Method for training an ai / ML model and network entities
By integrating measurement data from both AI-based and non-AI-based positioning procedures, the method enhances AI/ML model training in wireless communication networks, improving positioning accuracy and effectiveness.
Patent Information
- Application Number
- PCT/CN2024/086261
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-04-05
- Publication Date
- 2025-10-09
AI Technical Summary
Existing wireless communication networks face challenges in enhancing positioning procedures through AI/ML model training, particularly in utilizing measurement data from both AI-based and non-AI-based positioning methods effectively.
A method for training an AI/ML model in wireless communication networks that integrates measurement results from both AI-based and non-AI-based positioning procedures, utilizing a network data analysis function (NWDAF) to request and collect measurement data, and a location management function (LMF) to verify and provide data for training, enhancing the training process.
This approach enhances AI/ML model-based positioning by incorporating non-AI-based training data, improving the accuracy and effectiveness of positioning services in wireless communication networks.
Smart Images

Figure CN2024086261_09102025_PF_FP_ABST
Abstract
Description
METHOD FOR TRAINING AN AI / ML MODEL AND NETWORK ENTITIESTECHNICAL FIELD
[0001] The present disclosure relates to the field of wireless communications and, more particularly, to a method for training an artificial intelligence / machine learning, AI / ML, model, to a network entity such as a location management function, LMF and to a network entity such as a network data analysis function, NWDAF. Further, the present disclosure relates to a method for AI model training based on subscription service.BACKGROUND
[0002] In a wireless communication system or network, for example in a 3GPP network, one or more terminal devices, like a user device or a user equipment, UE are operated. A terminal device is connected via a radio or wireless connection with a radio access network, RAN, for example with a base station. The RAN, in turn, is connected to the core network, CN, implementing in one or more network entities respective core network functions for controlling the operation of the overall network, like the protocols, network interfaces and services. In such a wireless communication network, it may be desired to determine a location of one or more devices or entities, e.g., UEs.
[0003] Positioning in a wireless communication network may be performed with the support of an artificial intelligence / machine learning, AI / ML model, whilst other positioning methods may be executed without such an AI / ML model.SUMMARY
[0004] It is an object of the present disclosure to provide for methods and apparatuses that improve procedures such as positioning procedures, especially positioning procedures that are based on AI / ML model usage.
[0005] This object is achieved by the subject-matter as defined in the independent claims. Favorable further developments are defined in the dependent claims.
[0006] The present disclosure provides a method for training an artificial intelligence / machine learning, AI / ML, model in a wireless communication network, the wireless communication network adapted to execute a first procedure that is based on the AI / ML model and to execute a second procedure that is unrelated to the AI / ML model or related to the same or a different AI / ML model, the method comprising training the AI / ML model for the first procedure based on measurement results and / or measurement data obtained with the first and / or second procedure. In one example, this relates to execute the second procedure that is unrelated to the AI / ML model, the method comprising training the AI / ML model for the first procedure based on measurement results and / or measurement data obtained with the second procedure that is unrelated to the AI / ML model of the first procedure.
[0007] According to an embodiment the first procedure is a first positioning procedure and / or wherein the second procedure is a second positioning procedure.
[0008] The present disclosure provides for a method comprising:
[0009] - obtaining the measurement results and / or measurement data with a location management function, LMF, of the wireless communication network and providing the measurement results and / or measurement data to a network data analysis function, NWDAF, and training the AI / ML model with the NWDAF.
[0010] In accordance with embodiments, the method comprises using a network data analysis function, NWDAF, to request the measurement results and / or measurement data and obtaining the measurement results and / or measurement data with a location management function, LMF, of the wireless communication network based on the request.
[0011] In accordance with embodiments, the method further comprises verifying the request with the LMF to obtain a verification result indicating whether the request is allowed by the LMF or not. The method comprises transmitting a response to the NWDAF indicating the verification result.
