WO2024011433A1 - 一种人工智能ai模型的输入确定方法/装置/设备 - Google Patents

一种人工智能ai模型的输入确定方法/装置/设备 Download PDF

Info

Publication number
WO2024011433A1
WO2024011433A1 PCT/CN2022/105307 CN2022105307W WO2024011433A1 WO 2024011433 A1 WO2024011433 A1 WO 2024011433A1 CN 2022105307 W CN2022105307 W CN 2022105307W WO 2024011433 A1 WO2024011433 A1 WO 2024011433A1
Authority
WO
WIPO (PCT)
Prior art keywords
base stations
model
positioning measurement
measurement results
base station
Prior art date
Application number
PCT/CN2022/105307
Other languages
English (en)
French (fr)
Inventor
牟勤
洪伟
赵中原
周惠宣
Original Assignee
北京小米移动软件有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京小米移动软件有限公司 filed Critical 北京小米移动软件有限公司
Priority to CN202280002587.2A priority Critical patent/CN117693990A/zh
Priority to PCT/CN2022/105307 priority patent/WO2024011433A1/zh
Publication of WO2024011433A1 publication Critical patent/WO2024011433A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management

Definitions

  • the present disclosure relates to the field of communication technology, and in particular, to an input determination method/device/equipment for an AI model and a storage medium.
  • New Radio New Radio
  • AI Artificial Intelligent, AI
  • the positioning measurement results (such as impulse response and/or measurement power) corresponding to all base stations participating in the positioning measurement are spliced as the input of the AI model, so that the AI model outputs the positioned terminal device.
  • the position coordinates or the measurement information used to calculate the position coordinates of the positioned terminal device (such as Reference Signal Receiving Power (RSRP)), thereby achieving high-precision positioning functions.
  • RSRP Reference Signal Receiving Power
  • the input dimension of the AI model is very large, which will bring a greater burden to the processing of the AI model, and the storage requirements are also very large. Also, if the input of the AI model needs to be transmitted over the air interface (for example, it needs to be transmitted from the base station to the terminal device, or from the terminal device to the base station), it will also bring additional signaling burden.
  • the input determination method/device/equipment and storage medium of the AI model proposed in this disclosure are to solve the problem that the methods of related technologies will bring a greater burden to the processing of the AI model, very large requirements for storage, and additional signaling. Burden technical issues.
  • embodiments of the present disclosure provide an input determination method for an AI model, which is executed by a terminal device, including:
  • the positioning measurement results corresponding to the X base stations are determined as the input of the AI model.
  • the terminal device when the AI model is deployed on the terminal device side, the terminal device will first obtain the positioning measurement results corresponding to the preset number X base stations, where the preset number X is less than the total number M of all base stations participating in the positioning measurement; and M are both positive integers; later, the positioning measurement results corresponding to X base stations will be determined as the input of the AI model.
  • the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is,
  • the input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements.
  • the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • embodiments of the present disclosure provide an input determination method for an AI model, which is executed by a base station and includes:
  • the positioning measurement results corresponding to the X base stations are determined as the input of the AI model.
  • inventions of the present disclosure provide an input determination device for an AI model.
  • the device is configured in a terminal device and includes:
  • a transceiver module used to obtain positioning measurement results corresponding to a preset number of base stations X, where the preset number
  • a processing module configured to determine the positioning measurement results corresponding to the X base stations as input to the AI model.
  • inventions of the present disclosure provide an input determination device for an AI model.
  • the device is configured in a base station and includes:
  • a transceiver module used to obtain positioning measurement results corresponding to a preset number of base stations X, where the preset number
  • a processing module configured to determine the positioning measurement results corresponding to the X base stations as input to the AI model.
  • an embodiment of the present disclosure provides a communication device.
  • the communication device includes a processor.
  • the processor calls a computer program in a memory, it executes the method described in the first aspect.
  • an embodiment of the present disclosure provides a communication device.
  • the communication device includes a processor.
  • the processor calls a computer program in a memory, it executes the method described in the second aspect.
  • an embodiment of the present disclosure provides a communication device.
  • the communication device includes a processor and a memory, and a computer program is stored in the memory; the processor executes the computer program stored in the memory, so that the communication device executes The method described in the first aspect above.
  • an embodiment of the present disclosure provides a communication device.
  • the communication device includes a processor and a memory, and a computer program is stored in the memory; the processor executes the computer program stored in the memory, so that the communication device executes The method described in the second aspect above.
  • an embodiment of the present disclosure provides a communication device.
  • the device includes a processor and an interface circuit.
  • the interface circuit is used to receive code instructions and transmit them to the processor.
  • the processor is used to run the code instructions to cause the The device executes the method described in the first aspect.
  • an embodiment of the present disclosure provides a communication device.
  • the device includes a processor and an interface circuit.
  • the interface circuit is used to receive code instructions and transmit them to the processor.
  • the processor is used to run the code instructions to cause the The device performs the method described in the second aspect above.
  • an embodiment of the present disclosure provides a communication system, which includes the communication device described in the third aspect to the communication device described in the fourth aspect, or the system includes the communication device described in the fifth aspect to The communication device according to the sixth aspect, or the system includes the communication device according to the seventh aspect to the communication device according to the eighth aspect, or the system includes the communication device according to the ninth aspect to the tenth aspect. the above-mentioned communication device.
  • embodiments of the present invention provide a computer-readable storage medium for storing instructions used by the above-mentioned network device.
  • the terminal device When the instructions are executed, the terminal device is caused to perform the above-mentioned first aspect to the second aspect.
  • embodiments of the present invention provide a computer-readable storage medium for storing instructions used by the above-mentioned network device. When the instructions are executed, the terminal device is caused to perform the above-mentioned first aspect to the second aspect. The method described in any of the aspects.
  • the present disclosure also provides a computer program product including a computer program, which, when run on a computer, causes the computer to execute the method described in any one of the above first to second aspects.
  • the present disclosure provides a chip system that includes at least one processor and an interface for supporting a network device to implement the functions involved in the method described in any one of the first to second aspects, For example, at least one of the data and information involved in the above method is determined or processed.
  • the chip system further includes a memory, and the memory is used to store necessary computer programs and data of the source secondary node.
  • the chip system may be composed of chips, or may include chips and other discrete devices.
  • the present disclosure provides a computer program that, when run on a computer, causes the computer to perform the method described in any one of the above first to second aspects.
  • Figure 1 is a schematic architectural diagram of a communication system provided by an embodiment of the present disclosure
  • Figure 2a is a schematic flowchart of an input determination method for an AI model provided by an embodiment of the present disclosure
  • Figure 2b is a schematic flowchart of an input determination method for an AI model provided by another embodiment of the present disclosure
  • Figure 2c is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure
  • Figure 3a is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure
  • Figure 3b is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure
  • Figure 4a is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure
  • Figure 4b is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure
  • Figure 5a is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure
  • Figure 5b is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure
  • Figure 6 is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure.
  • Figure 7 is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure.
  • Figure 8 is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure.
  • Figure 9 is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure.
  • Figure 10a is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure
  • Figure 10b is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure.
  • Figure 10c is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure.
  • Figure 11 is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure.
  • Figure 12 is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure.
  • Figure 13 is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure.
  • Figure 14a is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure
  • Figure 14b is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure.
  • Figure 14c is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure.
  • Figure 14d is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure.
  • Figure 14e is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure.
  • Figure 14f is a schematic flowchart of an input determination method for an AI model provided by yet another embodiment of the present disclosure.
  • Figure 15 is a schematic structural diagram of an input determination device for an AI model provided by an embodiment of the present disclosure.
  • Figure 16 is a schematic structural diagram of an input determination device for an AI model provided by another embodiment of the present disclosure.
  • Figure 17 is a schematic structural diagram of a communication device provided by an embodiment of the present disclosure.
  • Figure 18 is a schematic structural diagram of a chip provided by an embodiment of the present disclosure.
  • first, second, third, etc. may be used to describe various information in the embodiments of the present disclosure, the information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other.
  • first information may also be called second information, and similarly, the second information may also be called first information.
  • the words "if” and “if” as used herein may be interpreted as “when” or “when” or “in response to determining.”
  • AI is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI can perform complex tasks without human intervention in solving them. Therefore, it is used in all walks of life.
  • FIG. 1 is a schematic architectural diagram of a communication system provided by an embodiment of the present disclosure.
  • the communication system may include but is not limited to one network device and one terminal device.
  • the number and form of devices shown in Figure 1 are only for examples and do not constitute a limitation on the embodiments of the present disclosure. In actual applications, two or more devices may be included. Network equipment, two or more terminal devices.
  • the communication system shown in Figure 1 includes a network device 11 and a terminal device 12 as an example.
  • LTE long term evolution
  • 5th generation fifth generation
  • 5G new radio (NR) system 5th generation new radio
  • the network device 11 in the embodiment of the present disclosure is an entity on the network side that is used to transmit or receive signals.
  • the network device 11 may be an evolved base station (evolved NodeB, eNB), a transmission reception point (TRP), a next generation base station (next generation NodeB, gNB) in an NR system, or other base stations in future mobile communication systems. Base stations or access nodes in wireless fidelity (WiFi) systems, etc.
  • the embodiments of the present disclosure do not limit the specific technologies and specific equipment forms used by network equipment.
  • the network equipment provided by the embodiments of the present disclosure may be composed of a centralized unit (CU) and a distributed unit (DU).
  • the CU may also be called a control unit (control unit).
  • CU-DU is used.
  • the structure can separate the protocol layers of network equipment, such as base stations, and place some protocol layer functions under centralized control on the CU. The remaining part or all protocol layer functions are distributed in the DU, and the CU centrally controls the
  • the terminal device 12 in the embodiment of the present disclosure is an entity on the user side for receiving or transmitting signals, such as a mobile phone.
  • Terminal equipment can also be called terminal equipment (terminal), user equipment (user equipment, UE), mobile station (mobile station, MS), mobile terminal equipment (mobile terminal, MT), etc.
  • the terminal device can be a car with communication functions, a smart car, a mobile phone, a wearable device, a tablet computer (Pad), a computer with wireless transceiver functions, a virtual reality (VR) terminal device, an augmented reality (augmented reality (AR) terminal equipment, wireless terminal equipment in industrial control, wireless terminal equipment in self-driving, wireless terminal equipment in remote medical surgery, smart grid ( Wireless terminal equipment in smart grid, wireless terminal equipment in transportation safety, wireless terminal equipment in smart city, wireless terminal equipment in smart home, etc.
  • the embodiments of the present disclosure do not limit the specific technology and specific equipment form used by the terminal equipment.
  • FIG. 2a is a schematic flowchart of an AI model input determination method provided by an embodiment of the present disclosure, which is applied to a terminal device.
  • the AI model input determination method may include the following steps:
  • Step 201a Obtain positioning measurement results corresponding to a preset number of X base stations.
  • the positioning measurement result may include at least one of the following:
  • Measured power obtained by measuring the reference signal transmitted between the base station and the located terminal device.
  • the preset number X is less than the total number M of all base stations participating in positioning measurement; where X and M are both positive integers.
  • the above-mentioned positioning measurement results can be obtained by measurements performed by the base station, or can be obtained by measurements performed by the terminal device, and, on the premise that the AI model is deployed on the terminal device, when the measurement execution subject of the positioning measurement results is different, the method of "obtaining the positioning measurement results corresponding to the preset number X base stations" in this step will also be different. This part will be introduced in detail in subsequent embodiments. .
  • Step 202a Determine the positioning measurement results corresponding to the X base stations as the input of the AI model.
  • the AI model can be caused to output the position coordinates of the positioned terminal device or measurement information used to calculate the position coordinates of the positioned terminal device. (such as RSRP) to achieve high-precision positioning function.
  • the terminal device when the AI model is deployed on the terminal device side, the terminal device will first obtain the positioning measurement results corresponding to the preset number X base stations, where, The preset number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • the measurement execution end of the positioning measurement results can be the terminal device or the base station. Based on this, subsequent embodiments specifically introduce the method of the present disclosure based on whether the deployment end of the AI model and the measurement execution end of the positioning measurement results are on the same side or not on the same side.
  • FIG. 2b is a schematic flowchart of an input determination method for an AI model provided by an embodiment of the present disclosure, applied to a terminal device, where in this embodiment, the AI model is deployed on the terminal device, and positioning measurement is performed by the terminal device, and , as shown in Figure 2b, the input determination method of the AI model may include the following steps:
  • Step 201b In response to the positioning measurement results measured by the terminal device, determine the measured positioning measurement results corresponding to the M base stations.
  • Step 202b Select X base stations from M base stations.
  • the terminal device can select X base stations from the M base stations uniformly or non-uniformly, and there are details about how the terminal device specifically selects the X base stations from the M base stations. The method will be described in subsequent embodiments. How do you understand uniformity?
  • Step 203b Obtain positioning measurement results corresponding to X base stations.
  • Step 204b Determine the positioning measurement results corresponding to the X base stations as input to the AI model.
  • the terminal device when the AI model is deployed on the terminal device side, the terminal device will first obtain the positioning measurement results corresponding to the preset number X base stations, where, The preset number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 2c is a schematic flow chart of an AI model input determination method provided by an embodiment of the present disclosure, applied to a terminal device, where the AI model is deployed on the terminal device, but positioning measurement is performed by the base station, and as shown in Figure 2c
  • the input determination method of the AI model may include the following steps:
  • Step 201c Obtain corresponding positioning measurement results sent by M base stations.
  • each base station participating in positioning measurement measures its corresponding positioning measurement result
  • each base station will send its corresponding measurement result to the terminal device, so that the terminal device can obtain
  • the corresponding positioning measurement results are sent to the M base stations participating in the positioning measurement.
  • Step 202c Select X base stations from M base stations.
  • Step 203c Obtain positioning measurement results corresponding to X base stations.
  • Step 204c Determine the positioning measurement results corresponding to the X base stations as the input of the AI model.
  • the terminal device when the AI model is deployed on the terminal device side, the terminal device will first obtain the positioning measurement results corresponding to the preset number X base stations, where, The preset number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 3a is a schematic flow chart of an AI model input determination method provided by an embodiment of the present disclosure, applied to a terminal device, where the AI model is deployed on the terminal device, and positioning measurement is performed by the terminal device, and as shown in Figure 3a
  • the input determination method of the AI model may include the following steps:
  • Step 301a In response to the positioning measurement results measured by the terminal equipment, determine the measured positioning measurement results corresponding to the M base stations.
  • Step 302a Determine the value of X.
  • the method for determining the value of X may include at least one of the following:
  • the value of X is determined based on the configuration of the base station.
  • the value of X configured by the base station in the above method may be one selected by the base station from the set of possible values of X ⁇ X1, value, where the set of possible values of X ⁇ X1, X2, X3, X4,... ⁇ can be based on the agreement, and X1,
  • the value of X configured by the base station in the above method may also be a value of X determined independently by the base station based on implementation.
  • the base station can select the value of X from the set of possible values of X or independently determine the value of
  • the value of X selected by the base station or the value of X independently determined may be larger.
  • the value of X selected by the base station or the value of X independently determined can be smaller.
  • Step 303a Arrange the M base stations in order of their positions.
  • each base station participating in positioning measurement can send its location coordinates to the terminal device, and the terminal device can sequentially arrange the M base stations based on the location coordinates of the M base stations, such as They can be arranged in any direction from east to west or from south to north, or they can be arranged in any direction from far to near or from near to far from the terminal device.
  • Step 304a Select X base stations uniformly or non-uniformly from the arranged M base stations.
  • the above-mentioned uniform selection may be a regular selection of base stations.
  • the above-mentioned non-uniform selection can be a random selection of base stations.
  • the arranged 18 base stations can be numbered first, for example, numbered 1-18. Afterwards, if it is determined that the value of Select 6 base stations numbered ⁇ 3, 4, 9, 10, 15, 16 ⁇ among the base stations.
  • Step 305a Obtain positioning measurement results corresponding to X base stations.
  • Step 306a Determine the positioning measurement results corresponding to the X base stations as the input of the AI model.
  • the AI model when the AI model outputs the position coordinates of the positioned terminal device or outputs the measurement information used to calculate the position coordinates of the positioned terminal device, in addition to needing to use the positioning measurement results corresponding to the base stations participating in the positioning measurement, It is also necessary to use the location coordinates of the base station. Based on this, during positioning measurement, if the AI model is deployed on the terminal device, the same terminal device can select the same X base stations when performing positioning measurements for different times. Since the terminal device selects the same X base stations for each positioning measurement, the position coordinates of the X base stations can be stored in the AI model. Therefore, when the AI model is used to position the terminal device, no input is needed. The position coordinates of X base stations are input, and only the positioning measurement results corresponding to X base stations are input, which reduces the input dimension and reduces signaling overhead.
  • the terminal device when the AI model is deployed on the terminal device side, the terminal device will first obtain the positioning measurement results corresponding to the preset number X base stations, where, The preset number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 3b is a schematic flowchart of an input determination method for an AI model provided by an embodiment of the present disclosure, applied to a terminal device, where the AI model is deployed on the terminal device, but the positioning measurement is performed by the base station, and as shown in Figure 3b
  • the input determination method of the AI model may include the following steps:
  • Step 301b In response to the positioning measurement results measured by the base stations, obtain corresponding positioning measurement results sent by M base stations.
  • Step 302b Determine the value of X.
  • Step 303b Arrange the M base stations in order of their positions.
  • Step 304b Select X base stations uniformly or non-uniformly from the arranged M base stations.
  • Step 305b Obtain positioning measurement results corresponding to X base stations.
  • Step 306b Determine the positioning measurement results corresponding to the X base stations as the input of the AI model.
  • steps 301b to 306b please refer to the description of the above embodiment.
  • the AI model when the AI model outputs the position coordinates of the positioned terminal device or outputs the measurement information used to calculate the position coordinates of the positioned terminal device, in addition to needing to use the positioning measurement results corresponding to the base stations participating in the positioning measurement, It is also necessary to use the location coordinates of the base station. Based on this, during positioning measurement, if the AI model is deployed on the terminal device, the same terminal device can select the same X base stations when performing positioning measurements for different times. Since the terminal device selects the same X base stations for each positioning measurement, the position coordinates of the X base stations can be stored in the AI model. Therefore, when the AI model is used to position the terminal device, there is no need to Enter the position coordinates of X base stations, and only input the positioning measurement results corresponding to the X base stations, which reduces the input dimension and reduces signaling overhead.
  • the terminal device when the AI model is deployed on the terminal device side, the terminal device will first obtain the positioning measurement results corresponding to the preset number X base stations, where, The preset number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 4a is a schematic flow chart of an AI model input determination method provided by an embodiment of the present disclosure, applied to a terminal device, where the AI model is deployed on the terminal device, and positioning measurement is performed by the terminal device, and as shown in Figure 4a
  • the input determination method of the AI model may include the following steps:
  • Step 401a In response to the positioning measurement results measured by the terminal equipment, determine the measured positioning measurement results corresponding to the M base stations.
  • Step 402a Determine a base station set, where the base station set may include X base stations among M base stations.
  • the method for determining the base station set includes at least one of the following:
  • the set of base stations is determined based on the configuration of the base stations.
  • the base station set configured by the base station in the above method may be the base station set from the candidate base station set ⁇ S1(X), S2(X), S3(X),... ⁇ A set of selected base stations, where the set of candidate base stations ⁇ S1(X), S2(X), S3(X),... ⁇ can be based on the protocol agreement, S1(X), S2(X), S3(X ) are all candidate base station sets.
  • S1(X), S2(X), and S3(X) each include X base stations among M base stations, and S1(X), S2(X), S3(X ) are different.
  • the number of base stations included in different candidate base station sets may be the same or different, that is, S1(X), S2(X), S3(X)
  • the number of base stations included in can be the same or different.
  • the base station set configured by the base station in the above method may also be a set independently determined by the base station based on implementation.
  • M base stations may be numbered, and the above-mentioned base station set may be the numbers of the selected X base stations.
  • the arranged 18 base stations can be first Number it, for example, the number is 1-18.
  • the base station set determined in this step can be, for example, ⁇ 3,4,9,10,15,16 ⁇ , that is, the base station set includes numbers 3,4,9,10,15,16 of 6 base stations.
  • Step 403a Determine X base stations based on the base station set.
  • the base stations in the base station set are determined as X base stations.
  • Step 404a Obtain positioning measurement results corresponding to X base stations.
