WO2024149480A1

WO2024149480A1 - Sensing service in a mobile network

Info

Publication number: WO2024149480A1
Application number: PCT/EP2023/077385
Authority: WO
Inventors: Konstantinos Samdanis; Seyedomid TAGHIZADEH MOTLAGH; Genadi Velev
Original assignee: Lenovo (Singapore) Pte. Ltd.
Priority date: 2023-09-21
Filing date: 2023-10-04
Publication date: 2024-07-18

Abstract

Various aspects of the present disclosure relate to a network entity comprising a memory and a processor coupled with the memory. The processor is configured to cause the network entity to receive a first request to perform a sensing operation, the sensing operation comprising analyzing a set of reflected signals to obtain information associated with an environment in proximity to a set of devices, transmit a sensing result to a sensing consumer, wherein the sensing result is based at least in part on the sensing operation, and transmit a second request for feedback associated with the sensing result from the sensing consumer. The processor is further configured to receive the feedback from the sensing consumer based at least in part on the second request, and trigger an update of a sensing model or a sensing operability based at least in part on the received feedback from the sensing consumer.

Description

Sensing Service in a Mobile Network

TECHNICAL FIELD

[0001] The present disclosure relates to a sensing service in a mobile network and more specifically to providing feedback in respect of such a service.

BACKGROUND

[0002] A wireless communications system may include one or multiple network communication devices, such as base stations, which may support wireless communications for one or multiple user communication devices, which may be otherwise known as user equipment (UE), or other suitable terminology. The wireless communications system may support wireless communications with one or multiple user communication devices by utilizing resources of the wireless communication system (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers, or the like). Additionally, the wireless communications system may support wireless communications across various radio access technologies including third generation (3G) radio access technology, fourth generation (4G) radio access technology, fifth generation (5G) radio access technology, among other suitable radio access technologies beyond 5G (e.g., sixth generation (6G)). The wireless communications system may also be considered, for the purpose of this discussion, to comprise multiple User Equipments (UEs).

SUMMARY

[0003] An article “a” before an element is unrestricted and understood to refer to “at least one” of those elements or “one or more” of those elements. The terms “a,” “at least one,” “one or more,” and “at least one of one or more” may be interchangeable. As used herein, including in the claims, “or” as used in a list of items (e.g., a list of items prefaced by a phrase such as “at least one of’ or “one or more of’ or “one or both of’) indicates an inclusive list such that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). Also, as used herein, the phrase “based on” shall not be construed as a reference to a closed set of conditions. For example, an example step that is described as “based on condition A” may be based on both a condition A and a condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase “based on” shall be constmed in the same manner as the phrase “based at least in part on. Further, as used herein, including in the claims, a “set” may include one or more elements.

[0004] Some implementations of the method and apparatuses described herein may further include a network entity of a wireless communication system, the network entity comprising at least one memory and at least one processor coupled with the at least one memory. The processor is configured to cause the network entity to receive a first request to perform a sensing operation, wherein the sensing operation comprises analyzing a set of reflected signals in the wireless communication system to obtain information associated with an environment in proximity to a set of devices in the wireless communication system, transmit a sensing result to a sensing consumer, wherein the sensing result is based at least in part on the sensing operation, and transmit a second request for feedback associated with the sensing result from the sensing consumer. The processor is further configured to receive the feedback from the sensing consumer based at least in part on the second request, and trigger an update of a sensing model or a sensing operability based at least in part on the received feedback from the sensing consumer.

[0005] The processor may be configured to incorporate the feedback into an accumulated feedback record to allow evaluation of the quality of a sensing service type and/or sensing task, which can be transmitted to potential sensing consumers.

[0006] The second request may comprise a subscription to receive the feedback in response to an occurrence of an event, and wherein the subscription corresponds to a previous subscription of the network entity to the sensing consumer. Alternatively, the second request may comprise an on-demand request.

[0007] The at least one processor may be further configured to cause the network entity to receive from the sensing consumer an indication prior to, during, or after receiving the feedback, wherein the indication comprises: a type of feedback; an availability of the type of feedback; a duration for reporting the feedback; or an accuracy value of the feedback, or a combination thereof.

[0008] The second request may comprise timing information for generating and transmitting the feedback, or wherein the second request comprises event information associated with an evaluation performance parameter.

[0009] The second request may be a dedicated request, or the request may be included in the sensing result notification signaling.

[0010] The feedback may comprise at least one evaluation performance parameter associated with one or more of: a sensing accuracy of the sensing result based at least in part on a presence or an absence of a target sensing object or a sensing event; a sensing perception of a target sensing object or a target sensing event; a sensing accuracy associated with a geometry of the target sensing object or a location of the target sensing object, or both; a sensing mobility characteristic associated with a mobility state of the sensing objection, a speed of the sensing object, or a direction of the sensing target object, or a combination thereof; a sensing service characteristic associated with a latency of the sensing result, a sensing refresh rate of the sensing result, or a reliability of the sensing result; and an indication that the sensing result was not used including optionally the reason why the sensing result was not used; or a combination thereof.