[0012] In accordance with embodiments, the method is executed such that verifying the request comprises verifying, using a unified data management, UDM, of the wireless communication network, where the data such as measurement results and / or measurement data related to a device subject to the first and / or second procedure is authorized for the training of the AI / ML model to obtain an authorization result. The method comprises providing the measurement results and / or measurement data based on the authorization result.
[0013] According to embodiments, the method comprises receiving a location service, LCS, service request and selecting, e.g., using an access and mobility function, AMF, of the wireless communication network, a location management function, LMF, for participating in the first and / or second procedure for obtaining the measurement results and / or measurement data.
[0014] According to embodiments, the method further comprises transmitting information indicating a position determined with the first and / or second procedure with the LMF to the AMF.
[0015] According to embodiments, an inventive method comprises transmitting the information indicating the position determined with the first and / or second procedure or an information derived thereof with the AMF to a recipient of the LCS services, e.g., an LSC consumer.
[0016] According to embodiments, an inventive method is executed such that the measurement results and / or measurement data are provided by a user equipment, UE, or a base station, gNB, to a location management function, LMF.
[0017] According to embodiments, a method described herein comprises requesting the measurement results and / or measurement data, e.g., related to a specific device in the wireless communication network, from a location management function, LMF, using a measurement result request. The method comprises verifying the measurement result request at the LMF and determining location information indicating the location of the specific device using the LMF for the first and / or second procedure based on measurement results and / or measurement data generated in the wireless communication network, e.g., based on a positioning request. The method comprises providing the location information and / or the measurement results and / or measurement data to a model training entity of the wireless communication network, e.g., a network data analysis function, NWDAF, for training the AI / ML model based on a successful verifying of the measurement result request.
[0018] In accordance with embodiments, the method comprises using the AI / ML model trained with the measurement results and / or measurement data unrelated to the AI / ML model for the first procedure Alternatively or in addition, the AU / ML model may be trained with measurement results and / or measurement data related to the AI / ML model, e.g., for the second procedure.
[0019] In accordance with embodiments, a computer-readable storage medium storing instructions that, when executed, cause a method described herein to be performed by a location management function and / or a network data analysis function, NWDAF, of a wireless communication system.
[0020] In accordance with embodiments, a network entity such as a location management function is adapted for operating in a wireless communication network and is configured for receiving a measurement result request to provide measurement results and / or measurement data, e.g., related to a procedure of a specific device in the wireless communication network, obtained with a second procedure that is unrelated to an AI / ML model. The network entity is adapted for verifying the measurement result request to determine a verification result indicating whether a provision of the measurement results and / or measurement data is allowed or not and is adapted for providing the measurement results and / or measurement data only when the verification result indicates that the provision of the measurement results and / or measurement data is allowed.
[0021] In accordance with embodiments, the network entity is adapted to provide the measurement results and / or measurement data to a network data analysis function, NWDAF, of the wireless communication network, e.g., for training an AI / ML model for a use in a first procedure.
[0022] In accordance with embodiments, a network entity such as a network data analysis function, NWDAF, for operating in a wireless communication network is provided that is configured for training an artificial intelligence / machine learning, AI / ML, model for the wireless communication network for execution of a first procedure that is based on the AI / ML model. The network entity is adapted for receiving measurement results and / or measurement data related to a second procedure that is unrelated to the AI / ML model. The network entity is configured for training the AI / ML model using the measurement results and / or measurement data.
[0023] The technical solutions provided according to embodiments of the present disclosure have the following beneficial effects. The present disclosure is advantageous as it allows to enhance AI / ML model based positioning by using training data, i.e., measurement results and / or measurement data that are obtained or collected during the non-AI based procedure, by enhancing AMF / LMF to notify the positioning service to AI model training entities such as NWDAF and / or to allow the NWDAF to subscribe to LMF for positioner collection for AI model training.
[0024] It should be understood that that the content described in this section is not intended to identify key or critical features of embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily appreciated from the following descriptions.BRIEF DESCRIPTION OF THE DRAWINGS
[0025] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure. The drawings are explanatory and serve to explain the present disclosure, and are not construed to limit the present disclosure to the illustrated embodiments.