  • Step 405a Determine the positioning measurement results corresponding to the X base stations as the input of the AI model.
  • the AI model when the AI model outputs the position coordinates of the positioned terminal device or outputs the measurement information used to calculate the position coordinates of the positioned terminal device, in addition to needing to use the positioning measurement results corresponding to the base stations participating in the positioning measurement, It is also necessary to use the location coordinates of the base station. Based on this, during positioning measurement, if the AI model is deployed on the terminal device, the same terminal device can select the same X base stations when performing positioning measurements for different times. Since the terminal device selects the same X base stations for each positioning measurement, the position coordinates of the X base stations can be stored in the AI model. Therefore, when the AI model is used to position the terminal device, there is no need to Enter the position coordinates of X base stations, and only input the positioning measurement results corresponding to the X base stations, which reduces the input dimension and reduces signaling overhead.
  • the terminal device when the AI model is deployed on the terminal device side, the terminal device will first obtain the positioning measurement results corresponding to the preset number X base stations, where, The preset number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 4b is a schematic flow chart of an AI model input determination method provided by an embodiment of the present disclosure, applied to a terminal device, where the AI model is deployed on the terminal device, but positioning measurement is performed by the base station, and as shown in Figure 4b
  • the input determination method of the AI model may include the following steps:
  • Step 401b In response to the positioning measurement results measured by the base stations, obtain corresponding positioning measurement results sent by M base stations.
  • Step 402b Determine a base station set, where the base station set may include X base stations among M base stations.
  • Step 403b Determine X base stations based on the base station set.
  • Step 404b Obtain positioning measurement results corresponding to X base stations.
  • Step 405b Determine the positioning measurement results corresponding to the X base stations as the input of the AI model.
  • steps 401b to 405b please refer to the description of the above embodiment.
  • the AI model when the AI model outputs the position coordinates of the positioned terminal device or outputs the measurement information used to calculate the position coordinates of the positioned terminal device, in addition to needing to use the positioning measurement results corresponding to the base stations participating in the positioning measurement, It is also necessary to use the location coordinates of the base station. Based on this, during positioning measurement, if the AI model is deployed on the terminal device, the same terminal device can select the same X base stations when performing positioning measurements for different times. Since the terminal device selects the same X base stations for each positioning measurement, the position coordinates of the X base stations can be stored in the AI model. Therefore, when the AI model is used to position the terminal device, there is no need to Enter the position coordinates of X base stations, and only input the positioning measurement results corresponding to the X base stations, which reduces the input dimension and reduces signaling overhead.
  • the terminal device when the AI model is deployed on the terminal device side, the terminal device will first obtain the positioning measurement results corresponding to the preset number X base stations, where, The preset number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 5a is a schematic flow chart of an AI model input determination method provided by an embodiment of the present disclosure, applied to a terminal device, where the AI model is deployed on the terminal device, and positioning measurement is performed by the terminal device, and as shown in Figure 5a
  • the input determination method of the AI model may include the following steps:
  • Step 501a In response to the positioning measurement results measured by the terminal device, determine the measured positioning measurement results corresponding to the M base stations.
  • Step 502a Determine the value of X.
  • step 502a For detailed introduction to step 502a, please refer to the above embodiment description.
  • Step 503a Select X base stations from the M base stations based on the arrival time of the first path of the channel between the M base stations and the terminal equipment.
  • the above-mentioned selection of X base stations from M base stations based on the arrival time of the first path of the channel between the M base stations and the terminal device may include: selecting from the M base stations and The X base stations with the shortest first path arrival time of the channel between terminal devices.
  • Step 504a Obtain positioning measurement results corresponding to X base stations.
  • Step 505a Determine the location coordinates of the selected X base stations.
  • the AI model when the AI model outputs the position coordinates of the positioned terminal device or outputs the measurement information used to calculate the position coordinates of the positioned terminal device, in addition to the need to use the base station corresponding to the positioning measurement In addition to the positioning measurement results, the location coordinates of the base station are also needed.
  • the terminal device may move, causing the position of the terminal device to change. Based on this, if each positioning measurement selects X base stations from M base stations based on the first path arrival time of the channel, then due to the change in the position of the terminal equipment, the terminal equipment will be under positioning measurement at different times. The first path arrival time of the channel between each base station will be different, and different X base stations may be selected.
  • the AI model in order to ensure that the AI model can correctly output the position coordinates or measurement information of the positioned terminal device, it is also necessary to determine the position coordinates of the X base stations selected by the terminal device each time, and together with the corresponding positioning of the X base stations The measurement results are also input into the AI model.
  • the position coordinates of the above-mentioned base station can be represented by two-dimensional coordinates (x, y).
  • the above-mentioned method of determining the location coordinates of X base stations may include: obtaining the location coordinates of the base station sent by the base station.
  • Step 506a Determine the positioning measurement results corresponding to the X base stations and the position coordinates of the X base stations as inputs to the AI model.
  • the positioning measurement results corresponding to the X base stations and the position coordinates of the Measurement information of the device's position coordinates (such as RSRP) to achieve high-precision positioning functions.
  • the terminal device when the AI model is deployed on the terminal device side, the terminal device will first obtain the positioning measurement results corresponding to the preset number X base stations, where, The preset number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 5b is a schematic flowchart of an input determination method for an AI model provided by an embodiment of the present disclosure, applied to a terminal device, where the AI model is deployed on the terminal device, but the positioning measurement is performed by the base station, and as shown in Figure 5b
  • the input determination method of the AI model may include the following steps:
  • Step 501b In response to the positioning measurement results measured by the base stations, obtain corresponding positioning measurement results sent by M base stations.
  • Step 502b Determine the value of X.
  • Step 503b Select X base stations from the M base stations based on the arrival time of the first path of the channel between the M base stations and the terminal equipment.
  • Step 504b Obtain positioning measurement results corresponding to X base stations.
  • Step 505b Determine the location coordinates of the selected X base stations.
  • Step 506b Determine the positioning measurement results corresponding to the X base stations and the position coordinates of the X base stations as inputs to the AI model.
  • steps 501b to 506b please refer to the description of the above embodiment.
  • the AI model when the AI model outputs the position coordinates of the positioned terminal device or outputs the measurement information used to calculate the position coordinates of the positioned terminal device, in addition to the need to use the base station corresponding to the positioning measurement In addition to the positioning measurement results, the location coordinates of the base station are also needed.
  • the terminal device may move, causing the position of the terminal device to change. Based on this, if each positioning measurement selects X base stations from M base stations based on the first path arrival time of the channel, then due to the change in the position of the terminal equipment, the terminal equipment will be under positioning measurement at different times. The first path arrival time of the channel between each base station will be different, and different X base stations may be selected.
  • the AI model in order to ensure that the AI model can correctly output the position coordinates or measurement information of the positioned terminal device, it is also necessary to determine the position coordinates of the X base stations selected by the terminal device each time, and together with the corresponding positioning of the X base stations The measurement results are also input into the AI model.
  • the terminal device when the AI model is deployed on the terminal device side, the terminal device will first obtain the positioning measurement results corresponding to the preset number X base stations, where, The preset number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • FIG. 6 is a schematic flowchart of an input determination method for an AI model provided by an embodiment of the present disclosure, which is applied to a terminal device, where the AI model is deployed on a base station, and, as shown in Figure 6, the input determination of the AI model Methods can include the following steps:
  • Step 601 In response to the positioning measurement results measured by the terminal device, determine the positioning measurement results corresponding to the measured M base stations, where M is the total number of all base stations participating in the positioning measurement, and M is a positive integer.
  • Step 602 Select X base stations from M base stations, X ⁇ M, and X is a positive integer.
  • Step 603 Send the positioning measurement results corresponding to the X base stations to the base station where the AI model is deployed.
  • steps 601 to 603 please refer to the description of the above embodiment.
  • the terminal device when the AI model is deployed on the base station side, the terminal device will determine the positioning measurement results corresponding to the M base stations participating in the positioning measurement. After that, X base stations will be selected from M base stations, and the positioning measurement results of the X base stations will be sent to the base station where the AI model is deployed, so that the positioning measurement results corresponding to the X base stations can be determined as the input of the AI model.
  • the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is,
  • the input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements.
  • the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 7 is a schematic flow chart of an AI model input determination method provided by an embodiment of the present disclosure, applied to a terminal device, where the AI model is deployed on the base station, but the positioning measurement results are measured by the terminal device, and as shown in Figure 7
  • the input determination method of the AI model may include the following steps:
  • Step 701 In response to the positioning measurement results measured by the terminal device, determine the positioning measurement results corresponding to the measured M base stations, where M is the total number of all base stations participating in the positioning measurement, and M is a positive integer.
  • Step 702 Determine the value of X.
  • the method for determining the value of X may include:
  • the value of X is determined based on the configuration of the base station.
  • Step 703 Arrange the M base stations in order of their positions.
  • Step 704 Select X base stations uniformly or non-uniformly from the arranged M base stations.
  • Step 705 Send the positioning measurement results corresponding to the X base stations to the base station where the AI model is deployed.
  • steps 701 to 705 please refer to the description of the above embodiment.
  • the AI model may be used to measure multiple terminal devices.
  • the AI model outputs the position coordinates of the positioned terminal device or outputs the measurement information used to calculate the position coordinates of the positioned terminal device, in addition to needing to use the positioning measurement results corresponding to the base stations participating in the positioning measurement, The location coordinates of the base stations are also needed.
  • each terminal device can select the same X base stations.
  • the location coordinates of the X base stations can be stored in the AI model. Therefore, when using the AI model to position each terminal device, there is no need to Enter the position coordinates of X base stations, and only input the positioning measurement results corresponding to the X base stations, which reduces the input dimension and reduces signaling overhead.
  • the terminal device when the AI model is deployed on the base station side, the terminal device will determine the positioning measurement results corresponding to the M base stations participating in the positioning measurement. After that, X base stations will be selected from M base stations, and the positioning measurement results of the X base stations will be sent to the base station where the AI model is deployed, so that the positioning measurement results corresponding to the X base stations can be determined as the input of the AI model.
  • the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is,
  • the input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements.
  • the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 8 is a schematic flow chart of an AI model input determination method provided by an embodiment of the present disclosure, applied to a terminal device, where the AI model is deployed on the base station, but the positioning measurement results are measured by the terminal device, and as shown in Figure 8
  • the input determination method of the AI model may include the following steps:
  • Step 801 In response to the positioning measurement results measured by the terminal device, determine the positioning measurement results corresponding to the measured M base stations, where M is the total number of all base stations participating in the positioning measurement, and M is a positive integer.
  • Step 802 Determine a base station set, where the base station set includes X base stations among the M base stations.
  • the method for determining the base station set may include at least one of the following:
  • the set of base stations is determined based on the configuration of the base stations.
  • Step 803 Determine X base stations based on the base station set.
  • Step 804 Send the positioning measurement results corresponding to the X base stations to the base station where the AI model is deployed.
  • steps 801 to 804 please refer to the description of the above embodiment.
  • the AI model may be used to measure multiple terminal devices.
  • the AI model outputs the position coordinates of the positioned terminal device or outputs the measurement information used to calculate the position coordinates of the positioned terminal device, in addition to needing to use the positioning measurement results corresponding to the base stations participating in the positioning measurement, The location coordinates of the base stations are also needed.
  • each terminal device can select the same X base stations.
  • the location coordinates of the X base stations can be stored in the AI model. Therefore, when using the AI model to position each terminal device, there is no need to Enter the location coordinates of X base stations, and only enter the positioning measurement results corresponding to X base stations, which reduces the input dimension and signaling overhead.
  • the terminal device when the AI model is deployed on the base station side, the terminal device will determine the positioning measurement results corresponding to the M base stations participating in the positioning measurement. After that, X base stations will be selected from M base stations, and the positioning measurement results of the X base stations will be sent to the base station where the AI model is deployed, so that the positioning measurement results corresponding to the X base stations can be determined as the input of the AI model.
  • the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is,
  • the input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements.
  • the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 9 is a schematic flow chart of an AI model input determination method provided by an embodiment of the present disclosure, applied to a terminal device, where the AI model is deployed on the base station, but the positioning measurement results are measured by the terminal device, and as shown in Figure 9
  • the input determination method of the AI model may include the following steps:
  • Step 901 In response to the positioning measurement results measured by the terminal device, determine the positioning measurement results corresponding to the measured M base stations, where M is the total number of all base stations participating in the positioning measurement, and M is a positive integer.
  • Step 902 Determine the value of X.
  • Step 903 Select X base stations from the M base stations based on the arrival time of the first path of the channel between the M base stations and the terminal equipment.
  • X base stations are selected from the M base stations based on the first path arrival time of the channel between the M base stations and the terminal equipment, including:
  • Step 904 Send the positioning measurement results corresponding to the X base stations to the base station where the AI model is deployed.
  • steps 901 to 904 please refer to the description of the above embodiment.
  • the AI model when the AI model outputs the position coordinates of the positioned terminal device or outputs the measurement information used to calculate the position coordinates of the positioned terminal device, in addition to the need to use the base station corresponding to the positioning measurement In addition to the positioning measurement results, the location coordinates of the base station are also needed.
  • the AI model may be used to measure multiple terminal devices.
  • the AI model may be used to measure multiple terminal devices.
  • X base stations are selected from M base stations based on the first path arrival time of the channel, due to the different locations of different terminal equipment, the first path arrival time of the channel between different terminal equipment and the base station will be different. If different, different X base stations will be selected for different terminal devices.
  • the terminal device when the AI model is deployed on the base station side, the terminal device will determine the positioning measurement results corresponding to the M base stations participating in the positioning measurement. After that, X base stations will be selected from M base stations, and the positioning measurement results of the X base stations will be sent to the base station where the AI model is deployed, so that the positioning measurement results corresponding to the X base stations can be determined as the input of the AI model.
  • the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is,
  • the input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements.
  • the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • FIG. 10a is a schematic flowchart of an AI model input determination method provided by an embodiment of the present disclosure, which is applied to a base station. As shown in Figure 10a, the AI model input determination method may include the following steps:
  • Step 1001a Obtain positioning measurement results corresponding to a preset number X base stations, where the preset number X is less than the total number M of all base stations participating in the positioning measurement; where X and M are both positive integers.
  • Step 1002a Determine the positioning measurement results corresponding to the X base stations as the input of the AI model.
  • steps 1001a to 1002a please refer to the description of the above embodiment.
  • the base station that performs the method may be a base station that deploys an AI model.
  • the base station when the AI model is deployed on the base station side, the base station will first obtain the positioning measurement results corresponding to the preset number X base stations, where the preset The number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • FIG. 10b is a schematic flow chart of an AI model input determination method provided by an embodiment of the present disclosure, applied to a base station, where the AI model is deployed on the base station, but positioning measurement is performed by the terminal device, and, as shown in Figure 10b , the input determination method of the AI model may include the following steps:
  • Step 1001b In response to the positioning measurement results measured by the terminal device, obtain positioning measurement results corresponding to X base stations sent by the terminal device.
  • Step 1002b Determine the positioning measurement results corresponding to the X base stations as input to the AI model.
  • the base station deployed with the AI model can receive positioning measurement results corresponding to the same X base stations from multiple terminal devices. (At this time, the terminal equipment selects X base stations using the method shown in Figure 7 or Figure 8 above). Based on this, the AI model can store the location coordinates of the X base stations.
  • the AI model can store the location coordinates of the X base stations.
  • the positioning measurement results are used as the input of the AI model, which can cause the AI model to output the position coordinates of the positioned terminal device or output measurement information used to calculate the position coordinates of the positioned terminal device.
  • the base station deploying the AI model may also receive positioning measurements corresponding to different X base stations from multiple terminal devices. Result (at this time, the terminal equipment selects X base stations using the method shown in Figure 9 above). Based on this, when using an AI model to position multiple different terminal devices, the base station deploying the AI model should obtain the position coordinates of the The coordinates, together with the positioning measurement results corresponding to the measurement information.
  • the method for the base station deploying the AI model to obtain the position coordinates of the X base stations currently determined by the terminal device may be: obtaining the corresponding position coordinates from the X base stations respectively, or obtaining the X base stations from the terminal device. location coordinates.
  • step 1001b to step 1002b please refer to the description of the above embodiment.
  • the base station when the AI model is deployed on the base station side, the base station will first obtain the positioning measurement results corresponding to the preset number X base stations, where the preset The number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 10c is a schematic flow chart of an AI model input determination method provided by an embodiment of the present disclosure, applied to a base station, where the AI model is deployed on the base station, and the positioning measurement is obtained by the base station measurement, and, as shown in Figure 10c , the input determination method of the AI model may include the following steps:
  • Step 1001c In response to the positioning measurement results measured by the base station, obtain positioning measurement results sent by other base stations that participate in the positioning measurement and do not deploy the AI model.
  • the base station that deploys the AI model after the base station that deploys the AI model obtains the positioning measurement results sent by other base stations that participate in positioning measurement and does not deploy the AI model, it then determines its own corresponding positioning measurement result, that is, The positioning measurement results corresponding to all M base stations participating in the positioning measurement can be determined.
  • Step 1002c Select X base stations from all M base stations participating in positioning measurement.
  • the base station deployed with the AI model can select the same X base stations from all M base stations for different terminal devices. .
  • the same X base stations can be selected from all M base stations.
  • the base station deployed with the AI model may select different X base stations from all M base stations for different terminal devices.
  • the base station deployed with the AI model may select different X base stations from all M base stations for different terminal devices.
  • different X base stations may be selected from all M base stations.
  • Step 1003c Obtain positioning measurement results corresponding to X base stations.
  • Step 1004c Determine the positioning measurement results corresponding to the X base stations as the input of the AI model.
  • steps 1001c-1004c please refer to the description of the above embodiment.
  • the base station when the AI model is deployed on the base station side, the base station will first obtain the positioning measurement results corresponding to the preset number X base stations, where the preset The number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • FIG 11 is a schematic flow chart of an AI model input determination method provided by an embodiment of the present disclosure, applied to a base station, where the AI model is deployed on the base station, and the positioning measurement is obtained by the base station measurement, and, as shown in Figure 11 , the input determination method of the AI model may include the following steps:
  • Step 1101 In response to the positioning measurement results measured by the base station, obtain positioning measurement results sent by other base stations that participate in the positioning measurement and do not deploy the AI model.
  • Step 1102 Select X base stations from all M base stations participating in positioning measurement.
  • Step 1103. Determine the value of X.
  • determining the value of X includes:
  • the value of X is determined based on the agreement.
  • Step 1104 Arrange the M base stations in order of their positions.
  • Step 1105 Select X base stations uniformly or non-uniformly from the arranged M base stations.
  • Step 1106 Determine the positioning measurement results corresponding to the X base stations as the input of the AI model.
  • steps 1101-1106 please refer to the description of the above embodiment.
  • the AI model may be used to measure multiple terminal devices, where the multiple terminal devices are all measured based on the measurement results corresponding to the same M base stations. And, in one embodiment of the present disclosure, for the embodiment of Figure 11, different terminal devices can select the same X base stations.
  • the AI model outputs the position coordinates of the positioned terminal device or outputs the measurement information used to calculate the position coordinates of the positioned terminal device, in addition to the positioning measurement results corresponding to the base stations participating in the positioning measurement, it is necessary to use , it is also necessary to use the location coordinates of the base stations. Based on this, since the X base stations selected by different terminal devices are the same, the location coordinates of the X base stations can be stored in the AI model. Therefore, when using the AI model to When each terminal device performs positioning, it is no longer necessary to input the location coordinates of X base stations, but only the positioning measurement results corresponding to X base stations, which reduces the input dimension and reduces signaling overhead.