[0011] The feedback may comprise a confidence score associated with a set of evaluation performance parameters included in the feedback.

[0012] The feedback may comprise collected data from the sensing consumer, and wherein the at least one processor is further configured to cause the network entity to verify a set of evaluation of performance parameters included in the feedback based at least in part on the collected data from the sensing consumer. [0013] The feedback may comprise at least one evaluation performance parameter and wherein the at least one processor is further configured to cause the network entity to associate the at least one evaluation performance parameter with one or more of: a first identifier associated with the sensing operation; a second identifier of a target object or an event that corresponds to the target object; a third identifier that indicates a relation of the sensing result and the feedback; a time window related to the sensing result, the time window being associated with a period over which the sensing customer used the result or a period over which the sensing customer collected the feedback; a geographical area related to the sensing result; or a timestamp related to the feedback.

[0014] The sensing consumer may comprise an application function, AF.

[0015] The network entity may comprise an interface configured to cause the network entity to output, to a network exposure function, NEF, sensing signaling exchanged with the AF.

[0016] The sensing model or other functionality used to determine the sensing results may be an Artificial Intelligence or Machine Learning model.

[0017] Some implementations of the method and apparatuses described herein may comprise a method performed by a network entity of a wireless communication system. The method comprises receiving a first request to perform a sensing operation, wherein the sensing operation comprises analyzing a set of reflected signals in the wireless communication system to obtain information associated with an environment in proximity to a set of devices in the wireless communication system, transmitting a sensing result to a sensing consumer, wherein the sensing result is based at least in part on the sensing operation, and transmitting a second request for feedback associated with the sensing result from the sensing consumer. The method further comprises receiving the feedback from the sensing consumer based at least in part on the second request, and triggering an update of a sensing model or a sensing operability based at least in part on the received feedback from the sensing consumer.

[0018] Some implementations of the method and apparatuses described herein may comprise apparatus for use external to a wireless communication system and having an interface for communicating with a network entity of the wireless communication system, the apparatus configured to operate as a sensing consumer. The apparatus comprises at least one memory and at least one processor coupled with the at least one memory. The processor is configured to send to the network entity a first request to perform a sensing operation, wherein the sensing operation comprises analyzing a set of reflected signals in the wireless communication system to obtain information associated with an environment in proximity to a set of devices in the wireless communication system, receive a sensing result from the network entity, wherein the sensing result is based at least in part on the sensing operation, receive from the network entity a second request for feedback associated with the sensing result from the sensing consumer, and send feedback to the network entity based at least in part on the second request.

[0019] Some implementations of the method and apparatuses described herein may comprise a method performed by apparatus external to a wireless communication system and having an interface for communicating with a network entity of the wireless communication system, the apparatus configured to operate as a sensing consumer. The method comprises sending to the network entity a first request to perform a sensing operation, wherein the sensing operation comprises analyzing a set of reflected signals in the wireless communication system to obtain information associated with an environment in proximity to a set of devices in the wireless communication system, receiving a sensing result from the network entity, wherein the sensing result is based at least in part on the sensing operation, receiving from the network entity a second request for feedback associated with the sensing result from the sensing consumer, and sending feedback to the network entity based at least in part on the second request.

BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 illustrates an example of a wireless communications system in accordance with aspects of the present disclosure.

[0021] Figure 2 illustrates an integrated sensing and communication architecture according to a first configuration.

[0022] Figure 3 illustrates an integrated sensing and communication architecture according to a second configuration. [0023] Figure 4 illustrates an integrated sensing and communication architecture according to a third configuration.

[0024] Figure 5 illustrates an integrated sensing and communication architecture according to a fourth configuration.

[0025] Figure 6 illustrates an integrated sensing and communication architecture according to a fifth configuration.

[0026] Figure 7 provides an overview of sensing feedback and its impact on the SF, showing the respective operations.

[0027] Figure 8 illustrates a procedure for requesting and receiving feedback from a trusted sensing consumer.

[0028] Figure 9 illustrates the procedure for requesting and receiving feedback from an untrusted sensing consumer.

[0029] Figure 10 illustrates an example of a processor 200 in accordance with aspects of the present disclosure.

[0030] Figure 11 illustrates an example of a network equipment (NE) 300 in accordance with aspects of the present disclosure.

[0031] Figure 12 is a flowchart of method performed by a NE in accordance with aspects of the present disclosure.

[0032] Figure 13 is a flowchart of method performed by an apparatus in accordance with aspects of the present disclosure.