[0026] Fig. 1 is a schematic flowchart of a training procedure for AI / ML direct positioning with LMF-side;
[0027] Fig. 2 shows a schematic flow diagram of a method in accordance with embodiments of the present disclosure;
[0028] Fig. 3 illustrates a flow diagram in accordance with further embodiments of the present disclosure;
[0029] MTLF, which enables the NWDAF to provide the trained AI / ML model;
[0030] Fig. 4 shows a flow diagram of at least a part of a method according to an embodiment that is related to a trigger causing the model update;
[0031] Fig. 5 shows a schematic flow diagram of a method in accordance with embodiments of the present disclosure;
[0032] Fig. 6 is a schematic flow chart describing at least a part of a method according to the present disclosure;
[0033] Fig. 7 is a schematic flow chart of at least a part of an embodied method. The method may be executed with regard to a location service, LCS service request;
[0034] Fig. 8 is a schematic flow chart of at least a part of a method described herein;
[0035] Fig. 9 is a schematic flow chart of at least a part of a method in accordance with embodiments. Beside reporting the position from the LMF to the AMF, the AMF may also inform the LCS service about the determined position;
[0036] Fig. 10 is a schematic flow chart of at least a part of a method in accordance with embodiments. Whether a specific device may be used, with regard to its position, to participate in the learning procedure may be subject to a verification;
[0037] Fig. 11 illustrates at least a part of a flow chart of a method described herein to indicate the purpose of the AI / ML model;
[0038] Fig. 12 shows a schematic flow chart of a method in accordance with embodiments that illustrates, on the one hand and when compared to Fig. 1, the inventive approach and on the other hand the interaction between different network entities from which one or more may be present and others may be omitted in different embodiments;
[0039] Fig. 13 is a block diagram illustrating an electronic device 1300 according to embodiments of the present invention.DETAILED DESCRIPTION
[0040] Illustrative embodiments of the present invention are described below with reference to the drawings, where various details of the embodiments of the present invention are included to facilitate understanding and should be considered as illustrative only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope of the present invention. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.
[0041] In the present invention, the term "and / or" is intended to cover all possible combinations and sub-combinations of the listed elements, including any one of the listed elements alone, any sub-combination, or all of the elements, and without necessarily excluding additional elements.
[0042] In the present invention, the phrase "at least one of. . . or. . . " is intended to cover any one or more of the listed elements, including any one of the listed elements alone, any sub-combination, or all of the elements, without necessarily excluding any additional elements, and without necessarily requiring all of the elements.
[0043] Terms used in embodiments of the present invention are for the purpose of describing specific embodiments, but should not be construed to limit the present invention. As used in the present invention and the appended claims, “a / an” , “said” and “the” in singular forms are intended to include plural forms, unless clearly indicated in the context otherwise. It should also be understood that, the term “and / or” used herein represents and contains any or all possible combinations of one or more associated listed items.
[0044] It should be understood that, although terms such as “first, ” “second” and “third” may be used in embodiments of the present invention for describing various information, these information should not be limited by these terms. These terms are only used for distinguishing information of the same type from each other. For example, first information may also be referred to as second information, and similarly, the second information may also be referred to as the first information, without departing from the scope of embodiments of the present invention. Depending on the context, the term “if” as used herein may be construed to mean “when” or “upon” or “in response to determining” .
[0045] In accordance with embodiments, there is made reference to a term positioning data which may represent measurement data collected from UE / gNB, e.g., during or related to a positioning procedure. Reference is made also to a measurement result which may be calculated by a network entity or network function such as a location management function, LMF, based on or using the measurement data or measurement result.
[0046] Embodiments of the present invention are described whilst making reference to positioning procedures that may benefit from using non-model related information for training an AI / ML model. However, embodiment s are not limited to positioning procedures. Other embodiments are, however, not required to rely on a position procedure but may be implemented for other procedures, e.g., for a wireless communication network. For example, beam management procedures may be based on an AI / ML model but may also be implemented without such a model and are subject to the present disclosure.
