbitrary. Each main body may be physical or virtual. The connection relationship between the main bodies is illustrative. The main bodies may not be connected or may be connected. The connection can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.

[0126] The embodiments disclosed herein can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X) systems, systems utilizing other communication methods, and next-generation systems built upon them. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).

[0127] In this disclosed embodiment, ISAC is one of the most important research directions in wireless communication and a key enabling technology in mobile communication. Sensor-integrated communication technology can enable sensing services based on existing mobile communication infrastructure, fully leverage the advantages of mobile communication networks to meet the sensing needs of various service scenarios, and improve communication performance by relying on sensing capabilities. This, in turn, helps to realize numerous application services such as detection, localization and tracking, environmental reconstruction and target imaging, gesture and posture recognition, etc.

[0128] In some embodiments, for integrated communication and sensing applications, relatively complete channel modeling of the sensing system has been carried out based on relevant channel modeling standards, providing strong support for the evaluation of sensing technology solutions. For scenarios such as highways, various estimation algorithms for parameters such as target speed, distance, and angle have been proposed and designed, including but not limited to the Multiple Signal Classification (MUSIC) algorithm and the Estimation of Signal Parameters using Rotational Invariance Techniques (ESPRIT) algorithm. These algorithms can achieve good target perception results in integrated communication and sensing simulation scenarios.

[0129] The application of AI technology in the field of wireless communication is also one of the important research topics. AI technology has been widely used in many fields. The powerful feature extraction and mapping relationship modeling capabilities of neural network models can provide new solutions to key problems in wireless communication systems. It can be widely used and studied in problems such as high-precision terminal positioning, channel state information feedback, and beam management.

[0130] The integration of communication and sensing based on AI technology is a potential application in future wireless communication systems. By leveraging the powerful computing capabilities of graphics processing units (GPUs), AI sensing models can be trained and acquired based on sample datasets. This can optimize aspects such as sensing accuracy, computational complexity, and applicability, promoting the deep application of communication and sensing integration technology, supporting more intelligent business applications and services, and thus contributing to the development of the integration of communication, sensing, algorithms, and AI.

[0131] In this embodiment, the following six sensing modes are provided, as shown in Figure 1B. Mono-static indicates self-transmission and self-reception, meaning the sending and receiving ends are the same; Bi-static indicates cross-station transmission and reception, meaning the sending and receiving ends are different.

[0132] Sensing Mode 1 is a self-transmitting and self-receiving mode where both the transmitter and receiver are User Equipment (UE), such as a user (person). The transmitter sends a sensing signal to another UE (e.g., a car) and receives the reflected echo from the other UE (car), thereby sensing the user's (person's) device sensing result.

[0133] Sensing Mode 2 is a self-transmitting and self-receiving mode where both the transmitter and receiver are User Equipment (UE), such as a user (person). The transmitter sends a sensing signal to the access network device, such as a gNB, and receives the reflected echo from the gNB to perceive the sensing results of itself (the person).

[0134] Sensing mode 3, cross-site transceiver, the transmitting end is gNB and the receiving end is UE (vehicle). For example, gNB sends a sensing signal and UE (vehicle) receives the signal forwarded by the user (person). UE (vehicle) calculates the channel matrix based on the received signal to sense the target in the environment, such as the user (person), and the device sensing result.

[0135] Sensing mode 4, cross-site transceiver, the transmitting end is UE (vehicle) and the receiving end is gNB. For example, the UE (vehicle) sends a sensing signal and the gNB receives the signal forwarded by the user (person). The gNB calculates the channel matrix based on the received signal to sense the target in the environment, such as the user (person), and the device sensing result.

[0136] Sensing mode 5, cross-site transmission and reception, with gNB#1 as the transmitter and gNB#2 as the receiver. For example, gNB#1 transmits a sensing signal, and gNB#2 receives the signal forwarded by the user (person). gNB#2 calculates the channel matrix based on the received signal to sense the device sensing results of targets in the environment, such as users (persons).

[0137] Sensing mode 6, cross-site transceiver, the transmitting end is UE#1 (vehicle #1) and the receiving end is UE#2 (vehicle #2). For example, UE#1 (vehicle #1) sends a sensing signal and UE#2 (vehicle #2) receives the signal forwarded by the user (person). UE#2 (vehicle #2) calculates the channel matrix based on the received signal to sense the target in the environment, such as the user (person), and the device sensing result.

[0138] It is understood that the aforementioned sensing target, namely the second device 102, can include: drones, people in indoor and outdoor scenarios, cars on highways in outdoor scenarios, automated guided vehicles in factories in indoor scenarios, and targets that create danger on roads or railways, etc. Sensor integration mainly involves the receiver calculating and acquiring information such as the distance, speed, and angle of the sensing target in the environment based on the received signal. The sensing target can be the receiver itself or other objects.

[0139] In some embodiments, taking self-transmitting and self-receiving as an example, the fourth device 104, the third device 103, and the second device 102 are the same device, assumed to be a vehicle. Other objects (also referred to as "sensing signal reflection ends") are assumed to be gNBs, as shown in Figure 1C. In this scenario, there are obstructions between the vehicle and the gNB; these obstructions may be other UEs or other debris. Four types of signals can be considered in the sensing channel model:

[0140] Line of sight (LOS) path; Non-line of sight (NLOS) path; Clutter LOS path; Clutter NLOS path.