DETAILED DESCRIPTION

[0033] Integrated sensing and communication (ISAC) may enable new features for mobile systems, for example 5G or a future 6G mobile communications systems, that will allow the inclusion of sensing capabilities, i.e., radar like sensing, in a communication network. Such sensing capabilities might be used to obtain information related to the shape, size, orientation, speed, location, distances, or relative motion between objects using New Radio (NR) Radio Frequency (RF) signals and, in some cases, previously defined information available in Evolved Packet Core (EPC) and/or Evolved Universal Terrestrial Radio Access (E-UTRA) as described in TR 22.837. [0034] ISAC is expected to impact future cellular wireless networks, both as a mechanism to improve the network performance as well as an enabler to serve vertical usecases, wherein radio/RF signals are utilized to obtain information of the surrounding environment via:

• Transmission of a sensing signal, e.g., a sensing Reference Signal (RS) from a radio or UE entity, hereafter termed as sensing Tx node.

• Reception of the reflections/echoes of the transmitted sensing excitation signal from the environment by a radio or User Equipment (UE) entity, hereafter termed a sensing Rx node. A sensing Rx node may as well be a non-3GPP sensor with capability to provide non-3GPP sensing data, or a 3 GPP node (e.g., a UE or a RAN node) connected to the said non-3GPP sensor and which can obtain, process, and transfer the non-3GPP sensing data of the said non -3 GPP sensor to other 3 GPP nodes/entities. More particularly, a set of devices configured to receive reflections and echoes may include one or more devices, which may be equipped with one or more receivers, transmitters, or a combination thereof, configured to or operable to receive one or more reflected signals in the wireless communication system. Additionally or alternatively, the one or more devices may be equipped with one or more transceivers configured to or operable to receive one or more reflected signals in the wireless communication system.

• Processing of the received reflections and inferring relevant information from the environment.

[0035] For the purposes of this discussion the following definitions [TR 22.837 may be useful:

3GPP sensing data: Data derived from 3GPP radio signals impacted (e.g., reflected, refracted, diffracted) by an object or environment of interest for sensing purposes, and optionally processed within the 5G system.

Sensing consumer: an entity, possibly an Application Function external to the wireless communication system configured to request performance of a sensing operation and to receive and consume results derived from the sensing operation.

Sensing result: processed 3GPP sensing data requested by a sensing consumer. Sensing service area: a service area where sensing services would solely rely on infrastructures and sensing technologies that can be assumed to be present anywhere where 5G/6G is present. This includes both indoor and outdoor environments.

Sensing target area: an area that needs to be sensed by deriving the dynamic characteristics of the area from any moving obstacles (e.g., cars, human, animals) from the impacted (e.g., reflected, refracted, diffracted) wireless signals. There are two kinds of target area:

1) Static sensing target area: a pre-defined area that does not move from the sensing transmitter’s perspective.

2) Moving sensing target area: a trusted zone with a target that moves from the sensing transmitter’s perspective.

[0036] The following KPIs apply to the definition of the use cases on sensing quantitative requirements:

Accuracy of positioning estimate describes the closeness of the measured sensing result (i.e., position) of the target object to its true position value. It can be further divided into a horizontal sensing accuracy referring to the sensing result error in a 2D reference or horizontal plane, and into a vertical sensing accuracy referring to the sensing result error on the vertical axis or altitude.

Accuracy of velocity estimate describes the closeness of the measured sensing result (i.e., velocity) of the target object’s velocity to its true velocity.

Confidence level describes the percentage of all the possible measured sensing results that can be expected to include the true sensing result considering the accuracy.

Sensing Resolution describes the minimum difference in the measured magnitude of target objects (e.g., range, velocity) to be allowed to detect objects in different magnitude.

Missed detection probability denotes the ratio of missing event to acquire a sensing result over all events during any predetermined period when the 5G/6G system attempts to acquire a sensing result. It applies only to binary sensing results.

False alarm probability denotes the ratio of detecting an event that does not represent the characteristics of a target object or environment over all events during any predetermined period when the 5G/6G system attempts to acquire a sensing result. It applies only to binary sensing results. Max sensing service latency: time elapsed between the event triggering the determination of the sensing result and the availability of the sensing result at the sensing system interface. Refreshing rate: rate at which the sensing result is generated by the sensing system. It is the inverse of the time elapsed between two successive sensing results.

[0037] Sensing may relate to a target UE, obj ects without network connectivity, i. e. , with no sim-card or for obtaining the environment characteristics, e.g., sensing weather conditions to determine if it is raining, and may use the radio signals from one or more base stations, i.e., sensing group whose location is known and whose sensing measurement data can be collected synchronously. The collected sensing data can then be provided to the mobile core network, which determines the sensing target and its corresponding characteristics.