[0047] Fig. 1 is a schematic flowchart of a training procedure for AI / ML direct positioning with a known LMF-side models. In 102, the location management function, LMF, subscribes to training data from network data analysis function, NWDAF, for an AI / ML model to be used direct positioning. The training data subscription may be a request for analytics using the existing services, or a request for a model, for other type of data relevant for training. Several optional parameters as defined in TS 23.288 may be provided as service operation inputs. The training data subscription may be triggered by the LMF receiving a previous request from another network entity. The trigger itself is not shown in Fig. 1 and may be considered as forming not a part of the training procedure itself.
[0048] In 104, data collection is performed to train the model (s) for direct positioning by the network function, NF, performing training. If the model is trained by LMF, LMF may use measurements already available at the LMF or new measurements, and possibly additional data such as analytics, to train the model. If the model is trained by the NWDAF, NWDAF may collect the necessary data from NFs to train the model.
[0049] In a conditional action 106, if the training data’s subscription from LMF in 102 requires a model to be trained, NWDAF containing a model training logical function, MTLF, may train the AI / ML model.
[0050] In 108 the NWDAF provides a training data notification to LMF. Depending on the request in 102, the notification may contain the requested trained AI / ML model for direct positioning if 106 is executed, or NWDAF may provide along the notification the requested analytic or data to the LMF for 112 to be executed.
[0051] In a conditional action 112, if the AI / ML model for positioning has not been trained and has not been provided 104, LMF trains the AI / ML model in 112.
[0052] The present invention or disclosure is based on the finding that this concept only proposes that AI model training is performed during AI based positioning procedures. But during the non-AI based positioning procedure, the positioning measurement are also important and / or useful to train the AI model. The present disclosure or disclosure is based on the finding that it is of benefit to use those positioning measurements obtained during the non-AI based positioning procedure. In the concept described in connection with Fig. 1, the AI model training does not apply in the non-AI based positioning. The embodiment proposed to train the AI model during the non-AI based positioning procedure, more particularly, to extend the training of the AI model to a use of measurements obtained during the non-AI positioning procedure, not emitting a use of the measurements obtained during the AI based positioning procedure. Training may be performed by enhancing AMF / LMF to notify the positioning service to AI model training entities such as an NWDAF. Alternatively or in addition, the NWDAF may subscribe to the LMF for positioning data collection for AI model training.
[0053] In some embodiments, the NWDAF may be assumed as AI model training entity, to collect the data for AI model training. That is, the NWDAF may comprise, host or operate a model training logical function, MTLF, to provide for an AI / ML model.
[0054] It is noted that embodiments of the present disclosure may be applied to various communication systems, for example, a long term evolution (LTE) system, a fifth generation (5G) mobile communication system, a 5G new radio (NR) system or other future new mobile communication systems. Some aspects of the present disclosure relates to the aspect, in particular, the connection with an AI / ML model for direct AI / ML positioning. With regard to the aspect which entity trains the model for direct AI / ML positioning and at the entity that trained the model and the consumer are different, how the model consumer gets the trained AI / ML model.
[0055] Fig. 2 shows a schematic flow diagram of a method in accordance with embodiments of the present disclosure. In 202, a wireless communication network is operated to execute a first procedure such as a positioning procedure that is based on the AI / ML model and to execute a second procedure such as a positioning procedure that is unrelated to the AI / ML model, i.e., the network performs both, AI based procedure and non-AI based procedure, for a same device and / or for different devices. The method comprises training 204 the AI / ML model for the first procedure based on measurement results obtained with the first and / or second procedure.
[0056] Fig. 3 illustrates a flow diagram in accordance with further embodiments of the present disclosure. The method comprises obtaining 302 the measurement results with a location management function, LMF, or the wireless communication network; providing 304 the measurement results to a network data analysis function, NWDAF; and training 306 the AI / ML model with the NWDAF, i.e., using the provided measurement results, possibly by using the MTLF, which enables the NWDAF to provide the trained AI / ML model.