[0141] For example, in addition to the four types of signals mentioned above, the impact of channel noise usually needs to be considered.

[0142] For example, as shown in Figure 1C, the above four types of signals are described below:

[0143] The path of perception LOS is the path between the sensing signal reflector (e.g., gNB) and the sensing target (e.g., vehicle). The path between the sensing target (e.g., vehicle) and the sensing signal receiver (e.g., gNB) is also a path of perception LOS (e.g., solid line path #1 between gNB and vehicle in Figure 1C).

[0144] Sensing NLOS path: The path between the sensing signal reflector (e.g., gNB) and the sensing target (e.g., vehicle) that needs to pass through clutter (e.g., clutter #1) is the sensing NLOS path. The path between the sensing target (e.g., vehicle) and the sensing signal receiver (e.g., gNB) that needs to pass through clutter is also the sensing NLOS path (e.g., solid line path #2 in Figure 1C).

[0145] Clutter LOS path: The path between the sensing signal reflector (e.g., gNB) and the scattering cluster in the environment (e.g., clutter #2) is the clutter LOS path. The path between the scattering cluster in the environment (e.g., clutter #2) and the sensing signal receiver (e.g., vehicle) is also the clutter LOS path (e.g., the dashed path #1 in Figure 1C).

[0146] Clutter NLOS path: The path between the sensing signal reflector (e.g., gNB) and the scattering cluster in the environment (e.g., clutter #2) that still needs to pass through clutter (e.g., clutter #3) is the sensing NLOS path. The path between the scattering cluster in the environment (e.g., clutter #3) and the sensing signal receiver (e.g., vehicle) that still needs to pass through clutter (e.g., clutter #2) is also the sensing NLOS path (e.g., the dashed path #2 in Figure 1C).

[0147] In this embodiment, the main information for device sensing is the Channel State Information (CSI) matrix H of the receiving end. This CSI matrix H is a superposition of the sensing target channel, clutter channel, and noise, reflecting the channel environment in which the sensing signal resides and the state information of the sensing target within that environment. The dimensions of the CSI matrix H are related to the specific parameter settings in the actual sensing scenario; the information in the data on different dimensions can reflect different types of state information of the sensing target. This embodiment presents one possible scenario:

[0148] The CSI matrix H typically includes three dimensions: subcarriers, Orthogonal Frequency Division Multiplexing (OFDM) symbols, and receiver antenna ports.

[0149] Specifically, the CSI matrix H can be an M×S×P complex matrix, where M is the number of OFDM symbols, S is the number of subcarriers, and P is the number of receive antenna ports. The element H at the position of the m-th OFDM symbol, the s-th subcarrier, and the p-th receive antenna port in the CSI matrix H is... m,s,p For a complex number Z m,s,p For example, as shown in Equation 1, it represents the influence of the signal's amplitude and phase on its propagation from the transmitting antenna to the receiving antenna: H m,s,p =Z m,s,p =a m,s,p +i×b m,s,p Formula 1

[0150] Among them, a m,s,p b m,s,p Used to represent the complex number Z m,s,p The values ​​of the real part and the imaginary part. Where, a m,s,p b m,s,p It can be a real number.

[0151] According to the received signal model, the phase shifts in the three dimensions of the channel matrix are independent of each other, and different types of sensing results for the target can be obtained based on the phase changes in the three dimensions. For example, the distance of the sensing device can be estimated based on the phase difference caused by the time delay between subcarriers, the velocity of the sensing device can be estimated based on the phase difference caused by the Doppler effect between OFDM symbols, and the angle of the sensing device can be estimated based on the phase changes between the received signals of multiple antenna ports. Sensing algorithms such as 3D-MUSIC (3-Dimensional Multiple Signal Classification) and 3D-ESPRIT (3-Dimensional Estimation of Signal Parameters using Rotational Invariance Techniques) can obtain the sensing results of the distance, velocity, and angle of the sensing device based on the channel state information matrix, as shown in Figure 1D.

[0152] In some embodiments, the scene applicability of the perception algorithm is affected by factors such as clutter and noise in the scene, and its performance will be significantly reduced. In the case of multiple targets, the direct path of non-perceived targets will have a certain impact on the perception results of perceived targets, and when the perceived target is far away, the impact of noise will be greater.

[0153] In some embodiments, the computational complexity of the perception algorithm is high. In order to obtain a high-accuracy perception result, the perception algorithm is complex and the application process of the perception algorithm is complicated.

[0154] In some embodiments, the accuracy needs to be improved in the case of multi-target perception. In actual integrated sensing application scenarios, existing multi-target perception algorithms usually have certain errors when estimating the number of sensing targets, resulting in large errors in the algorithm estimation results.

[0155] Leveraging the strong learning and modeling capabilities of neural network models, an AI perception model can be trained and acquired based on a sample dataset. This model can estimate the number of perceived targets and perceive information such as distance, velocity, and angle for each target in multi-target perception scenarios. For example, by directly using the channel state information matrix H as input data to the AI ​​perception model, a model can be trained that can simultaneously output the distance to the targets. speed angle The three types of perception results are shown in Figure 1E.