  • the base station when the AI model is deployed on the base station side, the base station will first obtain the positioning measurement results corresponding to the preset number X base stations, where the preset The number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 12 is a schematic flow chart of an AI model input determination method provided by an embodiment of the present disclosure, applied to a base station, where the AI model is deployed on the base station, and positioning measurements are performed by the base station, and, as shown in Figure 12,
  • the input determination method of the AI model may include the following steps:
  • Step 1201 In response to the positioning measurement results measured by the base station, obtain positioning measurement results sent by other base stations that participate in the positioning measurement and do not deploy the AI model.
  • Step 1202 Determine a base station set, where the base station set includes X base stations among the M base stations.
  • determining the base station set may include:
  • Step 1203 Determine X base stations based on the base station set.
  • Step 1204 Obtain positioning measurement results corresponding to X base stations.
  • Step 1205 Determine the positioning measurement results corresponding to the X base stations as the input of the AI model.
  • steps 1201-1205 please refer to the description of the above embodiment.
  • the AI model may be used to measure multiple terminal devices, where the multiple terminal devices are all measured based on the measurement results corresponding to the same M base stations. And, in one embodiment of the present disclosure, for the embodiment of Figure 12, different terminal devices can select the same X base stations.
  • the AI model outputs the position coordinates of the positioned terminal device or outputs the measurement information used to calculate the position coordinates of the positioned terminal device, in addition to the positioning measurement results corresponding to the base stations participating in the positioning measurement, it is necessary to use , it is also necessary to use the location coordinates of the base stations. Based on this, since the X base stations selected by different terminal devices are the same, the location coordinates of the X base stations can be stored in the AI model. Therefore, when using the AI model to When each terminal device performs positioning, it is no longer necessary to input the location coordinates of X base stations, but only the positioning measurement results corresponding to X base stations, which reduces the input dimension and reduces signaling overhead.
  • the base station when the AI model is deployed on the base station side, the base station will first obtain the positioning measurement results corresponding to the preset number X base stations, where the preset The number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • FIG 13 is a schematic flow chart of an AI model input determination method provided by an embodiment of the present disclosure, applied to a base station, where the AI model is deployed on the base station, and positioning measurements are performed by the base station, and, as shown in Figure 13,
  • the input determination method of the AI model may include the following steps:
  • Step 1301 In response to the positioning measurement results measured by the base station, obtain positioning measurement results sent by other base stations that participate in the positioning measurement and do not deploy the AI model.
  • Step 1302 Determine the value of X.
  • Step 1303 Select X base stations from the M base stations based on the arrival time of the first path of the channel between the M base stations and the terminal equipment.
  • X base stations are selected from the M base stations based on the first path arrival time of the channel between the M base stations and the terminal equipment, including:
  • Step 1304 Obtain positioning measurement results corresponding to X base stations.
  • Step 1305 Determine the location coordinates of the selected X base stations.
  • Step 1306 Determine the positioning measurement results corresponding to the X base stations and the position coordinates of the X base stations as inputs to the AI model.
  • steps 1301-1306 please refer to the description of the above embodiment.
  • the base station when the AI model is deployed on the base station side, the base station will first obtain the positioning measurement results corresponding to the preset number X base stations, where the preset The number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 14a is a schematic flow chart of an AI model input determination method provided by an embodiment of the present disclosure, applied to a base station, where the AI model is deployed on the terminal device, and positioning measurement is performed by the base station side, and, as shown in Figure 14 , the input determination method of the AI model may include the following steps:
  • Step 1401a In response to the positioning measurement result measured by the base station, send the positioning measurement result measured by the base station to the terminal device.
  • the base station that performs the method may be any base station participating in positioning measurement.
  • step 1401a For relevant introduction to step 1401a, please refer to the description of the above embodiment.
  • the base station participating in the positioning measurement will send the positioning measurement result obtained by its measurement to the terminal device.
  • This allows the terminal device to select the positioning measurement results of X base stations from all M base stations participating in positioning measurement as input to the AI model.
  • the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is,
  • the input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements.
  • the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 14b is a schematic flowchart of an AI model input determination method provided by an embodiment of the present disclosure, applied to a first network device, where the first network device is a non-terminal device and a non-base station device, and the AI model is deployed On the first network device, and as shown in Figure 14b, the input determination method of the AI model may include the following steps:
  • Step 1401b Obtain positioning measurement results corresponding to a preset number of X base stations.
  • the above-mentioned first network device may be, for example, a positioning server.
  • Step 1402b Determine the positioning measurement results corresponding to the X base stations as input to the AI model.
  • steps 1401b-1402b please refer to the description of the above embodiment.
  • the first network device when the AI model is deployed on the first network device side, the first network device will first obtain the positioning measurements corresponding to the preset number X base stations. As a result, the preset number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 14c is a schematic flowchart of an input determination method for an AI model provided by an embodiment of the present disclosure, applied to a first network device, where the first network device is a non-terminal device and a non-base station device, where the AI The model is deployed on the first network device, and positioning measurements are performed by the base station or terminal device, and, as shown in Figure 14c, the input determination method of the AI model may include the following steps:
  • Step 1401c In response to the positioning measurement results measured by the base station or the terminal device, obtain the positioning measurement results corresponding to the M base stations sent by the terminal device or the M base stations.
  • Step 1402c Select X base stations from M base stations.
  • Step 1403c Obtain positioning measurement results corresponding to X base stations.
  • Step 1404c Determine the positioning measurement results corresponding to the X base stations as the input of the AI model.
  • steps 1401c-1404c please refer to the description of the above embodiment.
  • the first network device when the AI model is deployed on the first network device side, the first network device will first obtain the positioning measurements corresponding to the preset number X base stations. As a result, the preset number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 14d is a schematic flowchart of an input determination method for an AI model provided by an embodiment of the present disclosure, applied to a first network device, where the first network device is a non-terminal device and a non-base station device, where the AI The model is deployed on the first network device, and positioning measurements are performed by the base station or terminal device, and, as shown in Figure 14h, the input determination method of the AI model may include the following steps:
  • Step 1401d In response to the positioning measurement results measured by the base station or the terminal device, obtain the positioning measurement results corresponding to the M base stations sent by the terminal device or the M base stations.
  • Step 1402d Determine the value of X.
  • Step 1403d Arrange the M base stations in order of their positions.
  • Step 1404d Select X base stations uniformly or non-uniformly from the arranged M base stations.
  • Step 1405d Obtain positioning measurement results corresponding to X base stations.
  • Step 1406d Determine the positioning measurement results corresponding to the X base stations as the input of the AI model.
  • steps 1401d-1406d please refer to the description of the above embodiment.
  • the first network device when the AI model is deployed on the first network device side, the first network device will first obtain the positioning measurements corresponding to the preset number X base stations. As a result, the preset number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 14e is a schematic flowchart of an input determination method for an AI model provided by an embodiment of the present disclosure, applied to a first network device, where the first network device is a non-terminal device and a non-base station device, where the AI The model is deployed on the first network device, and positioning measurements are performed by the base station or terminal device, and, as shown in Figure 14i, the input determination method of the AI model may include the following steps:
  • Step 1401e In response to the positioning measurement results measured by the base station or the terminal device, obtain the positioning measurement results corresponding to the M base stations sent by the terminal device or the M base stations.
  • Step 1402e Determine a base station set, where the base station set may include X base stations among the M base stations.
  • Step 1403e Determine X base stations based on the base station set.
  • Step 1404e Obtain positioning measurement results corresponding to X base stations.
  • Step 1405e Determine the positioning measurement results corresponding to the X base stations as input to the AI model.
  • steps 1401e-1405e please refer to the description of the above embodiment.
  • the first network device when the AI model is deployed on the first network device side, the first network device will first obtain the positioning measurements corresponding to the preset number X base stations. As a result, the preset number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 14f is a schematic flowchart of an input determination method for an AI model provided by an embodiment of the present disclosure, applied to a first network device, where the first network device is a non-terminal device and a non-base station device, where the AI The model is deployed on the first network device, and positioning measurements are performed by the base station or terminal device, and, as shown in Figure 14f, the input determination method of the AI model may include the following steps:
  • Step 1401f In response to the positioning measurement results measured by the base station or the terminal device, obtain the positioning measurement results corresponding to the M base stations sent by the terminal device or the M base stations.
  • Step 1402f Determine the value of X.
  • Step 1403f Select X base stations from the M base stations based on the arrival time of the first path of the channel between the M base stations and the terminal equipment.
  • Step 1404f Obtain positioning measurement results corresponding to X base stations.
  • Step 1405f Determine the location coordinates of the selected X base stations.
  • Step 1406f Determine the positioning measurement results corresponding to the X base stations and the position coordinates of the X base stations as inputs to the AI model.
  • steps 1401f-1406f please refer to the description of the above embodiment.
  • the first network device when the AI model is deployed on the first network device side, the first network device will first obtain the positioning measurements corresponding to the preset number X base stations. As a result, the preset number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • Figure 15 is a schematic structural diagram of an AI model input determination device provided by an embodiment of the present disclosure. It is configured in a terminal device. The AI model is deployed on the terminal device. As shown in Figure 15, the device may include:
  • a transceiver module used to obtain positioning measurement results corresponding to a preset number of base stations X, where the preset number
  • a processing module configured to determine the positioning measurement results corresponding to the X base stations as input to the AI model.
  • the terminal device when the AI model is deployed on the terminal device side, the terminal device will first obtain the positioning measurement results corresponding to the preset number X base stations, where, The preset number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • the positioning measurement results include at least one of the following:
  • Measured power obtained by measuring the reference signal transmitted between the base station and the located terminal device.
  • the transceiver module in response to the AI model being deployed on a terminal device or a base station, and the positioning measurement result being measured by the terminal device, is also configured to :
  • the transceiver module in response to the AI model being deployed on the terminal device and the positioning measurement result being measured by the base station, the transceiver module is also used to:
  • the processing module in response to the AI model being deployed on the base station, the processing module is also used to:
  • the positioning measurement results corresponding to the X base stations are sent to the base station where the AI model is deployed as input to the AI model.
  • the X base stations selected by the terminal device from the M base stations are combined with the X base stations selected by other terminal devices. same. .
  • the transceiver module is also used to:
  • X base stations are selected uniformly or non-uniformly from the arranged M base stations.
  • the transceiver module is also used to:
  • the value of X is determined based on the configuration of the base station.
  • the transceiver module is also used to:
  • the base station set includes X base stations among the M base stations;
  • the X base stations are determined based on the set of base stations.
  • the transceiver module is also used to:
  • the set of base stations is determined based on the configuration of the base stations.
  • the X base stations selected by different terminal devices are different.
  • the transceiver module is also used to:
  • X base stations are selected from the M base stations based on the arrival time of the first path of the channel between the M base stations and the terminal equipment.
  • the transceiver module is also used to:
  • the device is also used for:
  • the processing module is also used to:
  • the positioning measurement results corresponding to the X base stations and the position coordinates of the X base stations are determined as inputs to the AI model.
  • Figure 16 is a schematic structural diagram of an AI model input determination device provided by an embodiment of the present disclosure. It is configured in a base station. The AI model is deployed on the base station. As shown in Figure 16, the device may include:
  • a transceiver module used to obtain positioning measurement results corresponding to a preset number of base stations X, where the preset number
  • a processing module configured to determine the positioning measurement results corresponding to the X base stations as input to the AI model.
  • the base station when the AI model is deployed on the base station side, the base station will first obtain positioning measurement results corresponding to a preset number of X base stations, where the preset The number X is less than the total number M of all base stations participating in positioning measurements; It can be seen from this that in this disclosure, the positioning measurement results corresponding to all base stations participating in positioning measurement are not used as the input of the AI model, but the positioning measurement results corresponding to some base stations participating in positioning measurement are used as the input of the AI model, that is, The input of the AI model has been streamlined, which can significantly reduce the input dimensions of the AI model, reduce the processing burden of the AI model, and reduce storage requirements. Moreover, when the input of the AI model is transmitted over the air interface, the signaling burden can also be reduced.
  • the present disclosure provides a lightweight AI model that does not affect positioning accuracy and has low complexity.
  • the positioning measurement results include at least one of the following:
  • Measured power obtained by measuring the reference signal transmitted between the base station and the located terminal device.
  • the transceiver module in response to the AI model being deployed on the base station and the positioning measurement result being measured by the terminal device, is also used to:
  • the transceiver module in response to the AI model being deployed on the base station and the positioning measurement result being measured by the base station, the transceiver module is also used to:
  • the transceiver module is also used to:
  • the base station When the AI model is used to position multiple terminal devices, the base station receives the same or different positioning measurement results corresponding to X base stations from the multiple terminal devices.
  • the transceiver module is also used to:
  • the same or different X base stations are selected from all M base stations for different terminal devices.
  • the transceiver module is also used to:
  • X base stations are selected uniformly or non-uniformly from the arranged M base stations.
  • the transceiver module is also used to:
  • the base station independently determines the value of X.
  • the transceiver module is also used to:
  • the base station set includes X base stations among the M base stations;
  • the X base stations are determined based on the set of base stations.
  • the transceiver module is also used to:
  • the base station independently determines the base station set.
  • the transceiver module is also used to:
  • X base stations are selected from the M base stations based on the arrival time of the first path of the channel between the M base stations and the terminal equipment.
  • the transceiver module is also used to:
  • the device is also used for:
  • the processing module is also used to:
  • the positioning measurement results corresponding to the X base stations and the position coordinates of the X base stations are determined as inputs to the AI model.
  • FIG 17 is a schematic structural diagram of a communication device 1700 provided by an embodiment of the present application.
  • the communication device 1700 may be a network device, a terminal device, a chip, a chip system, or a processor that supports a network device to implement the above method, or a chip, a chip system, or a processor that supports a terminal device to implement the above method. Processor etc.
  • the device can be used to implement the method described in the above method embodiment. For details, please refer to the description in the above method embodiment.
  • Communication device 1700 may include one or more processors 1701.
  • the processor 1701 may be a general-purpose processor or a special-purpose processor, or the like.
  • it can be a baseband processor or a central processing unit.
  • the baseband processor can be used to process communication protocols and communication data.
  • the central processor can be used to control communication devices (such as base stations, baseband chips, terminal equipment, terminal equipment chips, DU or CU, etc.) and execute computer programs. , processing data for computer programs.
  • the communication device 1700 may also include one or more memories 1702, on which a computer program 1704 may be stored.
  • the processor 1701 executes the computer program 1704, so that the communication device 1700 performs the steps described in the above method embodiments. method.
  • the memory 1702 may also store data.
  • the communication device 1700 and the memory 1702 can be provided separately or integrated together.
  • the communication device 1700 may also include a transceiver 1705 and an antenna 1706.
  • the transceiver 1705 may be called a transceiver unit, a transceiver, a transceiver circuit, etc., and is used to implement transceiver functions.
  • the transceiver 1705 may include a receiver and a transmitter.
  • the receiver may be called a receiver or a receiving circuit, etc., used to implement the receiving function;
  • the transmitter may be called a transmitter, a transmitting circuit, etc., used to implement the transmitting function.
  • the communication device 1700 may also include one or more interface circuits 1707.
  • the interface circuit 1707 is used to receive code instructions and transmit them to the processor 1701 .
  • the processor 1701 executes the code instructions to cause the communication device 1700 to perform the method described in the above method embodiment.
  • the processor 1701 may include a transceiver for implementing receiving and transmitting functions.
  • the transceiver may be a transceiver circuit, an interface, or an interface circuit.
  • the transceiver circuits, interfaces or interface circuits used to implement the receiving and transmitting functions can be separate or integrated together.
  • the above-mentioned transceiver circuit, interface or interface circuit can be used for reading and writing codes/data, or the above-mentioned transceiver circuit, interface or interface circuit can be used for signal transmission or transfer.
  • the processor 1701 may store a computer program 1703, and the computer program 1703 runs on the processor 1701, causing the communication device 1700 to perform the method described in the above method embodiment.
  • the computer program 1703 may be solidified in the processor 1701, in which case the processor 1701 may be implemented by hardware.
  • the communication device 1700 may include a circuit, which may implement the functions of sending or receiving or communicating in the foregoing method embodiments.
  • the processor and transceiver described in this application can be implemented in integrated circuits (ICs), analog ICs, radio frequency integrated circuits RFICs, mixed signal ICs, application specific integrated circuits (ASICs), printed circuit boards ( printed circuit board (PCB), electronic equipment, etc.
  • the processor and transceiver can also be manufactured using various IC process technologies, such as complementary metal oxide semiconductor (CMOS), n-type metal oxide-semiconductor (NMOS), P-type Metal oxide semiconductor (positive channel metal oxide semiconductor, PMOS), bipolar junction transistor (BJT), bipolar CMOS (BiCMOS), silicon germanium (SiGe), gallium arsenide (GaAs), etc.
  • CMOS complementary metal oxide semiconductor
  • NMOS n-type metal oxide-semiconductor
  • PMOS P-type Metal oxide semiconductor
  • BJT bipolar junction transistor
  • BiCMOS bipolar CMOS
  • SiGe silicon germanium
  • GaAs gallium arsenide
  • the communication device described in the above embodiments may be a network device or a terminal device, but the scope of the communication device described in this application is not limited thereto, and the structure of the communication device may not be limited by FIG. 17 .
  • the communication device may be a stand-alone device or may be part of a larger device.
  • the communication device may be:
  • the IC collection may also include storage components for storing data and computer programs;
  • the communication device may be a chip or a chip system
  • the schematic structural diagram of the chip shown in FIG. 18 refer to the schematic structural diagram of the chip shown in FIG. 18 .
  • the chip shown in Figure 18 includes a processor 1801 and an interface 1802.
  • the number of processors 1801 may be one or more, and the number of interfaces 1802 may be multiple.
  • the chip also includes a memory 1803, which is used to store necessary computer programs and data.
  • This application also provides a readable storage medium on which instructions are stored. When the instructions are executed by a computer, the functions of any of the above method embodiments are implemented.
  • This application also provides a computer program product, which, when executed by a computer, implements the functions of any of the above method embodiments.
  • the above embodiments it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof.
  • software it may be implemented in whole or in part in the form of a computer program product.
  • the computer program product includes one or more computer programs.
  • the computer program When the computer program is loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part.
  • the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.
  • the computer program may be stored in or transferred from one computer-readable storage medium to another, for example, the computer program may be transferred from a website, computer, server, or data center Transmission to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) means.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more available media integrated.
  • the usable media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVD)), or semiconductor media (e.g., solid state disks, SSD)) etc.
  • magnetic media e.g., floppy disks, hard disks, magnetic tapes
  • optical media e.g., high-density digital video discs (DVD)
  • DVD digital video discs
  • semiconductor media e.g., solid state disks, SSD
  • At least one in this application can also be described as one or more, and the plurality can be two, three, four or more, which is not limited by this application.
  • the technical feature is distinguished by “first”, “second”, “third”, “A”, “B”, “C” and “D”, etc.
  • the technical features described in “first”, “second”, “third”, “A”, “B”, “C” and “D” are in no particular order or order.
  • the corresponding relationships shown in each table in this application can be configured or predefined.
  • the values of the information in each table are only examples and can be configured as other values, which are not limited by this application.
  • the corresponding relationships shown in some rows may not be configured.
  • appropriate deformation adjustments can be made based on the above table, such as splitting, merging, etc.
  • the names of the parameters shown in the titles of the above tables may also be other names understandable by the communication device, and the values or expressions of the parameters may also be other values or expressions understandable by the communication device.
  • other data structures can also be used, such as arrays, queues, containers, stacks, linear lists, pointers, linked lists, trees, graphs, structures, classes, heaps, hash tables or hash tables. wait.
  • Predefinition in this application can be understood as definition, pre-definition, storage, pre-storage, pre-negotiation, pre-configuration, solidification, or pre-burning.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本公开提出一种AI模型的输入确定方法/装置/设备/存储介质，属于通信技术领域。该方法包括：终端设备先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；其中，X和M均为正整数；将X个基站对应的定位测量结果确定为所述AI模型的输入。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。