[0057] Fig. 4 shows a flow diagram of at least a part of a method according to an embodiment that is related to a trigger causing the model update.
[0058] In accordance with embodiments, the method comprises using 402 a network data analysis function, NWDAF, to request the measurement results. A method comprises obtaining 404 the measurement results with a location management function, LMF, of the wireless communication network based on the request.
[0059] In accordance with embodiments, the LMF verifies whether a request received, e.g., by the NWDAF, is allowed or accepted or not.
[0060] Fig. 5 shows a schematic flow diagram of a method in accordance with embodiments of the present disclosure.
[0061] According to embodiments of the present disclosure a method comprises verifying 502 the request with the LMF to obtain a verification result indicating whether the request is allowed by the LMF or not. The method comprises transmitting 504 a response to the NWDAF indicating the verification result. Such a transmission 504 may comprises explicit or implicit information. For example, when not responding to the request, this may be considered as an implicit rejection whilst by responding with the requested data, this might be considered as an implicit acceptance. This does not to preclude to transmit, as an alternative or in addition, an explicit information containing the verification result, i.e., one or more bits or symbols.
[0062] Fig. 6 is a schematic flow chart describing at least a part of a method according to the present disclosure.
[0063] In accordance with embodiments a unified data management, UDM is used for verification.
[0064] In accordance with embodiments, a method comprises: verifying 602, using a unified data management, UDM, of the wireless communication network, where the data such as measurement results related to a device subject to the second procedure, i.e., a device that is located by use of the second procedure, is authorized for the training of the AI / ML model to obtain an authorization result. The method comprises providing 604 the measurement result based on the authorization result. That is, when the authorization result indicates an authorization, the measurement results may be provided whilst measurement results may be provided with a lower resolution or granularity or might not be provided when the authorization result is negative.
[0065] Fig. 7 is a schematic flow chart of at least a part of an embodied method. The method may be executed with regard to a location service, LCS service request.
[0066] According to an embodiment, a method described herein comprises receding 702 a location service, LCS, service request. The method may comprise selecting 704, e.g., using an access and mobility function, AMF of the wireless communication network, a location management function, LMF, for participating in the second procedure for obtaining the measurement results. That is, one or more LMF may be operated in the wireless communication network from which at least one may be selected for participating in the second procedure. Beside the LMF, other entities such as gNBs and / or UEs transmitting signals may participate in the second procedure.
[0067] Fig. 8 is a schematic flow chart of at least a part of a method described herein.
[0068] According to an embodiment, a method comprises transmitting 802 information indicating a position determined with the first and / or second procedure with the LMF to the AMF. That is, the LMF may report the determined position to the AMF, e.g., in response to 704.
[0069] Fig. 9 is a schematic flow chart of at least a part of a method in accordance with embodiments. Beside reporting the position from the LMF to the AMF, the AMF may also inform the LCS service about the determined position.
[0070] According to an embodiment, a method described herein comprises transmitting 902, the information indicating the position determined with the first and / or second procedure or an information derived thereof, e.g., confirmation of a requested position or area or the like, with the AMF to a recipient of the LCS service.
[0071] Fig. 10 is a schematic flow chart of at least a part of a method in accordance with embodiments. Whether a specific device may be used, with regard to its position, to participate in the learning procedure may be subject to a verification.
[0072] According to an embodiment, a method comprises requesting 1002 the measurement results, e.g., related to a specific device and the wireless communication network, from a location management function, LMF, using a measurement result request. The method may comprise verifying 1004 the measurement result request at the LMF. The method may comprise determining 1006 location information indicating the location of the specific device using the LMF for the second procedure based on measurement results generated in the wireless communication network, e.g., based on a positioning request. The method may comprises providing 1008 the location information and / or the measurement results to a model training entity of the wireless communication network, e.g., a network data analysis function, NWDAF, for training the AI / ML model based on a successful verifying of the measurement result request.