[0156] AI-based target perception models may be deployed on user devices such as mobile terminals and automobiles, or on the network side specifically for implementing sensing functions. The device that acquires channel measurement data for AI perception may differ from the device that performs the AI ​​perception model inference application. When the AI ​​perception model is deployed on a user device, the user device can acquire channel measurement data through self-transmission and self-reception, such as receiving the channel matrix and directly inputting it into the AI ​​perception model to obtain the perception results.

[0157] In wireless communication systems, data transmission via wireless communication links is affected by channel noise, causing a certain deviation between the received data and the original transmitted data. Furthermore, in target information perception tasks, AI perception algorithms and models primarily rely on the channel state information matrix corresponding to the perceived target to complete target information perception. The channel state information matrix of non-perceived targets can be considered an interference factor in the target perception process, affecting the accuracy of target information perception. In practice, the channel matrix that the sensing signal receiver, such as a UE or base station, can measure is a superposition of the channel matrix of the perceived target and the channel matrix of the non-perceived target. After the sensing signal receiver reports the sensing measurement data to the AI ​​perception model inference node, such as the LMF, the model input data is then superimposed with noise. Therefore, if the channel measurement data reported by the sensing signal measurement node is directly used as the input data of the AI ​​perception model, the interference from non-perceived targets and noise will affect the perception accuracy.

[0158] To improve the reliability of device sensing, this disclosure provides the following data processing method, a first device, and a storage medium.

[0159] Figure 2A is an interactive schematic diagram of a data processing method according to an embodiment of the present disclosure. As shown in Figure 2A, the embodiments of the present disclosure relate to a data processing method, which includes:

[0160] In step S2101, the fourth device 104 sends the first signal.

[0161] In some embodiments, the first signal may be a signal used to initiate device sensing.

[0162] In some embodiments, the name of the first signal is not limited and can be interchanged with sensing signal, sensing information, etc.

[0163] In some embodiments, the first signal may be, for example, a probe reference signal, a random sequence, etc.

[0164] In some embodiments, the fourth device 104 may be a device that sends the first signal, such as a terminal, vehicle, autonomous driving device, IoT device, environmental IoT device, etc. In some embodiments, the third device 103 receives the second signal.

[0165] In some embodiments, the name of the second signal is not limited and can be interchanged with received signal, received information, etc. In some embodiments, the second signal is a signal obtained based on the first signal.

[0166] In some embodiments, the third device 103 may be a device that receives the signal after the first signal has been propagated through processes such as reflection, refraction and / or scattering, such as access network devices, terminals, vehicles, autonomous driving devices, Internet of Things devices, environmental Internet of Things devices, etc.

[0167] In some embodiments, the fourth device 104 and the third device 103 are the same device. Corresponding to the above-mentioned sensing mode 1 or sensing mode 2, the fourth device 104 sends a first signal, which is then received by the fourth device 104 (i.e. the third device 103) after being propagated by a first object, such as, but not limited to, a base station, a vehicle, an IoT device, an environmental IoT device, etc., through reflection, refraction and / or scattering. The received signal is the second signal.

[0168] In some embodiments, the fourth device 104 and the third device 103 are different devices, corresponding to any of the above-mentioned sensing modes 3 to 6. The fourth device 104 sends a first signal, which is then received by the third device 103 after being propagated through reflection, refraction and / or scattering by the second device 102. The received signal is the second signal.

[0169] In one example, the second device 102 is the sensing target device, that is, the device that needs to be sensed.

[0170] In this embodiment of the disclosure, it is necessary to determine the device perception result of the second device 102.

[0171] In step S2102, the third device 103 determines the first data.

[0172] In some embodiments, the third device 103 performs channel measurements based on the second signal to obtain first data.

[0173] In some embodiments, the first data may be raw channel measurement data used for device awareness of the second device. The first data may include noise.

[0174] In some embodiments, the first data may include, but is not limited to, the CSI matrix H.

[0175] In some embodiments, noise may include, but is not limited to, at least one of the following:

[0176] Gaussian white noise; fifth data.

[0177] In one example, the power spectral density of Gaussian white noise follows a uniform distribution, while the amplitude distribution follows a Gaussian distribution.

[0178] In one example, the fifth data is channel measurement data used for device awareness of other devices, such as the fifth device.

[0179] For example, the second device 102 is a sensing target device, and the fifth device is a non-sensing target device.

[0180] For example, the second device 102 is vehicle #1, but the first data obtained by the third device 103 may include data on the device perception of the fifth device, such as terminal #1, such as the CSI matrix corresponding to terminal #1.

[0181] In some embodiments, the name of the fifth data is not limited.

[0182] In step S2103, the third device 103 sends the first data to the first device 101.

[0183] In some embodiments, the first device 101 receives first data.

[0184] In some embodiments, step S2103 is an optional execution step. For example, when the third device 103 and the first device 101 are the same device, step S2103 may not be executed.

[0185] In step S2104, the first device 101 removes noise from the first data to obtain the second data.

[0186] In some embodiments, the first device 101 can remove the noise using a first AI model to obtain the second data.

[0187] In some embodiments, a first AI model is used to remove the noise.

[0188] In some embodiments, the first device 101 may remove the noise in other ways, such as non-AI methods, including but not limited to filtering the noise through devices such as filters, or filtering the noise using noise reduction algorithms. This disclosure does not limit the scope of the noise removal process.