Description

一种人工智能AI模型的输入确定方法/装置/设备 技术领域
本公开涉及通信技术领域，尤其涉及一种AI模型的输入确定方法/装置/设备及存储介质。
背景技术
在新空口(NR，New Radio)系统中，引入了基于人工智能(Artificial Intelligent，AI)模型的定位，以提高定位精度。
相关技术中，在基于AI模型定位时，会将参与定位测量的所有基站对应的定位测量结果(如冲击响应和/或测量功率)拼接作为AI模型的输入，以使得AI模型输出被定位终端设备的位置坐标或用于计算被定位终端设备的位置坐标的测量信息(如参考信号接收功率(Reference Signal Receiving Power，RSRP))，从而实现高精度的定位功能。
但是，相关技术中，AI模型的输入维度非常大，会给AI模型的处理带来较大的负担，同时对存储的要求也非常大。以及，如果AI模型的输入需要在空口中传输(如需要从基站传输至终端设备，或者由终端设备传输至基站)，也会带来额外的信令负担。
发明内容
本公开提出的AI模型的输入确定方法/装置/设备及存储介质，以解决相关技术的方法会给AI模型的处理带来较大的负担、对存储的要求非常大以及带来额外的信令负担的技术问题。
第一方面，本公开实施例提供一种AI模型的输入确定方法，由终端设备执行，包括：
获取预设数量X个基站对应的定位测量结果，其中，所述预设数量X小于参与定位测量的所有基站的总数量M；其中，X和M均为正整数；
将所述X个基站对应的定位测量结果确定为所述AI模型的输入。
本公开中，当AI模型部署于终端设备侧时，终端设备会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
第二方面，本公开实施例提供一种AI模型的输入确定方法，由基站执行，包括：
获取预设数量X个基站对应的定位测量结果，其中，所述预设数量X小于参与定位测量的所有基站的总数量M；其中，X和M均为正整数；
将所述X个基站对应的定位测量结果确定为所述AI模型的输入。
第三方面，本公开实施例提供一种AI模型的输入确定装置，该装置被配置于终端设备中，包括：
收发模块，用于获取预设数量X个基站对应的定位测量结果，其中，所述预设数量X小于参与定位测量的所有基站的总数量M；其中，X和M均为正整数；
处理模块，用于将所述X个基站对应的定位测量结果确定为所述AI模型的输入。
第四方面，本公开实施例提供一种AI模型的输入确定装置，该装置被配置于基站中， 包括：
收发模块，用于获取预设数量X个基站对应的定位测量结果，其中，所述预设数量X小于参与定位测量的所有基站的总数量M；其中，X和M均为正整数；
处理模块，用于将所述X个基站对应的定位测量结果确定为所述AI模型的输入。
第五方面，本公开实施例提供一种通信装置，该通信装置包括处理器，当该处理器调用存储器中的计算机程序时，执行上述第一方面所述的方法。
第六方面，本公开实施例提供一种通信装置，该通信装置包括处理器，当该处理器调用存储器中的计算机程序时，执行上述第二方面所述的方法。
第七方面，本公开实施例提供一种通信装置，该通信装置包括处理器和存储器，该存储器中存储有计算机程序；所述处理器执行该存储器所存储的计算机程序，以使该通信装置执行上述第一方面所述的方法。
第八方面，本公开实施例提供一种通信装置，该通信装置包括处理器和存储器，该存储器中存储有计算机程序；所述处理器执行该存储器所存储的计算机程序，以使该通信装置执行上述第二方面所述的方法。
第九方面，本公开实施例提供一种通信装置，该装置包括处理器和接口电路，该接口电路用于接收代码指令并传输至该处理器，该处理器用于运行所述代码指令以使该装置执行上述第一方面所述的方法。
第十方面，本公开实施例提供一种通信装置，该装置包括处理器和接口电路，该接口电路用于接收代码指令并传输至该处理器，该处理器用于运行所述代码指令以使该装置执行上述第二方面所述的方法。
第十一方面，本公开实施例提供一种通信系统，该系统包括第三方面所述的通信装置至第四方面所述的通信装置，或者，该系统包括第五方面所述的通信装置至第六方面所述的通信装置，或者，该系统包括第七方面所述的通信装置至第八方面所述的通信装置，或者，该系统包括第九方面所述的通信装置至第十方面所述的通信装置。
第十二方面，本发明实施例提供一种计算机可读存储介质，用于储存为上述网络设备所用的指令，当所述指令被执行时，使所述终端设备执行上述第一方面至第二方面的任一方面所述的方法。
第十三方面，本发明实施例提供一种计算机可读存储介质，用于储存为上述网络设备所用的指令，当所述指令被执行时，使所述终端设备执行上述第一方面至第二方面的任一方面所述的方法。
第十四方面，本公开还提供一种包括计算机程序的计算机程序产品，当其在计算机上运行时，使得计算机执行上述第一方面至第二方面的任一方面所述的方法。
第十五方面，本公开提供一种芯片系统，该芯片系统包括至少一个处理器和接口，用于支持网络设备实现第一方面至第二方面的任一方面所述的方法所涉及的功能，例如，确定或处理上述方法中所涉及的数据和信息中的至少一种。在一种可能的设计中，所述芯片系统还包括存储器，所述存储器，用于保存源辅节点必要的计算机程序和数据。该芯片系统，可以由芯片构成，也可以包括芯片和其他分立器件。
第十六方面，本公开提供一种计算机程序，当其在计算机上运行时，使得计算机执行上述第一方面至第二方面的任一方面所述的方法。
附图说明
本公开上述的和/或附加的方面和优点从下面结合附图对实施例的描述中将变得明显和容易理解，其中：
图1为本公开实施例提供的一种通信系统的架构示意图；
图2a为本公开一个实施例所提供的AI模型的输入确定方法的流程示意图；
图2b为本公开另一个实施例所提供的AI模型的输入确定方法的流程示意图；
图2c为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图3a为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图3b为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图4a为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图4b为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图5a为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图5b为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图6为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图7为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图8为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图9为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图10a为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图10b为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图10c为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图11为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图12为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图13为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图14a为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图14b为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图14c为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图14d为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图14e为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图14f为本公开又一个实施例所提供的AI模型的输入确定方法的流程示意图；
图15为本公开一个实施例所提供的AI模型的输入确定装置的结构示意图；
图16为本公开另一个实施例所提供的AI模型的输入确定装置的结构示意图；
图17为本公开一个实施例所提供的一种通信装置的结构示意图；
图18为本公开一个实施例所提供的芯片的结构示意图。
具体实施方式
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本公开实施例相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开实施例的一些方面相一致的装置和方法的例子。
在本公开实施例使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本公开实施例。在本公开实施例和所附权利要求书中所使用的单数形式的“一种”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。还应当理解，本文中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。
应当理解，尽管在本公开实施例可能采用术语第一、第二、第三等来描述各种信息，但这些信息不应限于这些术语。这些术语仅用来将同一类型的信息彼此区分开。例如，在不脱离本公开实施例范围的情况下，第一信息也可以被称为第二信息，类似地，第二信息也可以被称为第一信息。取决于语境，如在此所使用的词语“如果”及“若”可以被解释成为“在……时”或“当……时”或“响应于确定”。
为了便于理解，首先介绍本申请涉及的术语。
1、人工智能(Artificial Intelligent，AI)
AI是研究、开发用于模拟、延伸和扩展人的智能的理论、方法、技术及应用系统的一门新的技术科学。AI可以执行复杂的任务，且在解决任务时无需人工干预。因此，被应用于各行各业。
为了更好的理解本公开实施例公开的一种AI模型的输入确定方法，下面首先对本公开实施例适用的通信系统进行描述。
下面详细描述本公开的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的要素。下面通过参考附图描述的实施例是示例性的，旨在用于解释本公开，而不能理解为对本公开的限制。
请参见图1，图1为本公开实施例提供的一种通信系统的架构示意图。该通信系统可包括但不限于一个网络设备和一个终端设备，图1所示的设备数量和形态仅用于举例并不构成对本公开实施例的限定，实际应用中可以包括两个或两个以上的网络设备，两个或两个以上的终端设备。图1所示的通信系统以包括一个网络设备11、一个终端设备12为例。
需要说明的是，本公开实施例的技术方案可以应用于各种通信系统。例如：长期演进(long term evolution，LTE)系统、第五代(5th generation，5G)移动通信系统、5G新空口(new radio，NR)系统，或者其他未来的新型移动通信系统等。
本公开实施例中的网络设备11是网络侧的一种用于发射或接收信号的实体。例如，网络设备11可以为演进型基站(evolved NodeB，eNB)、发送接收点(transmission reception point，TRP)、NR系统中的下一代基站(next generation NodeB，gNB)、其他未来移动通信系统中的基站或无线保真(wireless fidelity，WiFi)系统中的接入节点等。本公开的实施例对网络设备所采用的具体技术和具体设备形态不做限定。本公开实施例提供的网络设备可以是由集中单元(central unit，CU)与分布式单元(distributed unit，DU)组成的，其中，CU也可以称为控制单元(control unit)，采用CU-DU的结构可以将网络设备，例如基站的协议层拆分开，部分协议层的功能放在CU集中控制，剩下部分或全部协议层的功能分布在DU中，由CU集中控制DU。
本公开实施例中的终端设备12是用户侧的一种用于接收或发射信号的实体，如手机。终端设备也可以称为终端设备(terminal)、用户设备(user equipment，UE)、移动台(mobile station，MS)、移动终端设备(mobile terminal，MT)等。终端设备可以是具备通信功能的汽车、智能汽车、手机(mobile phone)、穿戴式设备、平板电脑(Pad)、带无线收发功能的电脑、虚拟现实(virtual reality，VR)终端设备、增强现实(augmented reality，AR)终端设备、工业控制(industrial control)中的无线终端设备、无人驾驶(self-driving)中的无线终端设备、远程手术(remote medical surgery)中的无线终端设备、智能电网(smart grid)中的无线终端设备、运输安全(transportation safety)中的无线终端设备、智慧城市(smart city)中的无线终端设备、智慧家庭(smart home)中的无线终端设备等等。本公开的实施例对终端设备所采用的具体技术和具体设备形态不做限定。
图2a为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于终端设备，以及，如图2a所示，该AI模型的输入确定方法可以包括以下步骤：
步骤201a、获取预设数量X个基站对应的定位测量结果。
其中，在本公开的一个实施例之中，该定位测量结果可以包括以下至少一种：
通过测量基站与被定位终端设备之间的信道所得的冲击响应；
通过测量基站与被定位终端设备之间传输的参考信号所得的测量功率。
需要说明的是，通常而言，在定位终端设备时，会有多个基站来参与定位测量。其中，在本公开的一个实施例之中，该预设数量X小于参与定位测量的所有基站的总数量M；其 中，X和M均为正整数。
进一步地，在本公开的一个实施例之中，上述的定位测量结果可以是由基站执行测量所得，也可以是由终端设备执行测量所得，以及，在AI模型部署在终端设备的前提下，当定位测量结果的测量执行主体不同时，本步骤中的“获取预设数量X个基站对应的定位测量结果”的方法也会有所不同，其中，关于该部分内容会在后续实施例进行详细介绍。
步骤202a、将X个基站对应的定位测量结果确定为AI模型的输入。
在本公开的一个实施例之中，通过向AI模型输入X个基站对应的定位测量结果，可以使得AI模型输出被定位终端设备的位置坐标或用于计算被定位终端设备的位置坐标的测量信息(如RSRP)，以此来实现高精度的定位功能。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于终端设备侧时，终端设备会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
进一步地，需要说明的是，在实际的应用场景中，当AI模型部署在终端设备上时，定位测量结果的测量执行端可以是终端设备，也可以是基站。基于此，后续实施例分别基于AI模型的部署端与定位测量结果的测量执行端在同一侧时或不在同一侧来对本公开的方法进行具体介绍。
图2b为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于终端设备，其中，本实施例中AI模型部署在终端设备上，且定位测量由终端设备执行，以及，如图2b所示，该AI模型的输入确定方法可以包括以下步骤：
步骤201b、响应于定位测量结果由终端设备测量所得，确定测量所得的M个基站对应的定位测量结果。
其中，关于终端设备如何测量得到定位测量结果的相关介绍可以参考现有技术的描述。
步骤202b、从M个基站中选择X个基站。
其中，在本公开的一个实施例之中，终端设备可以从M个基站中均匀或非均匀地选择出X个基站，以及，关于终端设备具体如何从M个基站中选择出X个基站的详细方法会在后续实施例进行描述。怎么理解均匀？
步骤203b、获取X个基站对应的定位测量结果。
步骤204b、将X个基站对应的定位测量结果确定为AI模型的输入。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于终端设备侧时，终端设备会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图2c为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于终端 设备，其中，AI模型部署在终端设备上，但定位测量由基站执行，以及，如图2c所示，该AI模型的输入确定方法可以包括以下步骤：
步骤201c、获取M个基站发送的对应的定位测量结果。
其中，在本公开的一个实施例之中，当参与定位测量的各个基站测量出其对应的定位测量结果时，各个基站会将其对应的测量结果发送至终端设备，由此终端设备即可获取到参与定位测量的M个基站发送的对应的定位测量结果。
步骤202c、从M个基站中选择X个基站。
步骤203c、获取X个基站对应的定位测量结果。
步骤204c、将X个基站对应的定位测量结果确定为AI模型的输入。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于终端设备侧时，终端设备会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图3a为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于终端设备，其中，AI模型部署在终端设备上，且定位测量由终端设备执行，以及，如图3a所示，该AI模型的输入确定方法可以包括以下步骤：
步骤301a、响应于定位测量结果由终端设备测量所得，确定测量所得的M个基站对应的定位测量结果。
步骤302a、确定X的取值。
其中，在本公开的一个实施例之中，确定X的取值的方法可以包括以下至少一种：
基于协议约定确定X的取值；
基于基站的配置确定X的取值。
具体的，在本公开的一个实施例之中，上述方法中的基站配置的X的取值，可以是基站从X的可能取值集合{X1,X2,X3,X4,…}中选择的一个值，其中，该X的可能取值集合{X1,X2,X3,X4,…}可以是基于协议约定的，X1,X2,X3,X4均为X的可能取值。
以及，在本公开的另一个实施例之中，上述方法中的基站配置的X的取值也可以是基站基于实现自主确定的一个X的取值。
以及，在本公开的一个实施例之中，基站可以根据部署该AI模型的终端设备的能力或者电量等信息来从X的可能取值集合中选择X的取值或者自主确定X的取值。
示例地，在本公开的一个实施例之中，当部署该AI模型的终端设备的能力较强或者电量较大时，则基站选择的X的取值或者自主确定的X的取值可以较大，当部署该AI模型的终端设备的能力较强或者电量较小时，则基站选择的X的取值或者自主确定的X的取值可以较小。
步骤303a、按照M个基站的位置顺序排列M个基站。
其中，在本公开的一个实施例之中，参与定位测量的各个基站均可以将其位置坐标发送至终端设备，以及，终端设备可以基于M个基站的位置坐标对M个基站进行顺序排列，如可以按照从东到西或从南到北等任一方向顺序排列，或者，可以按照距离终端设备由远至近或者由近至远等任一方向顺序排列。
步骤304a、从排列后的M个基站中均匀或非均匀选择出X个基站。
其中，在本公开的一个实施例之中，上述的均匀选择可以为有规律的选择基站。以及，上述的非均匀选择可以为随机选择基站。
示例的，假设参与定位测量的基站一共为18个，则按照该18个基站的位置顺序排列了18个基站之后，可以先对排列后的18个基站进行编号，如编号为1-18。之后，若确定出X的取值为6，则可以均匀地从18个基站中选取编号为{3,6,9,12,15,18}的6个基站，或者，可以非均匀地从18个基站中选取编号为{3,4,9,10,15,16}的6个基站。
步骤305a、获取X个基站对应的定位测量结果。
步骤306a、将X个基站对应的定位测量结果确定为AI模型的输入。
需要说明的是，由于AI模型在输出被定位终端设备的位置坐标或输出用于计算被定位终端设备的位置坐标的测量信息时，除了需要用到参与定位测量的基站对应的定位测量结果外，还需要用到基站的位置坐标，基于此，在定位测量时，若AI模型部署在终端设备上，可以使得同一终端设备在执行不同次的定位测量时，都选择相同的X个基站。则由于终端设备每次定位测量均选择相同的X个基站，可以将该X个基站的位置坐标存储至AI模型中，由此，当利用AI模型对该终端设备进行定位时，可以无需再输入X个基站的位置坐标，而仅输入X个基站对应的定位测量结果，降低了输入维度，且减少了信令开销。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于终端设备侧时，终端设备会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图3b为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于终端设备，其中，AI模型部署在终端设备上，但定位测量由基站执行，以及，如图3b所示，该AI模型的输入确定方法可以包括以下步骤：
步骤301b、响应于定位测量结果由基站测量所得，获取M个基站发送的对应的定位测量结果。
步骤302b、确定X的取值。
步骤303b、按照M个基站的位置顺序排列M个基站。
步骤304b、从排列后的M个基站中均匀或非均匀选择出X个基站。
步骤305b、获取X个基站对应的定位测量结果。
步骤306b、将X个基站对应的定位测量结果确定为AI模型的输入。
其中，关于步骤301b-步骤306b的相关介绍可以参考上述实施例描述。
需要说明的是，由于AI模型在输出被定位终端设备的位置坐标或输出用于计算被定位终端设备的位置坐标的测量信息时，除了需要用到参与定位测量的基站对应的定位测量结果外，还需要用到基站的位置坐标，基于此，在定位测量时，若AI模型部署在终端设备上，可以使得同一终端设备在执行不同次的定位测量时，都选择相同的X个基站。则由于终端设备每次定位测量均选择相同的X个基站时，可以将该X个基站的位置坐标存储至AI模型中，由此，当利用AI模型对该终端设备进行定位时，可以无需再输入X个基站的位置坐标，而仅输入X个基站对应的定位测量结果，降低了输入维度，且减少了信令开销。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于终端设备侧时，终端设备会先获取预设数量X个基站对应的定位测量结果，其中，预设数量 X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图4a为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于终端设备，其中，AI模型部署在终端设备上，且定位测量由终端设备执行，以及，如图4a所示，该AI模型的输入确定方法可以包括以下步骤：
步骤401a、响应于定位测量结果由终端设备测量所得，确定测量所得的M个基站对应的定位测量结果。
步骤402a、确定基站集合，其中，该基站集合中可以包括M个基站中的X个基站。