[0073] Fig. 11 illustrates at least a part of a flow chart of a method described herein to indicate the purpose of the AI / ML model.
[0074] According to embodiments, the method comprises using 1102 the AI / ML model trained with the measurement results unrelated to the AI / ML model for the first procedure.
[0075] Fig. 12 shows a schematic flow chart of a method in accordance with embodiments that illustrates, on the one hand and when compared to Fig. 1, the inventive approach and on the other hand the interaction between different network entities from which one or more may be present and others may be omitted in different embodiments. For example, a user equipment UE, 1202, a base station, gNB 1204, an AMF 1206, a NWDAF 1208, an LMF 1212, a UDM 1214 and an LCS client or LCS consumer 1216 may be present. However, the AMF 1206, UDM 1214 and / or LCS client 1216 may be optional.
[0076] Whilst, for example, UE 1202 and gNB 1204 may comprise one or more antennas to wirelessly transmit and / or receive signals in the wireless communication network, other entities may be implemented, as an option, without wireless interface, not precluding the same. Whilst this may be implemented for AMF 1206, NWDAF 1208, LMF 1212, UDM 1214 and / or LCS client 1216, one or more of them may also be connected to the wireless communication network via an optical and / or wired connection or combinations thereof.
[0077] In 1222, NWDAF 1208 may subscribe the data collection for AI model training service to LMF 1212, to collect the measurements or the measurement data when the LMF 1212 performs the positioning service, e.g., the first and / or second procedure, i.e., AI-model based or unrelated hereto.
[0078] In 1224 LMF 1212 sends the response message to NWDAF 1208, whether the request is allowed or not as described in connection with Fig. 5.
[0079] In 1226 the AMF 1206 may receive an LCS service request from another device such as UE 1202, e.g., a mobile originated location request, MO-LR, or from the LCS client 1216, e.g., as mobile terminated location request MT-LR, or the AMF itself.
[0080] In 1228 and / or 1232 the AMF 1206 may select LMF 1212 or a different LMF or combinations thereof and may send a location request to the LMF 1212 to perform positioning or to cause the LMF 1212 to perform positioning.
[0081] In 1234, the UE 1202 and / or gNB 1204 may report the positioning measurements to the LMF 1212 and the LMF 1212 may compute the UE final location based thereon. That is, based on uplink or down signals used for the reporting, different entities may report their measurements.
[0082] In 1236, the LMF may send the measurement results or measurement data to the NWDAF, for example, in a case where the NWDAF has subscribed to the data collection for AI model training service, see 1222 and / or 1224. Prior hereto, the LMF 1212 may check, optionally by use of UDM 1214, whether the measurement data of the particular UE, i.e., this UE, is allowed or authorized for a use in connection with the AI model training as described in connection with Fig. 6 and / or Fig. 10.
[0083] In 1238 NWDAF 1208 may perform AI model training by using the received measurement data, i.e., the measurement data received from LMF 1212.
[0084] In 1242, the LMF 1212 may send the final UE location to AMF 1206, which is with regard to the training of the AI / ML model an optional aspect of the method. As a further optional aspect AMF 1206 may send the UE location to LCS consumers such as the UE 1202, other UEs, gNB 1204 and / or LCS client 1216 or the like.
[0085] In other words, Fig. 12 shows an AI model training based on a subscription service.
[0086] Fig. 13 is a block diagram illustrating an electronic device 1300 according to embodiments of the present invention.
[0087] The electronic device is intended to represent various forms of digital computers, such as a laptop, a desktop, a workstation, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The electronic device may also represent various forms of CN network entities The components shown herein, their connections and relationships, and their functions are described as examples only, and are not intended to limit implementations of the present invention described and / or claimed herein.
[0088] Referring to Fig. 13, the device 1300 includes a computing unit 1301 to perform various appropriate actions and processes according to computer program instructions stored in a read only memory (ROM) 1302, or loaded from a storage unit 1308 into a random access memory (RAM) 1303. In the RAM 1303, various programs and data for the operation of the storage device 1300 can also be stored. The computing unit 1301, the ROM 1302, and the RAM 1303 are connected to each other through a bus 1304. An input / output (I / O) interface 1305 is also connected to the bus 1304.