[0189] In some embodiments, to improve the availability of AI in synesthesia, the noise can be removed using a first AI model.

[0190] In one example, the first data can be used as the input value of the first AI model, and the output value of the first AI model can be obtained. This output value is the second data.

[0191] In one example, the first AI model has determined the mapping relationship between noisy data and noise-removed data, and the second data can be obtained based on this mapping relationship.

[0192] In one example, the mapping could be a mapping between a CSI matrix with Gaussian white noise and fifth data and an ideal CSI matrix.

[0193] For example, an ideal CSI matrix may refer to a noise-free CSI matrix, or a CSI matrix that, although noisy, includes noise whose impact on the final device perception result is negligible.

[0194] In some embodiments, the training process of the first AI model will be described in subsequent embodiments and will not be described here.

[0195] In some embodiments, after the first AI model has been trained, the second data can be obtained directly during the inference phase.

[0196] In step S2105, the first device 101 performs device perception on the second device 102 based on the second data and determines the device perception result.

[0197] In some embodiments, the first device 101 may determine the device perception result based on a second AI model.

[0198] In some embodiments, the first device 101 may use the second data as the input value of the second AI model and determine the output value of the second AI model as the device perception result.

[0199] In some embodiments, the device perception result is the device perception result corresponding to the second device 102, which may include, but is not limited to, the specific values ​​of the three parameters of the second device 102: distance, speed, and angle.

[0200] In some embodiments, the training process of the second AI model will be described in subsequent embodiments and will not be described here.

[0201] In some embodiments, the first device 101 may determine the device perception result based on a non-AI method, and this disclosure does not limit this.

[0202] In some embodiments, the results of device perception can be used for autonomous driving control, device localization and tracking, environmental reconstruction, etc., and this disclosure does not limit them.

[0203] In some embodiments, the names of signals, etc., are not limited to those described in the embodiments. Terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0204] In some embodiments, the terms "codebook," "codeword," and "precoding matrix" can be used interchangeably. For example, a codebook can be a collection of one or more codewords / precoding matrices.

[0205] In some embodiments, “get,” “obtain,” “receive,” “transmit,” “bidirectional transmission,” and “send and / or receive” can be used interchangeably and can be interpreted as receiving from other entities, obtaining from protocols, obtaining from higher layers, obtaining through self-processing, or autonomous implementation, among other meanings.

[0206] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transfer,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.

[0207] In some embodiments, terms such as "certain," "preset," "default," "set," "indicated," "a certain," "any," and "first" can be used interchangeably. "Certain A," "preset A," "default A," "set A," "indicated A," "a certain A," "any A," and "first A" can be interpreted as A pre-defined in a protocol or the like, or as A obtained through setting, configuration, or instruction, or as specific A, a certain A, any A, or first A, but are not limited thereto.

[0208] The data processing method involved in the embodiments of this disclosure may include at least one of steps S2101 to S2105. For example, step S2104 may be implemented as an independent embodiment, step S2105 may be implemented as an independent embodiment, step S2104+S2105 may be implemented as an independent embodiment, step S2101 may be implemented as an independent embodiment, step S2102 may be implemented as an independent embodiment, step S2103 may be implemented as an independent embodiment, step S2101+S2102 may be implemented as an independent embodiment, and step S2101+S2102+S2103 may be implemented as an independent embodiment, but is not limited thereto.

[0209] In some embodiments, steps S2101 and S2103 may be performed in an alternate order or simultaneously.

[0210] In some embodiments, steps S2104 and S2105 may be performed in an alternate order or simultaneously.

[0211] In some embodiments, steps S2101, S2102, S2103, and S2105 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0212] In some embodiments, steps S2101, S2102, S2103, and S2104 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0213] In some embodiments, steps S2104 and S2105 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0214] In some embodiments, other alternative implementations may be described before or after the specification corresponding to FIG2A.

[0215] In the above embodiments, the first device can remove noise from the first data to obtain the second data, and the first device can perform device sensing based on the second data, which improves the reliability of device sensing, improves the usability of ISAC technology, and is conducive to promoting the integrated development of communication, sensing and artificial intelligence.

[0216] Figure 2B is a flowchart illustrating a data processing method according to an embodiment of the present disclosure. As shown in Figure 2B, the present disclosure relates to a data processing method, which can be executed by a first device 101. The method includes:

[0217] Step S2201: Input the first sample data into the first initial AI model and obtain the third data output by the first initial AI model.

[0218] In some embodiments, the first sample data is raw sample channel measurement data used for device awareness.

[0219] In some embodiments, the first sample data is raw sample data used for device sensing of multiple devices respectively.

[0220] In some embodiments, the first sample data includes multiple CSI matrices.

[0221] In some embodiments, the first initial AI model may use a convolutional neural network (CNN) or an autoencoder network as its backbone network, and may include, but is not limited to, at least one of the following network layers: input layer; convolutional layer; pooling layer; activation function layer; connection layer; and output layer. This disclosure does not limit the architecture of the first initial AI model.

[0222] In some embodiments, the first sample data can be used as the input value of the first initial AI model to obtain the third data output by the first initial AI model.

[0223] Step S2202: Determine the first loss function based on the difference between the third data and the fourth data.

[0224] In some embodiments, the fourth data is data used for device sensing and with the noise removed, including but not limited to the ideal CSI matrix described above.