其中，在本公开的一个实施例之中，确定基站集合的方法包括以下至少一种：
基于协议约定确定基站集合；
基于基站的配置确定基站集合。
具体的，在本公开的一个实施例之中，上述方法中的基站配置的基站集合，可以是基站从备选基站集合{S1(X),S2(X),S3(X),…}中选择的一个集合，其中，该备选基站集合{S1(X),S2(X),S3(X),…}可以是基于协议约定的，S1(X),S2(X),S3(X)均为备选基站集合，S1(X),S2(X),S3(X)中均分别包括有M个基站中的X个基站，且S1(X),S2(X),S3(X)中所包括的X个基站不同。以及，需要说明的是，在本公开的一个实施例之中，不同的备选基站集合中包括的基站的个数可以相同或不同，即S1(X),S2(X),S3(X)中所包括的基站的个数可以相同或不同。
在本公开的另一个实施例之中，上述方法中的基站配置的基站集合也可以是基站基于实现自主确定的一个集合。
以及，需要说明的是，在本公开的一个实施例之中，可以对M个基站进行编号，以及，上述的基站集合中可以是选择出的X个基站的编号。
则示例的，在本公开的一个实施例之中，假设参与定位测量的基站一共为18个，则按照该18个基站的位置顺序排列了18个基站之后，可以先对排列后的18个基站进行编号，如编号为1-18。此时，本步骤中所确定出的基站集合例如可以为{3,4,9,10,15,16}，也即是，基站集合中包括编号为3,4,9,10,15,16的6个基站。
步骤403a、基于基站集合确定X个基站。
在本公开的一个实施例之中，具体是将基站集合中的基站确定为X个基站。
步骤404a、获取X个基站对应的定位测量结果。
步骤405a、将X个基站对应的定位测量结果确定为AI模型的输入。
需要说明的是，由于AI模型在输出被定位终端设备的位置坐标或输出用于计算被定位终端设备的位置坐标的测量信息时，除了需要用到参与定位测量的基站对应的定位测量结果外，还需要用到基站的位置坐标，基于此，在定位测量时，若AI模型部署在终端设备上，可以使得同一终端设备在执行不同次的定位测量时，都选择相同的X个基站。则由于终端设备每次定位测量均选择相同的X个基站是，可以将该X个基站的位置坐标存储至AI模型中，由此，当利用AI模型对该终端设备进行定位时，可以无需再输入X个基站的位置坐标，而仅输入X个基站对应的定位测量结果，降低了输入维度，且减少了信令开销。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于终端设备侧时，终端设备会先获取预设数量X个基站对应的定位测量结果，其中，预设数量 X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图4b为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于终端设备，其中，AI模型部署在终端设备上，但定位测量由基站执行，以及，如图4b所示，该AI模型的输入确定方法可以包括以下步骤：
步骤401b、响应于定位测量结果由基站测量所得，获取M个基站发送的对应的定位测量结果。
步骤402b、确定基站集合，其中，该基站集合中可以包括M个基站中的X个基站。
步骤403b、基于基站集合确定X个基站。
步骤404b、获取X个基站对应的定位测量结果。
步骤405b、将X个基站对应的定位测量结果确定为AI模型的输入。
其中，关于步骤401b-步骤405b的相关介绍可以参考上述实施例描述。
需要说明的是，由于AI模型在输出被定位终端设备的位置坐标或输出用于计算被定位终端设备的位置坐标的测量信息时，除了需要用到参与定位测量的基站对应的定位测量结果外，还需要用到基站的位置坐标，基于此，在定位测量时，若AI模型部署在终端设备上，可以使得同一终端设备在执行不同次的定位测量时，都选择相同的X个基站。则由于终端设备每次定位测量均选择相同的X个基站是，可以将该X个基站的位置坐标存储至AI模型中，由此，当利用AI模型对该终端设备进行定位时，可以无需再输入X个基站的位置坐标，而仅输入X个基站对应的定位测量结果，降低了输入维度，且减少了信令开销。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于终端设备侧时，终端设备会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图5a为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于终端设备，其中，AI模型部署在终端设备上，且定位测量由终端设备执行，以及，如图5a所示，该AI模型的输入确定方法可以包括以下步骤：
步骤501a、响应于定位测量结果由终端设备测量所得，确定测量所得的M个基站对应的定位测量结果。
步骤502a、确定X的取值。
其中，关于步骤502a的详细介绍可以参考上述实施例描述。
步骤503a、基于M个基站与终端设备之间的信道的首径到达时间从M个基站中选择出X个基站。
其中，在本公开的一个实施例之中，上述的基于M个基站与终端设备之间的信道的首径到达时间从M个基站中选择出X个基站可以包括：从M个基站中选择与终端设备之间的 信道的首径到达时间最短的X个基站。
示例的，假设参与定位测量的基站总数是18个，且上述步骤502a中确定出的X的值为6，此时，可以从18个基站中选择与终端设备之间的信道的首径到达时间最短的6个基站。
步骤504a、获取X个基站对应的定位测量结果。
步骤505a、确定选择的X个基站的位置坐标。
其中，在本公开的一个实施例之中，AI模型在输出被定位终端设备的位置坐标或输出用于计算被定位终端设备的位置坐标的测量信息时，除了需要用到参与定位测量的基站对应的定位测量结果外，还需要用到基站的位置坐标。
在此基础上，在定位测量时，若AI模型部署在终端设备侧，由于终端设备可能会发生移动，从而导致终端设备的位置发生变化。基于此，若每次定位测量均是基于信道的首径到达时间从M个基站中选择出X个基站，则由于终端设备的位置发生了变化，会使得不同时刻的定位测量下，该终端设备与各个基站之间的信道的首径到达时间会有所不同，可能会选择出不同的X个基站。此时，为了确保AI模型能够正确输出被定位终端设备的位置坐标或测量信息，则还需要确定出终端设备每次所选择出的X个基站的位置坐标，并连同该X个基站对应的定位测量结果一同输入至AI模型中。
其中，在本公开的一个实施例之中，上述的基站的位置坐标可以利用二维坐标(x,y)表示。
以及，在本公开的一个实施例之中，上述的确定X个基站的位置坐标的方法可以包括：获取由基站发送的该基站的位置坐标。
步骤506a、将X个基站对应的定位测量结果和X个基站的位置坐标确定为AI模型的输入。
在本公开的一个实施例之中，通过向AI模型输入X个基站对应的定位测量结果和X个基站的位置坐标，可以使得AI模型输出被定位终端设备的位置坐标或用于计算被定位终端设备的位置坐标的测量信息(如RSRP)，以此来实现高精度的定位功能。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于终端设备侧时，终端设备会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图5b为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于终端设备，其中，AI模型部署在终端设备上，但定位测量由基站执行，以及，如图5b所示，该AI模型的输入确定方法可以包括以下步骤：
步骤501b、响应于定位测量结果由基站测量所得，获取M个基站发送的对应的定位测量结果。
步骤502b、确定X的取值。
步骤503b、基于M个基站与终端设备之间的信道的首径到达时间从M个基站中选择出X个基站。
步骤504b、获取X个基站对应的定位测量结果。
步骤505b、确定选择的X个基站的位置坐标。
步骤506b、将X个基站对应的定位测量结果和X个基站的位置坐标确定为AI模型的输入。
其中，关于步骤501b-步骤506b的相关介绍可以参考上述实施例描述。
其中，在本公开的一个实施例之中，AI模型在输出被定位终端设备的位置坐标或输出用于计算被定位终端设备的位置坐标的测量信息时，除了需要用到参与定位测量的基站对应的定位测量结果外，还需要用到基站的位置坐标。
在此基础上，在定位测量时，若AI模型部署在终端设备侧，由于终端设备可能会发生移动，从而导致终端设备的位置发生变化。基于此，若每次定位测量均是基于信道的首径到达时间从M个基站中选择出X个基站，则由于终端设备的位置发生了变化，会使得不同时刻的定位测量下，该终端设备与各个基站之间的信道的首径到达时间会有所不同，可能会选择出不同的X个基站。此时，为了确保AI模型能够正确输出被定位终端设备的位置坐标或测量信息，则还需要确定出终端设备每次所选择出的X个基站的位置坐标，并连同该X个基站对应的定位测量结果一同输入至AI模型中。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于终端设备侧时，终端设备会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图6为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于终端设备，其中，AI模型部署在基站上，以及，如图6所示，该AI模型的输入确定方法可以包括以下步骤：
步骤601、响应于定位测量结果由终端设备测量所得，确定测量所得的M个基站对应的定位测量结果，其中，M为参与定位测量的所有基站的总数量，M为正整数。
步骤602、从M个基站中选择出X个基站，X＜M，X为正整数。
步骤603、将X个基站对应的定位测量结果发送至部署了AI模型的基站。
其中，关于步骤601-步骤603的相关介绍可以参考上述实施例描述。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于基站侧时，终端设备会确定出参与定位测量的M个基站对应的定位测量结果，之后，会从M个基站中选择出X个基站，并将该X个基站的定位测量结果发送至部署了AI模型的基站，以便将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图7为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于终端设备，其中，AI模型部署在基站上，但定位测量结果终端设备测量所得，以及，如图7所示，该AI模型的输入确定方法可以包括以下步骤：
步骤701、响应于定位测量结果由终端设备测量所得，确定测量所得的M个基站对应的定位测量结果，其中，M为参与定位测量的所有基站的总数量，M为正整数。
步骤702、确定X的取值。
其中，在本公开的一个实施例之中，确定X的取值的方法可以包括：
基于协议约定确定X的取值；
基于基站的配置确定X的取值。
步骤703、按照M个基站的位置顺序排列M个基站。
步骤704、从排列后的M个基站中均匀或非均匀选择出X个基站。
步骤705、将X个基站对应的定位测量结果发送至部署了AI模型的基站。
其中，关于步骤701-步骤705的相关介绍可以参考上述实施例描述。
需要说明的是，在定位测量时，若AI模型部署在基站侧，则可能会利用该AI模型对多个终端设备均进行测量。在此基础上，由于AI模型在输出被定位终端设备的位置坐标或输出用于计算被定位终端设备的位置坐标的测量信息时，除了需要用到参与定位测量的基站对应的定位测量结果外，还需要用到基站的位置坐标，基于此，当利用AI模型对多个终端设备进行测量时，可以使得各个终端设备选择相同的X个基站。此时，由于不同终端设备选择的X个基站是相同的，则可以将该X个基站的位置坐标存储至AI模型中，由此，当利用AI模型对各个终端设备进行定位时，可以无需再输入X个基站的位置坐标，而仅输入X个基站对应的定位测量结果，降低了输入维度，且减少了信令开销。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于基站侧时，终端设备会确定出参与定位测量的M个基站对应的定位测量结果，之后，会从M个基站中选择出X个基站，并将该X个基站的定位测量结果发送至部署了AI模型的基站，以便将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图8为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于终端设备，其中，AI模型部署在基站上，但定位测量结果终端设备测量所得，以及，如图8所示，该AI模型的输入确定方法可以包括以下步骤：
步骤801、响应于定位测量结果由终端设备测量所得，确定测量所得的M个基站对应的定位测量结果，其中，M为参与定位测量的所有基站的总数量，M为正整数。
步骤802、确定基站集合，其中，该基站集合中包括M个基站中的X个基站。
其中，在本公开的一个实施例之中，确定基站集合的方法可以包括以下至少一种：
基于协议约定确定基站集合；
基于基站的配置确定基站集合。
步骤803、基于基站集合确定X个基站。
步骤804、将X个基站对应的定位测量结果发送至部署了AI模型的基站。
其中，关于步骤801-步骤804的相关介绍可以参考上述实施例描述。
需要说明的是，在定位测量时，若AI模型部署在基站侧，则可能会利用该AI模型对多个终端设备均进行测量。在此基础上，由于AI模型在输出被定位终端设备的位置坐标或输出用于计算被定位终端设备的位置坐标的测量信息时，除了需要用到参与定位测量的基站对应的定位测量结果外，还需要用到基站的位置坐标，基于此，当利用AI模型对多个终端设备进行测量时，可以使得各个终端设备选择相同的X个基站。此时，由于不同终端设备选择的X个基站是相同的，则可以将该X个基站的位置坐标存储至AI模型中，由此，当利用AI模型对各个终端设备进行定位时，可以无需再输入X个基站的位置坐标，而仅输入X 个基站对应的定位测量结果，降低了输入维度，且减少了信令开销。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于基站侧时，终端设备会确定出参与定位测量的M个基站对应的定位测量结果，之后，会从M个基站中选择出X个基站，并将该X个基站的定位测量结果发送至部署了AI模型的基站，以便将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图9为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于终端设备，其中，AI模型部署在基站上，但定位测量结果终端设备测量所得，以及，如图9所示，该AI模型的输入确定方法可以包括以下步骤：
步骤901、响应于定位测量结果由终端设备测量所得，确定测量所得的M个基站对应的定位测量结果，其中，M为参与定位测量的所有基站的总数量，M为正整数。
步骤902、确定X的取值。
步骤903、基于M个基站与终端设备之间的信道的首径到达时间从M个基站中选择出X个基站。
其中，在本公开的一个实施例之中，基于M个基站与终端设备之间的信道的首径到达时间从M个基站中选择出X个基站，包括：
从M个基站中选择与终端设备之间的信道的首径到达时间最短的X个基站。
步骤904、将X个基站对应的定位测量结果发送至部署了AI模型的基站。
其中，关于步骤901-步骤904的相关介绍可以参考上述实施例描述。
其中，在本公开的一个实施例之中，AI模型在输出被定位终端设备的位置坐标或输出用于计算被定位终端设备的位置坐标的测量信息时，除了需要用到参与定位测量的基站对应的定位测量结果外，还需要用到基站的位置坐标。
在此基础上，在定位测量时，若AI模型部署在基站侧，则可能会利用AI模型对多个终端设备均进行测量。此时，若是基于信道的首径到达时间从M个基站中选择出X个基站，由于不同终端设备的位置不同，从而会使得不同终端设备与基站之间的信道的首径到达时间会有所不同，则针对不同终端设备会选择出不同的X个基站。此时，为了确保AI模型能够成功输出各个被定位终端设备的位置坐标或测量信息，还需要确定出每个终端设备所选择出的X个基站的位置坐标，并连同该X个基站对应的定位测量结果一同输入至AI模型中。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于基站侧时，终端设备会确定出参与定位测量的M个基站对应的定位测量结果，之后，会从M个基站中选择出X个基站，并将该X个基站的定位测量结果发送至部署了AI模型的基站，以便将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图10a为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于基站，以及，如图10a所示，该AI模型的输入确定方法可以包括以下步骤：
步骤1001a、获取预设数量X个基站对应的定位测量结果，其中，该预设数量X小于 参与定位测量的所有基站的总数量M；其中，X和M均为正整数。
步骤1002a、将X个基站对应的定位测量结果确定为AI模型的输入。
其中，关于步骤1001a-步骤1002a的相关介绍可以参考上述实施例描述。
以及，在本公开的一个实施例之中，执行该方法的基站可以为部署了AI模型的基站。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于基站侧时，基站会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图10b为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于基站，其中，AI模型部署在基站上，但定位测量由终端设备执行，以及，如图10b所示，该AI模型的输入确定方法可以包括以下步骤：
步骤1001b、响应于定位测量结果由终端设备测量所得，获取终端设备发送的X个基站对应的定位测量结果。
步骤1002b、将X个基站对应的定位测量结果确定为AI模型的输入。
其中，在本公开的一个实施例之中，当AI模型用于对多个终端设备进行定位时，该部署了AI模型的基站可以从多个终端设备接收相同的X个基站对应的定位测量结果(此时终端设备采用如上述图7或图8所示的方法选择X个基站)。基于此，该AI模型中可以存储有该X个基站的位置坐标，则当利用AI模型对多个不同的终端设备进行定位时，可以通过仅将该被定位的终端设备发送的X个基站对应的定位测量结果作为AI模型的输入，即可使得AI模型输出被定位终端设备的位置坐标或输出用于计算被定位终端设备的位置坐标的测量信息。
在本公开的另一个实施例之中，当AI模型用于对多个终端设备进行定位时，该部署了AI模型的基站也可能会从多个终端设备接收不同的X个基站对应的定位测量结果(此时终端设备采用如上述图9所示的方法选择X个基站)。基于此，当利用AI模型对多个不同的终端设备进行定位时，部署了AI模型的基站应当获取被定位的终端设备当前确定出的X个基站的位置坐标，并将该X个基站的位置坐标连同该被定位的终端设备发送的X个基站对应的定位测量结果一起作为AI模型的输入，以使得AI模型输出被定位终端设备的位置坐标或输出用于计算被定位终端设备的位置坐标的测量信息。其中，部署了AI模型的基站获取终端设备当前确定出的X个基站的位置坐标的方法可以为：分别从该X个基站处获取对应的位置坐标，或者，从终端设备处获取该X个基站的位置坐标。
其中，关于步骤1001b-步骤1002b的相关介绍可以参考上述实施例描述。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于基站侧时，基站会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型 的AI模型。
图10c为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于基站，其中，AI模型部署在基站上，且定位测量由基站测量所得，以及，如图10c所示，该AI模型的输入确定方法可以包括以下步骤：
步骤1001c、响应于定位测量结果由基站测量所得，获取参与定位测量的且未部署AI模型的其他基站发送的定位测量结果。
其中，在本公开的一个实施例之中，部署了AI模型的基站获取到参与定位测量的且未部署AI模型的其他基站发送的定位测量结果后，再确定其自身对应的定位测量结果，即可确定出参与定位测量的所有M个基站对应的定位测量结果。
步骤1002c、从参与定位测量的所有M个基站中选择X个基站。
其中，在本公开的一个实施例之中，当AI模型用于对多个终端设备进行定位时，该部署了AI模型的基站针对不同终端设备可以从所有M个基站中选择相同的X个基站。如后续的图11和图12的方法中，可以从所有M个基站中选择相同的X个基站。
在本公开的另一个实施例之中，当AI模型用于对多个终端设备进行定位时，该部署了AI模型的基站针对不同终端设备可能会从所有M个基站中选择出不同的X个基站。如后续的图13的方法中可能会从所有M个基站中选择出不同的X个基站。
步骤1003c、获取X个基站对应的定位测量结果。
步骤1004c、将X个基站对应的定位测量结果确定为AI模型的输入。
其中，关于步骤1001c-1004c的相关介绍可以参考上述实施例描述。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于基站侧时，基站会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图11为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于基站，其中，AI模型部署在基站上，且定位测量由基站测量所得，以及，如图11所示，该AI模型的输入确定方法可以包括以下步骤：
步骤1101、响应于定位测量结果由基站测量所得，获取参与定位测量的且未部署AI模型的其他基站发送的定位测量结果。
步骤1102、从参与定位测量的所有M个基站中选择X个基站。
步骤1103、确定X的取值。
其中，在本公开的一个实施例之中，确定X的取值，包括：
基于协议约定确定X的取值。
步骤1104、按照M个基站的位置顺序排列M个基站。
步骤1105、从排列后的M个基站中均匀或非均匀选择出X个基站。
步骤1106、将X个基站对应的定位测量结果确定为AI模型的输入。
其中，关于步骤1101-1106的相关介绍可以参考上述实施例描述。
需要说明的是，在定位测量时，可能会利用AI模型对多个终端设备均进行测量，其中，该多个终端设备均是基于相同的M个基站对应的测量结果来进行测量。以及，在本公开的一个实施例之中，针对图11的实施例而言，不同终端设备可以选择相同的X个基站。
则在此基础上，由于AI模型在输出被定位终端设备的位置坐标或输出用于计算被定位终端设备的位置坐标的测量信息时，除了需要用到参与定位测量的基站对应的定位测量结果外，还需要用到基站的位置坐标，基于此，由于不同终端设备选择的X个基站是相同的，则可以将该X个基站的位置坐标存储至AI模型中，由此，当利用AI模型对各个终端设备进行定位时，可以无需再输入X个基站的位置坐标，而仅输入X个基站对应的定位测量结果，降低了输入维度，且减少了信令开销。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于基站侧时，基站会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图12为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于基站，其中，AI模型部署在基站上，且定位测量由基站执行，以及，如图12所示，该AI模型的输入确定方法可以包括以下步骤：