[0089] Components in the device 1300 are connected to the I / O interface 1305, including: an input unit 1306, such as a keyboard, a mouse; an output unit 1307, such as various types of displays, speakers; a storage unit 1308, such as a disk, an optical disk; and a communication unit 1309, such as network cards, modems, wireless communication transceivers, and the like. The communication unit 1309 allows the device 1300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0090] The computing unit 1301 may be formed of various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1301 include, but are not limited to, a central processing unit (CPU) , graphics processing unit (GPU) , various specialized artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processor (DSP) , and any suitable processor, controller, microcontroller, etc. The computing unit 1301 performs various methods and processes described above, such as an image processing method. For example, in some embodiments, the image processing method may be implemented as computer software programs that are tangibly embodied on a machine-readable medium, such as the storage unit 1308. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1300 via the ROM 1302 and / or the communication unit 1309. When a computer program is loaded into the RAM 1303 and executed by the computing unit 1301, one or more steps of the image processing method described above may be performed. In some embodiments, the computing unit 1301 may be configured to perform the image processing method in any other suitable manner (e.g., by means of firmware) .
[0091] Various implementations of the systems and techniques described herein above may be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGA) , application specific integrated circuits (ASIC) , application specific standard products (ASSP) , system-on-chip (SOC) , complex programmable logic device (CPLD) , computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and / or interpretable on a programmable system including at least one programmable processor, and the programmable processor may be a special-purpose or general-purpose programmable processor, and may receive data and instructions from a storage system, at least one input device and at least one output device, and may transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0092] Program code for implementing the methods of the present invention may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general computer, a dedicated computer, or other programmable data processing device, such that the program codes, when executed by the processor or controller, cause the functions and / or operations specified in the flowcharts and / or block diagrams is performed. The program code can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
[0093] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memories (RAM) , read-only memories (ROM) , erasable programmable read-only memories (EPROM or flash memory) , fiber optics, compact disc read-only memories (CD-ROM) , optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0094] To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having a display device (e.g., a cathode ray tube (CRT) or liquid crystal display (LCD) ) for displaying information for the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which a user can provide an input to the computer. Other types of devices can also be used to provide interaction with the user, for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback) ; and may be in any form (including acoustic input, voice input, or tactile input) to receive the input from the user.
[0095] The systems and techniques described herein may be implemented on a computing system that includes back-end components (e.g., as a data server) , or a computing system that includes middleware components (e.g., an application server) , or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein) , or a computer system including such a backend components, middleware components, front-end components or any combination thereof. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network) . Examples of the communication network includes: Local Area Networks (LAN) , Wide Area Networks (WAN) , the Internet and blockchain networks.
[0096] The computer system may include a client and a server. The Client and server are generally remote from each other and usually interact through a communication network. The relationship of the client and the server is generated by computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, and solves the defects of difficult management and weak business expansion in traditional physical hosts and virtual private servers ( "VPS" for short) . The server may also be a server of a distributed system, or a server combined with a blockchain.
[0097] It should be understood that the steps may be reordered, added or deleted by using the various forms of flows shown above. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions in the present invention can be achieved, and no limitation is imposed herein.
[0098] The above-mentioned specific embodiments do not limit the scope of protection of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and replacements may be made depending on design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the principles of the present invention should be included within the protection scope of the present invention.