[0225] In some embodiments, the first device 101 may determine the first loss function as the difference between the third data and the fourth data.

[0226] Step S2203: Based on the first loss function, train the first initial AI model until the first stopping condition is met, and then stop training to obtain the first AI model.

[0227] In some embodiments, the first device 101 may reduce the loss function based on the first loss function described above, using, for example, a stochastic gradient descent (SGD) algorithm.

[0228] In some embodiments, the first stopping condition may include, but is not limited to, at least one of the following:

[0229] Reach the first training cycle number;

[0230] The first loss function decreases to within the first fault tolerance range;

[0231] The first initial AI model achieved a first-value accuracy in removing noise.

[0232] In some embodiments, the first number of training epochs may be agreed upon by a protocol or configured by the network device, and this disclosure does not limit this. Specifically, to reduce the first loss function, the first device 101 increments the number of training epochs by 1 each time it adjusts the parameters of each network layer of the first initial AI model. The first device 101 may stop training when the number of training epochs of the first initial AI model reaches the specified first number of training epochs, at which point the first AI model can be obtained.

[0233] In some embodiments, the first fault tolerance range may be agreed upon by a protocol or configured by a network device, and this disclosure does not limit this. The first device 101 may use the fourth data as a label and stop training when the first loss function falls within the first fault tolerance range, thus obtaining the first AI model. Using the fourth data as a label can be understood as setting the training objective as infinitely close to the fourth data.

[0234] In some embodiments, the first value may be agreed upon by a protocol or configured by a network device, and this disclosure does not limit this. Specifically, the first device 101 may stop training and obtain the first AI model when it determines that the noise removal accuracy of the first initial AI model reaches the first value.

[0235] In some embodiments, steps S2201 to S2203 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0236] In some embodiments, the execution order of steps S2201 to S2203 is not limited.

[0237] In the above embodiments, the first AI model can be trained in the above manner, thereby improving the application of artificial intelligence in sensory integration and improving the reliability of device perception.

[0238] Figure 2C is a flowchart illustrating a data processing method according to an embodiment of the present disclosure. As shown in Figure 2C, the present disclosure relates to a data processing method, which can be executed by a first device 101. The method includes:

[0239] Step S2301: Obtain the device perception prediction result output by the second initial AI model.

[0240] In some embodiments, after the first AI model is trained, the third data output by the first AI model can be used as the input value of the second initial AI model to obtain the device perception prediction result output by the second initial AI model.

[0241] In some embodiments, to improve the training accuracy of the second AI model, the fourth data can be used as the input value of the second initial AI model to obtain the device perception prediction result output by the second initial AI model. Here, the fourth data is the ideal CSI matrix, i.e., the CSI matrix excluding noise. In some embodiments, the second initial AI model can use a convolutional neural network, autoencoder network, etc., as its backbone network, and may include, but is not limited to, at least one of the following network layers: input layer; convolutional layer; pooling layer; activation function layer; connection layer; output layer. This disclosure does not limit the architecture of the second initial AI model.

[0242] Step S2302: Determine the second loss function based on the difference between the device perception prediction result and the true value of the device perception result.

[0243] In some embodiments, the first device may acquire the true value of the device perception result corresponding to the fourth data. Specifically, the true value of the device perception result may include the true values ​​of the three parameters corresponding to the "perceived target": distance, speed, and angle. The number of perceived targets may be one or more, and this disclosure does not limit this.

[0244] In some embodiments, the second loss function may be determined based on the difference between the device perception prediction result output by the second initial AI model and the true value of the device perception result.

[0245] Step S2303: Based on the second loss function, train the second initial AI model until the second stopping condition is met, and then stop training to obtain the second AI model.

[0246] The second stopping condition includes at least one of the following:

[0247] Reach the second training cycle number;

[0248] The second loss function decreases to within the second fault tolerance range;

[0249] The accuracy of the second initial AI model in device perception reached the second value.

[0250] The specific implementation process is similar to the training process of the first AI model mentioned above, and will not be repeated here.

[0251] In some embodiments, steps S2301 to S2303 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0252] In some embodiments, the execution order of steps S2301 to S2303 is not limited.

[0253] In the above embodiments, the second AI model can be trained in the above manner, thereby improving the application of artificial intelligence in sensory integration and improving the reliability of device perception.

[0254] In some embodiments, a third AI model may be deployed on the first device 101, which can be used to remove noise and perform device perception.

[0255] In one example, the training process for the third AI model may include:

[0256] The third data is used as the input value of the third AI model to obtain the device perception prediction result output by the third AI model. Based on the difference between the device perception prediction result and the true value of the device perception prediction result, a third loss function is determined. Further, based on the third loss function, the third initial AI model is trained until a third stopping condition is met, at which point training stops, and the third AI model is obtained.

[0257] The training process of the third AI model is similar to that of the first and second AI models mentioned above, and will not be repeated here.

[0258] In one example, the third AI model includes two sequentially connected sub-models. The first sub-model is used to remove noise, and the second sub-model is used for device perception. The training process of the first sub-model can be similar to that of the first AI model, and the training process of the second sub-model can be similar to that of the second AI model. The specific process will not be described in detail here.

[0259] In the above embodiments, in order to reduce the number of AI models deployed on the first device, noise can be removed and device perception can be performed by an AI model, which simplifies the complexity of deploying AI models and improves availability.