步骤1201、响应于定位测量结果由基站测量所得，获取参与定位测量的且未部署AI模型的其他基站发送的定位测量结果。
步骤1202、确定基站集合，其中，基站集合中包括M个基站中的X个基站。
其中，在本公开的一个实施例之中，确定基站集合可以包括：
基于协议约定确定基站集合。
步骤1203、基于基站集合确定X个基站。
步骤1204、获取X个基站对应的定位测量结果。
步骤1205、将X个基站对应的定位测量结果确定为AI模型的输入。
其中，关于步骤1201-1205的相关介绍可以参考上述实施例描述。
需要说明的是，在定位测量时，可能会利用AI模型对多个终端设备均进行测量，其中，该多个终端设备均是基于相同的M个基站对应的测量结果来进行测量。以及，在本公开的一个实施例之中，针对图12的实施例而言，不同终端设备可以选择相同的X个基站。
则在此基础上，由于AI模型在输出被定位终端设备的位置坐标或输出用于计算被定位终端设备的位置坐标的测量信息时，除了需要用到参与定位测量的基站对应的定位测量结果外，还需要用到基站的位置坐标，基于此，由于不同终端设备选择的X个基站是相同的，则可以将该X个基站的位置坐标存储至AI模型中，由此，当利用AI模型对各个终端设备进行定位时，可以无需再输入X个基站的位置坐标，而仅输入X个基站对应的定位测量结果，降低了输入维度，且减少了信令开销。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于基站侧时，基站会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型 的AI模型。
图13为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于基站，其中，AI模型部署在基站上，且定位测量由基站执行，以及，如图13所示，该AI模型的输入确定方法可以包括以下步骤：
步骤1301、响应于定位测量结果由基站测量所得，获取参与定位测量的且未部署AI模型的其他基站发送的定位测量结果。
步骤1302、确定X的取值。
步骤1303、基于M个基站与终端设备之间的信道的首径到达时间从M个基站中选择出X个基站。
其中，在本公开的一个实施例之中，基于M个基站与终端设备之间的信道的首径到达时间从M个基站中选择出X个基站，包括：
从M个基站中选择与终端设备之间的信道的首径到达时间最短的X个基站。
步骤1304、获取X个基站对应的定位测量结果。
步骤1305、确定选择的X个基站的位置坐标。
步骤1306、将X个基站对应的定位测量结果和X个基站的位置坐标确定为AI模型的输入。
其中，关于步骤1301-1306的相关介绍可以参考上述实施例描述。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于基站侧时，基站会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图14a为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于基站，其中，AI模型部署在终端设备上，定位测量由基站侧执行，以及，如图14所示，该AI模型的输入确定方法可以包括以下步骤：
步骤1401a、响应于定位测量结果由基站测量所得，将基站测量所得的定位测量结果发送至终端设备。
在本公开的一个实施例之中，执行该方法的基站可以为参与定位测量的任一基站。
其中，关于步骤1401a的相关介绍可以参考上述实施例描述。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于终端设备侧时，参与定位测量的基站会将其测量所得的定位测量结果发送至终端设备，以使得终端设备可以从参与定位测量的所有M个基站中选择出X个基站的定位测量结果作为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图14b为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于第一网络设备，其中，所述第一网络设备为非终端设备和非基站的设备，AI模型部署在所述第一网络设备上，以及，如图14b所示，该AI模型的输入确定方法可以包括以下步骤：
步骤1401b、获取预设数量X个基站对应的定位测量结果。
其中，在本公开的一个实施例之中，上述的第一网络设备例如可以为定位服务器。
步骤1402b、将X个基站对应的定位测量结果确定为AI模型的输入。
其中，关于步骤1401b-1402b的相关介绍可以参考上述实施例描述。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于第一网络设备侧时，第一网络设备会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图14c为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于第一网络设备，其中，所述第一网络设备为非终端设备和非基站的设备，其中，AI模型部署在所述第一网络设备上，且定位测量由基站或终端设备执行，以及，如图14c所示，该AI模型的输入确定方法可以包括以下步骤：
步骤1401c、响应于定位测量结果由基站或终端设备测量所得，获取终端设备或M个基站发送的M个基站对应的定位测量结果。
步骤1402c、从M个基站中选择X个基站。
步骤1403c、获取X个基站对应的定位测量结果。
步骤1404c、将X个基站对应的定位测量结果确定为AI模型的输入。
其中，关于步骤1401c-1404c的相关介绍可以参考上述实施例描述。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于第一网络设备侧时，第一网络设备会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图14d为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于第一网络设备，其中，所述第一网络设备为非终端设备和非基站的设备，其中，AI模型部署在所述第一网络设备上，且定位测量由基站或终端设备执行，以及，如图14h所示，该AI模型的输入确定方法可以包括以下步骤：
步骤1401d、响应于定位测量结果由基站或终端设备测量所得，获取终端设备或M个基站发送的M个基站对应的定位测量结果。
步骤1402d、确定X的取值。
步骤1403d、按照M个基站的位置顺序排列M个基站。
步骤1404d、从排列后的M个基站中均匀或非均匀选择出X个基站。
步骤1405d、获取X个基站对应的定位测量结果。
步骤1406d、将X个基站对应的定位测量结果确定为AI模型的输入。
其中，关于步骤1401d-1406d的相关介绍可以参考上述实施例描述。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于第一网络设备侧时，第一网络设备会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图14e为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于第一网络设备，其中，所述第一网络设备为非终端设备和非基站的设备，其中，AI模型部署在所述第一网络设备上，且定位测量由基站或终端设备执行，以及，如图14i所示，该AI模型的输入确定方法可以包括以下步骤：
步骤1401e、响应于定位测量结果由基站或终端设备测量所得，获取终端设备或M个基站发送的M个基站对应的定位测量结果。
步骤1402e、确定基站集合，其中，该基站集合中可以包括M个基站中的X个基站。
步骤1403e、基于基站集合确定X个基站。
步骤1404e、获取X个基站对应的定位测量结果。
步骤1405e、将X个基站对应的定位测量结果确定为AI模型的输入。
其中，关于步骤1401e-1405e的相关介绍可以参考上述实施例描述。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于第一网络设备侧时，第一网络设备会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图14f为本公开实施例所提供的一种AI模型的输入确定方法的流程示意图，应用于第一网络设备，其中，所述第一网络设备为非终端设备和非基站的设备，其中，AI模型部署在所述第一网络设备上，且定位测量由基站或终端设备执行，以及，如图14f所示，该AI模型的输入确定方法可以包括以下步骤：
步骤1401f、响应于定位测量结果由基站或终端设备测量所得，获取终端设备或M个基站发送的M个基站对应的定位测量结果。
步骤1402f、确定X的取值。
步骤1403f、基于M个基站与终端设备之间的信道的首径到达时间从M个基站中选择出X个基站。
步骤1404f、获取X个基站对应的定位测量结果。
步骤1405f、确定选择的X个基站的位置坐标。
步骤1406f、将X个基站对应的定位测量结果和X个基站的位置坐标确定为AI模型的输入。
其中，关于步骤1401f-1406f的相关介绍可以参考上述实施例描述。
综上所述，在本公开实施例提供的AI模型的输入确定方法之中，当AI模型部署于第 一网络设备侧时，第一网络设备会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
图15为本公开实施例所提供的一种AI模型的输入确定装置的结构示意图，被配置于终端设备中，所述AI模型部署于终端设备上，如图15所示，装置可以包括：
收发模块，用于获取预设数量X个基站对应的定位测量结果，其中，所述预设数量X小于参与定位测量的所有基站的总数量M；其中，X和M均为正整数；
处理模块，用于将所述X个基站对应的定位测量结果确定为所述AI模型的输入。
综上所述，在本公开实施例提供的AI模型的输入确定装置之中，当AI模型部署于终端设备侧时，终端设备会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
可选地，在本公开的一个实施例之中，所述定位测量结果包括以下至少一种：
通过测量基站与被定位终端设备之间的信道所得的冲击响应；
通过测量基站与被定位终端设备之间传输的参考信号所得的测量功率。
可选地，在本公开的一个实施例之中，响应于所述AI模型部署在终端设备或基站上，且所述定位测量结果由所述终端设备测量所得，所述收发模块，还用于：
确定测量所得的所述M个基站对应的定位测量结果；
从所述M个基站中选择X个基站；
获取所述X个基站对应的定位测量结果。
可选地，在本公开的一个实施例之中，响应于所述AI模型部署在终端设备上，且所述定位测量结果由所述基站测量所得，所述收发模块，还用于：
获取M个基站发送的对应的定位测量结果；
从所述M个基站中选择X个基站；
获取所述X个基站对应的定位测量结果。
可选地，在本公开的一个实施例之中，响应于所述AI模型部署在基站上，所述处理模块还用于：
将所述X个基站对应的定位测量结果发送至部署了AI模型的基站以作为AI模型的输入。
可选地，在本公开的一个实施例之中，响应于所述AI模型部署在基站上，所述终端设备从M个基站中选择出的X个基站与其他终端设备选择出的X个基站相同。。
可选地，在本公开的一个实施例之中，所述收发模块，还用于：
确定所述X的取值；
按照所述M个基站的位置顺序排列所述M个基站；
从排列后的M个基站中均匀或非均匀选择出X个基站。
可选地，在本公开的一个实施例之中，所述收发模块，还用于：
基于协议约定确定所述X的取值；
基于基站的配置确定所述X的取值。
可选地，在本公开的一个实施例之中，所述收发模块，还用于：
确定基站集合，其中，所述基站集合中包括所述M个基站中的X个基站；
基于所述基站集合确定所述X个基站。
可选地，在本公开的一个实施例之中，所述收发模块，还用于：
基于协议约定确定所述基站集合；
基于基站的配置确定所述基站集合。
可选地，在本公开的一个实施例之中，不同终端设备所选择的X个基站不同。
可选地，在本公开的一个实施例之中，所述收发模块，还用于：
确定所述X的取值；
基于所述M个基站与所述终端设备之间的信道的首径到达时间从所述M个基站中选择出X个基站。
可选地，在本公开的一个实施例之中，所述收发模块，还用于：
从所述M个基站中选择与所述终端设备之间的信道的首径到达时间最短的X个基站。
可选地，在本公开的一个实施例之中，所述装置，还用于：
确定选择的所述X个基站的位置坐标。
可选地，在本公开的一个实施例之中，所述处理模块，还用于：
将所述X个基站对应的定位测量结果和所述X个基站的位置坐标确定为所述AI模型的输入。
图16为本公开实施例所提供的一种AI模型的输入确定装置的结构示意图，被配置于基站中，所述AI模型部署于基站上，如图16所示，装置可以包括：
收发模块，用于获取预设数量X个基站对应的定位测量结果，其中，所述预设数量X小于参与定位测量的所有基站的总数量M；其中，X和M均为正整数；
处理模块，用于将所述X个基站对应的定位测量结果确定为所述AI模型的输入。
综上所述，在本公开实施例提供的AI模型的输入确定装置之中，当AI模型部署于基站侧时，基站会先获取预设数量X个基站对应的定位测量结果，其中，预设数量X小于参与定位测量的所有基站的总数量M；X和M均为正整数；之后，会将X个基站对应的定位测量结果确定为AI模型的输入。由此可知，本公开中并非是将参与定位测量的所有基站对应的定位测量结果均作为AI模型的输入，而是将参与定位测量的部分基站对应的定位测量结果作为AI模型的输入，即，对AI模型的输入进行了精简，从而可以大幅降低AI模型的输入维度、减轻AI模型的处理负担、降低存储要求。并且，当要在空口中传输AI模型的输入时，还可以减轻信令负担。则本公开提供了一种不影响定位精度且复杂度较低的轻量型的AI模型。
可选地，在本公开的一个实施例之中，所述定位测量结果包括以下至少一种：
通过测量基站与被定位终端设备之间的信道所得的冲击响应；
通过测量基站与被定位终端设备之间传输的参考信号所得的测量功率。
可选地，在本公开的一个实施例之中，响应于所述AI模型部署在基站上，且所述定位测量结果由所述终端设备测量所得，所述收发模块，还用于：
获取终端设备发送的X个基站对应的定位测量结果。
可选地，在本公开的一个实施例之中，响应于所述AI模型部署在基站上，且所述定位测量结果由所述基站测量所得，所述收发模块，还用于：
获取参与定位测量的且未部署AI模型的其他基站发送的定位测量结果；
从参与定位测量的所有M个基站中选择X个基站；
获取所述X个基站对应的定位测量结果。
可选地，在本公开的一个实施例之中，所述收发模块还用于：
所述AI模型用于对多个终端设备进行定位时，所述基站从所述多个终端设备接收相同或不同的X个基站对应的定位测量结果。
可选地，在本公开的一个实施例之中，所述收发模块还用于：
所述AI模型用于对多个终端设备进行定位时，针对不同终端设备从所有M个基站中选择相同或不同的X个基站。
可选地，在本公开的一个实施例之中，所述收发模块，还用于：
确定所述X的取值；
按照所述M个基站的位置顺序排列所述M个基站；
从排列后的所述M个基站中均匀或非均匀选择出X个基站。
可选地，在本公开的一个实施例之中，所述收发模块，还用于：
基于协议约定确定所述X的取值；
所述基站自主确定所述X的取值。
可选地，在本公开的一个实施例之中，所述收发模块，还用于：
确定基站集合，其中，所述基站集合中包括所述M个基站中的X个基站；
基于所述基站集合确定所述X个基站。
可选地，在本公开的一个实施例之中，所述收发模块，还用于：
基于协议约定确定所述基站集合；
所述基站自主确定所述基站集合。
可选地，在本公开的一个实施例之中，所述收发模块，还用于：
确定所述X的取值；
基于所述M个基站与所述终端设备之间的信道的首径到达时间从所述M个基站中选择出X个基站。
可选地，在本公开的一个实施例之中，所述收发模块，还用于：
从所述M个基站中选择与所述终端设备之间的信道的首径到达时间最短的X个基站。
可选地，在本公开的一个实施例之中，所述装置，还用于：
确定选择的所述X个基站的位置坐标。
可选地，在本公开的一个实施例之中，所述处理模块，还用于：
将所述X个基站对应的定位测量结果和所述X个基站的位置坐标确定为所述AI模型的输入。
请参见图17，图17是本申请实施例提供的一种通信装置1700的结构示意图。通信装置1700可以是网络设备，也可以是终端设备，也可以是支持网络设备实现上述方法的芯片、芯片系统、或处理器等，还可以是支持终端设备实现上述方法的芯片、芯片系统、或处理器等。该装置可用于实现上述方法实施例中描述的方法，具体可以参见上述方法实施例中的说明。
通信装置1700可以包括一个或多个处理器1701。处理器1701可以是通用处理器或者专用处理器等。例如可以是基带处理器或中央处理器。基带处理器可以用于对通信协议以及通信数据进行处理，中央处理器可以用于对通信装置(如，基站、基带芯片，终端设备、终端设备芯片，DU或CU等)进行控制，执行计算机程序，处理计算机程序的数据。
可选的，通信装置1700中还可以包括一个或多个存储器1702，其上可以存有计算机程序1704，处理器1701执行所述计算机程序1704，以使得通信装置1700执行上述方法实施 例中描述的方法。可选的，所述存储器1702中还可以存储有数据。通信装置1700和存储器1702可以单独设置，也可以集成在一起。
可选的，通信装置1700还可以包括收发器1705、天线1706。收发器1705可以称为收发单元、收发机、或收发电路等，用于实现收发功能。收发器1705可以包括接收器和发送器，接收器可以称为接收机或接收电路等，用于实现接收功能；发送器可以称为发送机或发送电路等，用于实现发送功能。
可选的，通信装置1700中还可以包括一个或多个接口电路1707。接口电路1707用于接收代码指令并传输至处理器1701。处理器1701运行所述代码指令以使通信装置1700执行上述方法实施例中描述的方法。
在一种实现方式中，处理器1701中可以包括用于实现接收和发送功能的收发器。例如该收发器可以是收发电路，或者是接口，或者是接口电路。用于实现接收和发送功能的收发电路、接口或接口电路可以是分开的，也可以集成在一起。上述收发电路、接口或接口电路可以用于代码/数据的读写，或者，上述收发电路、接口或接口电路可以用于信号的传输或传递。
在一种实现方式中，处理器1701可以存有计算机程序1703，计算机程序1703在处理器1701上运行，可使得通信装置1700执行上述方法实施例中描述的方法。计算机程序1703可能固化在处理器1701中，该种情况下，处理器1701可能由硬件实现。
在一种实现方式中，通信装置1700可以包括电路，所述电路可以实现前述方法实施例中发送或接收或者通信的功能。本申请中描述的处理器和收发器可实现在集成电路(integrated circuit，IC)、模拟IC、射频集成电路RFIC、混合信号IC、专用集成电路(application specific integrated circuit，ASIC)、印刷电路板(printed circuit board，PCB)、电子设备等上。该处理器和收发器也可以用各种IC工艺技术来制造，例如互补金属氧化物半导体(complementary metal oxide semiconductor，CMOS)、N型金属氧化物半导体(nMetal-oxide-semiconductor，NMOS)、P型金属氧化物半导体(positive channel metal oxide semiconductor，PMOS)、双极结型晶体管(bipolar junction transistor，BJT)、双极CMOS(BiCMOS)、硅锗(SiGe)、砷化镓(GaAs)等。
以上实施例描述中的通信装置可以是网络设备或者终端设备，但本申请中描述的通信装置的范围并不限于此，而且通信装置的结构可以不受图17的限制。通信装置可以是独立的设备或者可以是较大设备的一部分。例如所述通信装置可以是：
(1)独立的集成电路IC，或芯片，或，芯片系统或子系统；
(2)具有一个或多个IC的集合，可选的，该IC集合也可以包括用于存储数据，计算机程序的存储部件；
(3)ASIC，例如调制解调器(Modem)；
(4)可嵌入在其他设备内的模块；
(5)接收机、终端设备、智能终端设备、蜂窝电话、无线设备、手持机、移动单元、车载设备、网络设备、云设备、人工智能设备等等；
(6)其他等等。
对于通信装置可以是芯片或芯片系统的情况，可参见图18所示的芯片的结构示意图。图18所示的芯片包括处理器1801和接口1802。其中，处理器1801的数量可以是一个或多个，接口1802的数量可以是多个。
可选的，芯片还包括存储器1803，存储器1803用于存储必要的计算机程序和数据。
本领域技术人员还可以了解到本申请实施例列出的各种说明性逻辑块(illustrative logical block)和步骤(step)可以通过电子硬件、电脑软件，或两者的结合进行实现。这样的功能是通过硬件还是软件来实现取决于特定的应用和整个系统的设计要求。本领域技术人 员可以对于每种特定的应用，可以使用各种方法实现所述的功能，但这种实现不应被理解为超出本申请实施例保护的范围。
本申请还提供一种可读存储介质，其上存储有指令，该指令被计算机执行时实现上述任一方法实施例的功能。
本申请还提供一种计算机程序产品，该计算机程序产品被计算机执行时实现上述任一方法实施例的功能。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机程序。在计算机上加载和执行所述计算机程序时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机程序可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机程序可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如，软盘、硬盘、磁带)、光介质(例如，高密度数字视频光盘(digital video disc，DVD))、或者半导体介质(例如，固态硬盘(solid state disk，SSD))等。
本领域普通技术人员可以理解：本申请中涉及的第一、第二等各种数字编号仅为描述方便进行的区分，并不用来限制本申请实施例的范围，也表示先后顺序。
本申请中的至少一个还可以描述为一个或多个，多个可以是两个、三个、四个或者更多个，本申请不做限制。在本申请实施例中，对于一种技术特征，通过“第一”、“第二”、“第三”、“A”、“B”、“C”和“D”等区分该种技术特征中的技术特征，该“第一”、“第二”、“第三”、“A”、“B”、“C”和“D”描述的技术特征间无先后顺序或者大小顺序。
本申请中各表所示的对应关系可以被配置，也可以是预定义的。各表中的信息的取值仅仅是举例，可以配置为其他值，本申请并不限定。在配置信息与各参数的对应关系时，并不一定要求必须配置各表中示意出的所有对应关系。例如，本申请中的表格中，某些行示出的对应关系也可以不配置。又例如，可以基于上述表格做适当的变形调整，例如，拆分，合并等等。上述各表中标题示出参数的名称也可以采用通信装置可理解的其他名称，其参数的取值或表示方式也可以通信装置可理解的其他取值或表示方式。上述各表在实现时，也可以采用其他的数据结构，例如可以采用数组、队列、容器、栈、线性表、指针、链表、树、图、结构体、类、堆、散列表或哈希表等。
本申请中的预定义可以理解为定义、预先定义、存储、预存储、预协商、预配置、固化、或预烧制。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (33)