Claims
1.A method for training an artificial intelligence / machine learning, AI / ML, model in a wireless communication network, the wireless communication network adapted to execute a first procedure that is based on the AI / ML model and to execute a second procedure that is unrelated to the AI / ML model, the method comprising:training the AI / ML model for the first procedure based on measurement results and / or measurement data obtained with the first procedure and / or second procedure.2.The method of claim 1, wherein the first procedure is a first positioning procedure and / or wherein the second procedure is a second positioning procedure.3.The method of claim 1 or 2, comprising:obtaining the measurement results in a location management function, LMF, of the wireless communication network; andproviding the measurement results and / or measurement data to a network data analysis function, NWDAF, andtraining the AI / ML model in the NWDAF.4.The method of one of previous claims, comprising:using a network data analysis function, NWDAF, to request the measurement results and / or measurement data; andobtaining the measurement results from a location management function, LMF, of the wireless communication network based on the request.5.The method of claim 4, further comprising:verifying the request by the LMF to obtain a verification result indicating whether the request is allowed or not; andtransmitting a response to the NWDAF indicating the verification result.6.The method of claim 5, wherein verifying the request comprises:verifying, using a unified data management, UDM, of the wireless communication network, whether data such as measurement results related to a device subject to the first or / and second procedure is authorized for the training of the AI / ML model to obtain an authorization result; andproviding the measurement results based on the authorization result.7.The method of one of previous claims, comprising:receiving a location service, LCS, service request; andselecting, e.g., using an access and mobility function, AMF, of the wireless communication network, a location management function, LMF, for participating in the first or second procedure for obtaining the measurement results and / or measurement data.8.The method of claim 7, further comprising:transmitting information indicating a position determined with the first or second procedure with the LMF to the AMF.9.The method of claim 8, further comprising:transmitting the information indicating the position determined with the first or second procedure or an information derived thereof with the AMF to a recipient of the LCS service.10.The method of one of previous claims, executed such that the measurement results and / or measurement data are provided by a user equipment, UE, or a base station, gNB, to a location management function, LMF.11.The method of one of previous claims, comprising:requesting the measurement results and / or measurement data, e.g., related to a specific device in the wireless communication network, from a location management function, LMF, using a measurement result request;verifying the measurement result request at the LMF;determining location information indicating the location of the specific device using the LMF for the first or second procedure based on measurement results and / or measurement data generated in the wireless communication network, e.g., based on a positioning request;providing the location information and / or the measurement results and / or measurement data to a model training entity of the wireless communication network, e.g., a network data analysis function, NWDAF, for training the AI / ML model based on a successful verifying of the measurement result request.12.The method of one of previous claims, comprising:using the AI / ML model trained with the measurement results and / or measurement data unrelated to the AI / ML model for the first procedure. {or / and related to AI / ML model for the second procedure}13.A computer-readable storage medium storing instructions that, when executed, cause the method of any one of the preceding claims to be performed by a location management function, LMF, and / or a network data analysis function, NWDAF, of a wireless communication system.14.A network entity such as a location management function, LMF, for operating in a wireless communication network, the network entity configured forreceiving a measurement result request to provide measurement results and / or measurement data, e.g., related to a procedure of a specific device in the wireless communication network, obtained with a second procedure that is unrelated to an AI / ML model,verifying the measurement result request to determine a verification result indicating whether a provision of the measurement results and / or measurement data is allowed or not;providing the measurement results and / or measurement data only when the verification result indicates that the provision of the measurement results is allowed.15.The network entity of claim 14, adapted to provide the measurement results and / or measurement data to a network data analysis function, NWDAF, of the wireless communication network, e.g., for training an AI / ML model for a use in a first procedure.16.A network entity such as a network data analysis function, NWDAF, for operating in a wireless communication network, the network entity configured fortraining an artificial intelligence / machine learning, AI / ML, model for the wireless communication network for execution of a first procedure that is based on the AI / ML model;receiving measurement results and / or measurement data related to a second procedure that is unrelated to the AI / ML model;wherein the network entity is configured for training the AI / ML model using the measurement results and / or measurement data.
Citation Information
Patent Citations
Wireless network load balancing method, system, equipment and medium
CN117580099A
Wireless network load balancing method, system, equipment and medium
CN117580100A
Methods, apparatus and machine-readable media relating to machine-learning in a communication network
WO2021032498A1
Network measurements for enhanced machine learning model training and inference
WO2023028319A1