[0260] Figure 3A is a flowchart illustrating a data processing method according to an embodiment of the present disclosure. As shown in Figure 3A, the present disclosure relates to a data processing method, which can be executed by a first device 101. The method includes:

[0261] Step S3101: Obtain the first data.

[0262] In some embodiments, the first device 101 and the third device 103 are the same device. The optional implementation of step S3101 can be found in the optional implementation of step S2102 in FIG2A and other related parts in the embodiments involved in FIG2A, which will not be repeated here.

[0263] In some embodiments, the first device 101 and the third device 103 are different devices. The optional implementation of step S3102 can be found in the optional implementation of step S2103 in FIG2A and other related parts in the embodiments involved in FIG2A, which will not be repeated here.

[0264] In some embodiments, the first device 101 receives first data sent by the third device 103, but is not limited thereto, and may also receive first data sent by other entities.

[0265] In some embodiments, the first device 101 acquires first data as defined by a protocol.

[0266] In some embodiments, the first device 101 obtains first data from the upper layer(s).

[0267] In some embodiments, the first device 101 processes data to obtain first data.

[0268] In some embodiments, step S3101 is omitted, and the first device 101 autonomously implements the function indicated by the first data, or the above function is a default or default setting.

[0269] Optionally, the third device 103 may send the first data to the first device 101 based on the request message sent by the first device 101.

[0270] Optionally, the third device 103 may send the first data to the first device 101 after receiving the first data.

[0271] Step S3102: Determine the second data.

[0272] In some embodiments, optional implementations of step S3102 can be found in optional implementations of step S2104 in FIG2A and other related parts in the embodiments involved in FIG2A, which will not be repeated here.

[0273] Step S3103: Determine the device sensing results.

[0274] In some embodiments, optional implementations of step S3102 can be found in optional implementations of step S2105 in FIG2A and other related parts in the embodiments involved in FIG2A, which will not be repeated here.

[0275] The data processing method involved in the embodiments of this disclosure may include at least one of steps S3101 to S3103. For example, step S3102 may be implemented as an independent embodiment, step S3103 may be implemented as an independent embodiment, step S3102+S3103 may be implemented as an independent embodiment, step S3101 may be implemented as an independent embodiment, and step S3101+S3102+S3103 may be implemented as an independent embodiment, but is not limited thereto.

[0276] In some embodiments, steps S3102 and S3103 may be performed in an alternate order or simultaneously.

[0277] In some embodiments, steps S3101 and S3103 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0278] In some embodiments, steps S2101 and S3102 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0279] In some embodiments, steps S3101 to S3103 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0280] In the above embodiments, the first device can remove noise from the first data to obtain the second data, and the first device can perform device sensing based on the second data, which improves the reliability of device sensing, improves the usability of ISAC technology, and is conducive to promoting the integrated development of communication, sensing and artificial intelligence.

[0281] Figure 3B is a flowchart illustrating a data processing method according to an embodiment of the present disclosure. As shown in Figure 3B, the present disclosure relates to a data processing method, which can be executed by a second device 102, and the method includes:

[0282] Step S3201: Send the first signal.

[0283] In some embodiments, if the second device 102 is the same device as the fourth device 104 and the third device 103, the second device 102 may send a first signal.

[0284] In some embodiments, optional implementations of step S3201 can be found in optional implementations of step S2101 in FIG2A and other related parts in the embodiments involved in FIG2A, which will not be repeated here.

[0285] In the above embodiments, the second device can send a first signal so that the third device can perform channel measurement based on the received second signal and obtain first data, which is simple to implement and highly available.

[0286] Figure 3C is a flowchart illustrating a data processing method according to an embodiment of the present disclosure. As shown in Figure 3C, the present disclosure relates to a data processing method, which can be executed by a third device 103, and the method includes:

[0287] Step S3301: Obtain the second signal.

[0288] In some embodiments, optional implementations of step S3301 can be found in optional implementations of step S2101 in FIG2A and other related parts in the embodiments involved in FIG2A, which will not be repeated here.

[0289] Step S3302: Determine the first data.

[0290] In some embodiments, optional implementations of step S3202 can be found in optional implementations of step S2102 in FIG2A and other related parts in the embodiments involved in FIG2A, which will not be repeated here.

[0291] Step S3303: Send the first data.

[0292] In some embodiments, optional implementations of step S3303 can be found in optional implementations of step S2103 in FIG2A and other related parts in the embodiments involved in FIG2A, which will not be repeated here.

[0293] In the above embodiments, after acquiring the second signal, the third device can perform channel measurement to obtain the first data and send the first data to the first device so that the first device can filter out the noise in the first data and perform device sensing, thereby improving the availability of the integrated sensing and communication system.

[0294] Figure 3D is a flowchart illustrating a data processing method according to an embodiment of the present disclosure. As shown in Figure 3D, the present disclosure relates to a data processing method, which can be executed by a fourth device 104, and the method includes:

[0295] Step S3401: Send the first signal.

[0296] In some embodiments, the fourth device 104 serves as the transmitting device of the first signal and can transmit the first signal.

[0297] In some embodiments, optional implementations of step S3401 can be found in optional implementations of step S2101 in FIG2A and other related parts in the embodiments involved in FIG2A, which will not be repeated here.