  1. 一种人工智能AI模型的输入确定方法，其特征在于，所述AI模型的输出用于确定终端设备的定位位置，所述方法被终端设备执行，所述方法包括：
    获取预设数量X个基站对应的定位测量结果，其中，所述预设数量X小于参与定位测量的所有基站的总数量M；其中，X和M均为正整数；
    将所述X个基站对应的定位测量结果确定为所述AI模型的输入。
  2. 如权利要求1所述的方法，其特征在于，所述定位测量结果包括以下至少一种：
    通过测量基站与被定位终端设备之间的信道所得的冲击响应；
    通过测量基站与被定位终端设备之间传输的参考信号所得的测量功率。
  3. 如权利要求1所述的方法，其特征在于，响应于所述AI模型部署在终端设备或基站上，且所述定位测量结果由所述终端设备测量所得，所述获取预设数量X个基站对应的定位测量结果，包括：
    确定测量所得的所述M个基站对应的定位测量结果；
    从所述M个基站中选择X个基站；
    获取所述X个基站对应的定位测量结果。
  4. 如权利要求1所述的方法，其特征在于，响应于所述AI模型部署在终端设备上，且所述定位测量结果由所述基站测量所得，所述获取预设数量X个基站对应的定位测量结果，包括：
    获取M个基站发送的对应的定位测量结果；
    从所述M个基站中选择X个基站；
    获取所述X个基站对应的定位测量结果。
  5. 如权利要求3所述的方法，其特征在于，响应于所述AI模型部署在基站上，所述将所述X个基站对应的定位测量结果确定为所述AI模型的输入，包括：
    将所述X个基站对应的定位测量结果发送至部署了AI模型的基站以作为AI模型的输入。
  6. 如权利要求3所述的方法，其特征在于，响应于所述AI模型部署在基站上，所述终端设备从M个基站中选择出的X个基站与其他终端设备选择出的X个基站相同。
  7. 如权利要求3或4所述的方法，其特征在于，所述从所述M个基站中选择X个基站，包括：
    确定所述X的取值；
    按照所述M个基站的位置顺序排列所述M个基站；
    从排列后的M个基站中均匀或非均匀选择出X个基站。
  8. 如权利要求7所述的方法，其特征在于，所述确定所述X的取值的方法包括以下至少一种：
    基于协议约定确定所述X的取值；
    基于基站的配置确定所述X的取值。
  9. 如权利要求3或4所述的方法，其特征在于，所述从所述M个基站中选择X个基站，包括：
    确定基站集合，其中，所述基站集合中包括所述M个基站中的X个基站；
    基于所述基站集合确定所述X个基站。
  10. 如权利要求9所述的方法，其特征在于，所述确定所述基站集合的方法包括以下至少一种：
    基于协议约定确定所述基站集合；
    基于基站的配置确定所述基站集合。
  11. 如权利要求3或4所述的方法，其特征在于，所述从所述M个基站中选择X个基站，包括：
    确定所述X的取值；
    基于所述M个基站与所述终端设备之间的信道的首径到达时间从所述M个基站中选择出X个基站。
  12. 如权利要求11所述的方法，其特征在于，所述基于所述M个基站与所述终端设备之间的信道的首径到达时间从所述M个基站中选择出X个基站，包括：
    从所述M个基站中选择与所述终端设备之间的信道的首径到达时间最短的X个基站。
  13. 如权利要求11所述的方法，其特征在于，所述方法还包括：
    确定选择的所述X个基站的位置坐标。
  14. 如权利要求13所述的方法，其特征在于，所述将所述X个基站对应的定位测量结果确定为所述AI模型的输入，包括：
    将所述X个基站对应的定位测量结果和所述X个基站的位置坐标确定为所述AI模型的输入。
  15. 一种AI模型的输入确定方法，其特征在于，所述AI模型的输出用于确定终端设备的定位位置，所述方法被基站执行，所述方法包括：
    获取预设数量X个基站对应的定位测量结果，其中，所述预设数量X小于参与定位测量的所有基站的总数量M；其中，X和M均为正整数；
    将所述X个基站对应的定位测量结果确定为所述AI模型的输入。
  16. 如权利要求15所述的方法，其特征在于，所述定位测量结果包括以下至少一种：
    通过测量基站与被定位终端设备之间的信道所得的冲击响应；
    通过测量基站与被定位终端设备之间传输的参考信号所得的测量功率。
  17. 如权利要求15所述的方法，其特征在于，响应于所述AI模型部署在基站上，且所述定位测量结果由所述终端设备测量所得，所述获取预设数量X个基站对应的定位测量结果，包括：
    获取终端设备发送的X个基站对应的定位测量结果。
  18. 如权利要求15所述的方法，其特征在于，响应于所述AI模型部署在基站上，且所述定位测量结果由所述基站测量所得，所述获取预设数量X个基站对应的定位测量结果，包括：
    获取参与定位测量的且未部署AI模型的其他基站发送的定位测量结果；
    从参与定位测量的所有M个基站中选择X个基站；
    获取所述X个基站对应的定位测量结果。
  19. 如权利要求17所述的方法，其特征在于，所述获取终端设备发送的X个基站所对应的定位测量结果，包括：
    所述AI模型用于对多个终端设备进行定位时，所述基站从所述多个终端设备接收相同或不同的X个基站对应的定位测量结果。
  20. 如权利要求18所述的方法，其特征在于，所述从参与定位测量的所有M个基站中选择X个基站，包括：
    所述AI模型用于对多个终端设备进行定位时，针对不同终端设备从所有M个基站中选择相同或不同的X个基站。
  21. 如权利要求18所述的方法，其特征在于，所述从参与定位测量的所有M个基站中选择X个基站，包括：
    确定所述X的取值；
    按照所述M个基站的位置顺序排列所述M个基站；
    从排列后的所述M个基站中均匀或非均匀选择出X个基站。
  22. 如权利要求21所述的方法，其特征在于，所述确定所述X的取值，包括：
    基于协议约定确定所述X的取值；
    所述基站自主确定所述X的取值。
  23. 如权利要求18所述的方法，其特征在于，所述从参与定位测量的所有M个基站中选择X个基站，包括：
    确定基站集合，其中，所述基站集合中包括所述M个基站中的X个基站；
    基于所述基站集合确定所述X个基站。
  24. 如权利要求23所述的方法，其特征在于，所述确定所述基站集合，包括：
    基于协议约定确定所述基站集合；
    所述基站自主确定所述基站集合。
  25. 如权利要求18所述的方法，其特征在于，所述从所述M个基站中选取出预设数量X个基站，包括：
    确定所述X的取值；
    基于所述M个基站与所述终端设备之间的信道的首径到达时间从所述M个基站中选择出X个基站。
  26. 如权利要求25所述的方法，其特征在于，所述基于所述M个基站与所述终端设备之间的信道的首径到达时间从所述M个基站中选择出X个基站，包括：
    从所述M个基站中选择与所述终端设备之间的信道的首径到达时间最短的X个基站。
  27. 如权利要求25所述的方法，其特征在于，所述方法还包括：
    确定选择的所述X个基站的位置坐标。
  28. 如权利要求25所述的方法，其特征在于，所述将所述X个基站对应的定位测量结果确定为所述AI模型的输入，包括：
    将所述X个基站对应的定位测量结果和所述X个基站的位置坐标确定为所述AI模型的输入。
  29. 一种AI模型的输入确定装置，其特征在于，被配置于终端设备中，所述装置，包括：
    收发模块，用于获取预设数量X个基站对应的定位测量结果，其中，所述预设数量X小于参与定位测量的所有基站的总数量M；其中，X和M均为正整数；
    处理模块，用于将所述X个基站对应的定位测量结果确定为所述AI模型的输入。
  30. 一种AI模型的输入确定装置，其特征在于，被配置于基站中，所述装置，包括：
    收发模块，用于获取预设数量X个基站对应的定位测量结果，其中，所述预设数量X小于参与定位测量的所有基站的总数量M；其中，X和M均为正整数；
    处理模块，用于将所述X个基站对应的定位测量结果确定为所述AI模型的输入。
  31. 一种通信装置，其特征在于，所述装置包括处理器和存储器，其中，所述存储器中存储有计算机程序，所述处理器执行所述存储器中存储的计算机程序，以使所述装置执行如权利要求1至14或15至28中任一项所述的方法。
  32. 一种通信装置，其特征在于，包括：处理器和接口电路，其中，所述接口电路，用于接收代码指令并传输至所述处理器；
    所述处理器，用于运行所述代码指令以执行如权利要求1至14或15至28中任一项所述的方法。
  33. 一种计算机可读存储介质，用于存储有指令，当所述指令被执行时，使如权利要求1至14或15至28中任一项所述的方法被实现。
PCT/CN2022/105307 2022-07-12 2022-07-12 一种人工智能ai模型的输入确定方法/装置/设备 WO2024011433A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202280002587.2A CN117693990A (zh) 2022-07-12 2022-07-12 一种人工智能ai模型的输入确定方法/装置/设备
PCT/CN2022/105307 WO2024011433A1 (zh) 2022-07-12 2022-07-12 一种人工智能ai模型的输入确定方法/装置/设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/105307 WO2024011433A1 (zh) 2022-07-12 2022-07-12 一种人工智能ai模型的输入确定方法/装置/设备