[0298] In the above embodiments, the fourth device can send a first signal so that the third device can perform channel measurement based on the received second signal and obtain first data, which is simple to implement and highly available.

[0299] The above process is further illustrated with examples below.

[0300] In some embodiments, this disclosure proposes a channel measurement data de-interference processing method for AI sensing. After the AI ​​sensing model inference node (LMF) acquires the channel measurement data for sensing reported by the UE or base station, it processes the channel measurement data based on the AI ​​data de-interference model, obtaining model output data close to the sensing target channel as input data for the AI ​​sensing model, thereby improving the target information sensing accuracy of the AI ​​sensing model. The application flow of the AI-based sensing measurement signal de-interference processing method proposed in this invention is shown in Figure 4A.

[0301] The AI-based interference-reduction processing model for sensing measurement signals uses channel measurement data, such as the channel state information matrix, received by the sensing model's inference node as input, and the sensing target channel matrix used for target perception as the label output for training. This allows the model to learn the mapping relationship between channel matrix data under noisy and non-sensory target interference conditions and the ideal sensing target channel matrix data. In practical system applications, the AI ​​sensing model's inference node can first process the data based on the interference-reduction model to obtain data close to the ideal sensing target channel as input data for the AI ​​sensing model, effectively improving the sensing accuracy of the AI ​​sensing model.

[0302] When applying the channel measurement data de-interference method for AI perception proposed in this disclosure, the overall application process is shown in Figure 4B, including the following steps:

[0303] Step S4201: Acquire sensing measurement data.

[0304] The sensing signal receiving device measures and obtains raw channel measurement data for AI sensing based on the sensing signals sent by the sensing signal transmitting device, including but not limited to the channel state information matrix.

[0305] Step S4202: Report the sensing measurement data.

[0306] The sensing signal receiving device reports channel measurement data to the sensing model inference device.

[0307] Step S4203: Sensing measurement data interference removal processing.

[0308] The perception model inference device inputs the received channel measurement data into the AI ​​interference removal model to obtain the interference-removed data.

[0309] Step S4204, AI perception model inference.

[0310] The perception model inference device inputs the interference-free processed data into the AI ​​perception model to obtain the perception results.

[0311] In the embodiments disclosed herein, some or all of the steps and their optional implementations may be arbitrarily combined with some or all of the steps in other embodiments, or may be arbitrarily combined with the optional implementations in other embodiments.

[0312] This disclosure also proposes an apparatus for implementing any of the above methods. For example, an apparatus is proposed that includes units or modules for implementing the steps performed by the first device in any of the above methods.

[0313] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0314] In this embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), or a Deep Learning Processing Unit (DPU).

[0315] Figure 5 is a schematic diagram of the structure of the first device proposed in an embodiment of this disclosure. As shown in Figure 5, the first device 5100 may include a processing module 5101.

[0316] In some embodiments, the processing module 5101 is used to acquire first data; wherein the first data is raw channel measurement data for device sensing of the second device; noise is removed from the first data to obtain second data; based on the second data, device sensing is performed on the second device to determine the device sensing result.

[0317] Optionally, the processing module 5101 is used to execute at least one of the other steps (such as step S2104, step S2105, but not limited thereto) executed by the first device 5100 in any of the above methods, which will not be described in detail here.

[0318] In some embodiments, the processing module may be a single module or may include multiple sub-modules. Optionally, the multiple sub-modules may each perform all or part of the steps required by the processing module. Optionally, the processing module may be interchangeable with a processor.

[0319] Figure 6A is a schematic diagram of the structure of the communication device 6100 proposed in an embodiment of this disclosure. The communication device 6100 can be a first device, which can be a network device (e.g., access network device, core network device, etc.), a terminal (e.g., user equipment, vehicle, etc.), a chip, chip system, or processor that supports the network device in implementing any of the above methods, or a chip, chip system, or processor that supports the terminal in implementing any of the above methods. The communication device 6100 can be used to implement the methods described in the above method embodiments; for details, please refer to the descriptions in the above method embodiments.

[0320] As shown in Figure 6A, the communication device 6100 includes one or more processors 6101. The processor 6101 can be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control communication devices (e.g., base stations, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute programs, and process program data. Optionally, the communication device 6100 can be used to execute any of the above methods. Optionally, one or more processors 6101 can be used to invoke instructions to cause the communication device 6100 to execute any of the above methods.

[0321] In some embodiments, the communication device 6100 further includes one or more transceivers 6102. When the communication device 6100 includes one or more transceivers 6102, the transceiver 6102 performs at least one of the communication steps (e.g., steps S2101, S2103, but not limited thereto) in the above method, such as sending and / or receiving, while the processor 6101 performs at least one of other steps (e.g., steps S2102, S2104, S2105, but not limited thereto). In optional embodiments, the transceiver may include a receiver and / or a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, interface, etc., can be used interchangeably; the terms transmitter, sending unit, transmitter, sending circuit, etc., can be used interchangeably; and the terms receiver, receiving unit, receiver, receiving circuit, etc., can be used interchangeably.