Publications (1)

Publication Number Publication Date
WO2024011433A1 true WO2024011433A1 (zh) 2024-01-18

Family

ID=89535268

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/105307 WO2024011433A1 (zh) 2022-07-12 2022-07-12 一种人工智能ai模型的输入确定方法/装置/设备

Country Status (2)

Country Link
CN (1) CN117693990A (zh)
WO (1) WO2024011433A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104521297A (zh) * 2013-07-29 2015-04-15 华为技术有限公司 移动终端定位测量处理方法及装置
US20200033438A1 (en) * 2017-03-15 2020-01-30 Sigfox Method and system for geolocating a terminal of a wireless communication system
JP2021060259A (ja) * 2019-10-07 2021-04-15 ソフトバンク株式会社 測位システム、サーバ、情報配信方法及びプログラム
CN113661748A (zh) * 2019-03-27 2021-11-16 三菱电机株式会社 通信系统、基站和上位装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104521297A (zh) * 2013-07-29 2015-04-15 华为技术有限公司 移动终端定位测量处理方法及装置
US20200033438A1 (en) * 2017-03-15 2020-01-30 Sigfox Method and system for geolocating a terminal of a wireless communication system
CN113661748A (zh) * 2019-03-27 2021-11-16 三菱电机株式会社 通信系统、基站和上位装置
JP2021060259A (ja) * 2019-10-07 2021-04-15 ソフトバンク株式会社 測位システム、サーバ、情報配信方法及びプログラム

Also Published As

Publication number Publication date
CN117693990A (zh) 2024-03-12

Similar Documents

Publication Publication Date Title
WO2023168716A1 (zh) 一种载波相位定位的方法及其装置
WO2024011433A1 (zh) 一种人工智能ai模型的输入确定方法/装置/设备
WO2024050776A1 (zh) 一种信息确定方法/装置/设备及存储介质
CN116157706A (zh) 全球导航卫星系统gnss定位测量方法及装置
WO2023236124A1 (zh) 一种人工智能ai模型训练方法/装置/设备及存储介质
WO2024016245A1 (zh) 一种信息指示方法、装置、设备及存储介质
WO2024026889A1 (zh) 一种数据类型确定方法/装置/设备及存储介质
WO2023201752A1 (zh) 一种信息处理方法及其装置
WO2023168719A1 (zh) 一种载波相位定位的方法及其装置
WO2023230794A1 (zh) 一种定位方法及装置
WO2024026639A1 (zh) 一种波束赋形方法、装置、设备及存储介质
WO2024026795A1 (zh) 一种侧行链路sl定位参考信号prs的发送方法及装置
WO2024031273A1 (zh) 一种条件主辅小区PScell添加或改变的方法及装置
WO2023206565A1 (zh) 探测参考信号srs的传输方法、srs资源配置方法及其装置
WO2024000202A1 (zh) 一种信道状态信息csi反馈的确定方法及其装置
WO2023240556A1 (zh) 一种上报方法/装置/设备及存储介质
WO2023201502A1 (zh) 测量配置的处理方法和装置
WO2023168575A1 (zh) 一种天线切换能力上报方法及其装置
WO2023245452A1 (zh) 一种系统信息配置方法/装置/设备及存储介质
WO2023197121A1 (zh) 一种发送直连测距信号的方法及装置
WO2023150918A1 (zh) 一种波束管理的方法及其装置
CN116420414A (zh) 一种反馈方法、装置、设备及存储介质
WO2023015424A1 (zh) 一种定位方法及其装置
WO2023236123A1 (zh) 一种系统消息传输方法/装置/设备及存储介质
CN116420372A (zh) 一种反馈方法、装置、设备及存储介质

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 202280002587.2

Country of ref document: CN

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22950563

Country of ref document: EP

Kind code of ref document: A1