[0322] In some embodiments, the communication device 6100 further includes one or more memories 6103 for storing data. Optionally, all or part of the memories 6103 may be located outside the communication device 6100. In optional embodiments, the communication device 6100 may include one or more interface circuits 6104. Optionally, the interface circuits 6104 are connected to the memories 6102 and can be used to receive data from the memories 6102 or other devices, and to send data to the memories 6102 or other devices. For example, the interface circuits 6104 can read data stored in the memories 6102 and send the data to the processor 6101.

[0323] The communication device 6100 described in the above embodiments may be a network device or a terminal, but the scope of the communication device 6100 described in this disclosure is not limited thereto, and the structure of the communication device 6100 may not be limited by FIG. 6A. The communication device may be a standalone device or a part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data and programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, terminal device, smart terminal device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0324] Figure 6B is a schematic diagram of the structure of chip 6200 according to an embodiment of this disclosure. For cases where the communication device 6100 can be a chip or a chip system, please refer to the schematic diagram of chip 6200 shown in Figure 6B, but it is not limited thereto.

[0325] Chip 6200 includes one or more processors 6201. Chip 6200 is used to perform any of the methods described above.

[0326] In some embodiments, chip 6200 further includes one or more interface circuits 6202. Optionally, terms such as interface circuit, interface, and transceiver pin can be used interchangeably. In some embodiments, chip 6200 further includes one or more memories 6203 for storing data. Optionally, all or part of the memories 6203 may be located outside chip 6200. Optionally, interface circuit 6202 is connected to memory 6203, and interface circuit 6202 can be used to receive data from memory 6203 or other devices, and interface circuit 6202 can be used to send data to memory 6203 or other devices. For example, interface circuit 6202 can read data stored in memory 6203 and send the data to processor 6201.

[0327] In some embodiments, the interface circuit 6202 performs at least one of the communication steps (e.g., steps S2101, S2103, but not limited thereto) in the above-described method, such as sending and / or receiving. For example, the interface circuit 6202 performing the communication steps (e.g., sending and / or receiving) in the above-described method means that the interface circuit 6202 performs data interaction between the processor 6201, the chip 6200, the memory 6203, or the transceiver device. In some embodiments, the processor 6201 performs at least one of other steps (e.g., steps S2102, S2104, S2105, but not limited thereto).

[0328] The modules and / or devices described in the various embodiments, such as virtual devices, physical devices, and chips, can be combined or separated arbitrarily as needed. Optionally, some or all steps can also be performed collaboratively by multiple modules and / or devices, which is not limited here.

[0329] This disclosure also proposes a storage medium storing instructions that, when executed on the communication device 6100, cause the communication device 6100 to perform any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but not limited thereto; it may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but not limited thereto; it may also be a temporary storage medium.

[0330] This disclosure also provides a program product that, when executed by the communication device 6100, causes the communication device 6100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0331] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods.

[0332] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A data processing method, characterized in that, The method includes: Acquire first data; wherein the first data is raw channel measurement data used for device sensing of the second device; Remove noise from the first data to obtain the second data; Based on the second data, device perception is performed on the second device to determine the device perception result.

2. The method according to claim 1, characterized in that, The acquisition of the first data includes: Receive the first data sent by the third device.

3. The method according to claim 1, characterized in that, The acquisition of the first data includes: Receive a second signal; wherein the second signal is determined based on a first signal; wherein the first signal is a signal used to initiate device sensing; The first data is obtained by performing channel measurements based on the second signal.

4. The method according to any one of claims 1-3, characterized in that, The step of removing noise from the first data to obtain the second data includes: The first data is used as the input value of the first artificial intelligence (AI) model to obtain the second data output by the first AI model; wherein the first AI model is used to remove the noise.

5. The method according to claim 4, characterized in that, The method further includes: The first sample data is input into the first initial AI model to obtain the third data output by the first initial AI model; wherein, the first sample data is raw sample channel measurement data used for device perception; Based on the difference between the third data and the fourth data, a first loss function is determined; wherein, the fourth data is data used for device sensing and the noise has been removed; Based on the first loss function, the first initial AI model is trained until the first stopping condition is met, and the training stops to obtain the first AI model.

6. The method according to claim 5, characterized in that, The first stopping condition includes at least one of the following: Reach the first training cycle number; The first loss function decreases to within the first fault tolerance range; The first initial AI model achieved a first-value accuracy in removing noise.

7. The method according to any one of claims 1-6, characterized in that, The step of performing device perception on the second device based on the second data and determining the device perception result includes: The second data is used as the input value of the second AI model to obtain the device perception result output by the second AI model; wherein, the second AI model is used to perform device perception.

8. The method according to any one of claims 1-7, characterized in that, The noise includes at least one of the following: Gaussian white noise; The fifth data; wherein, the fifth data is channel measurement data used for device awareness of the fifth device.

9. A first device, characterized in that, include: The processing module is configured to acquire first data; wherein the first data is raw channel measurement data used for device awareness of the second device; The processing module is also configured to remove noise from the first data to obtain the second data; The processing module is also configured to perform device perception on the second device based on the second data and determine the device perception result.

10. A first device, characterized in that, include: One or more processors; The processor is used to execute the data processing method according to any one of claims 1-8.

11. A storage medium storing instructions, characterized in that, When the instruction is executed on the communication device, the communication device performs the data processing method as described in any one of claims 1-8.

12. A computer program, characterized in that, When it is run on a computer, it causes the computer to perform the data processing method as described in any one of claims 1-8.

Images