[0038] Integrated sensing and communication may enhance 5G/6G core architecture by introducing a new Sensing Function (SF). Four proposals for enhancing the 5G/6G core by introducing a SF as a dedicated or logical Network Function (NF) are considered in IMT- 2020 as illustrated in Figures 2 to 6.

[0039] Figure 2: Tight coupling ISAC network architecture in which the SF appears as a dedicated NF handling both: (i) the sensing control plane aspects such as the interaction with the sensing consumer via Network Exposure Function (NEF) and information exchange with other NFs, for gathering UE information, (i.e., from the Access and Mobility Management Function (AMF), Unified Data Management (UDM), Location Management Function (LMF), UE related policies from the Policy Control Function (PCF), and analytics from the Network Data Analytics Function (NWDAF)) and (ii) the sensing radio signals for performing the analysis or prediction for determining the sensing target. Figure 3 illustrates a service-based architecture (SBA) alternative of the tight coupling ISAC network architecture of Figure 2 and in which the new SF directly interacts via NS7 with the UPF to receive sensing data, while it interacts via the service-based interconnection medium with the remaining of the 5G core control plane NFs.

[0040] Figure 4: Tight coupling ISAC network architecture with CP/UP split where the SF has two dedicated NF counter parts: (i) SF-C that handles the control plane aspects as described above and (ii) SF-U that is responsible for collecting the sensing radio signals via the user plane, i.e., via the Radio Access Network (RAN) and User Plane Function (UPF). The idea of this architecture is to split and offload heavy data volumes associated with sensing radio signals to the user plane to ensure light traffic, i.e., signalling, in the control plane.

[0041] Figure 5: SF collocated with the LMF appears as a logical NF embedded in the LMF to perform sensing taking advantage of the knowledge of a UE location.

[0042] Figure 6: Loose coupling ISAC network architecture where the SF is independent of the 5G/6G core, i.e., typically used for local field scenarios or private networks, and the interaction with the 5G/6NG core is minimal. The main idea is to use SF close to the RAN, i.e., collect and process the sensing radio signals locally, and interact with 5G/6G core for the purpose of exposure via NEF, for getting the UE location from the AMF and for analytics (NWDAF).

[0043] The main benefit of integrated sensing and communication in 5G/6G is the fact that its operation is based on the existing wireless infrastructure, which provides coverage to leverage the benefits of radio signal sensing as well as on the use of 5G/6G core that can assist in collecting further information related to the UEs, policies, analytics and can facilitate sensing exposure towards external network consumers, e.g., Application Functions (AFs).

[0044] Currently in TR 22.837 and 5G advanced IMT-2020, some preliminary requirements are introduced relating to requesting sensing services and reporting sensing results, i.e., processed sensing output information. An assumption is that a sensing consumer shall issue a sensing request towards the SF indicating the sensing service type, the sensing area or sensing target also providing the details of the sensing object (e.g., dimension details), the desired format of the sensing result and sensing confidence, as well as how to transport the sensing results, i.e., which protocol to use and via which node sensing results shall be exposed to the consumer.

[0045] When a sensing request is issued towards a SF, i.e., considering all architecture variations as illustrated in Figures 2 to 6, the sensing consumer receives a sensing result. However, there is currently no way for the SF to verify if the result provided to the consumer was valid, the degree of accuracy of the result, or whether the reporting parameters satisfied the expectations of the consumer.

[0046] The SF relies on intelligence to analyse and interpret the collected sensing data, a process that can be achieved using an Artificial Intelligence (Al) or Machine Learning (ML) model. A sensing AI/ML model can provide sensing inference, i.e., interpret the collected sensing data and “recognize” an object or situation, generating in this way the sensing result. Such a sensing AI/ML model may be collocated with the SF, or the SF may interact with another function, typically a private function, which holds the sensing AI/ML model responsible for inference. In either case, the SF would need to know the performance, i.e., the correctness and accuracy, of the sensing inference to realize when a performance drift, i.e., a deviation, occurs sufficient to trigger sensing AI/ML model re-training. It shall be noted that a drift of performance may also be caused by erroneous sensing data, but this is an issue that can be handled by data quality control operations, which can check the data range considering the average for outliers and clean erroneous data before feeding input data to the sensing AI/ML model.

[0047] A method is presented here to enable the sensing consumer to provide feedback that indicates the performance of the sensing result to in turn enable the SF to identify when the sensing AI/ML model degrades and trigger a sensing AI/ML model re-training. Such feedback may provide insight related to the performance of a sensing result in terms of:

• Correctness of perception related to a target object or situation, considering (i) the presence or absence (e.g., a dog is present on highway and that perception was correct or false, e.g., a dog was erroneously perceived to be on the highway or was there but missed), and (ii) interpretation or “understanding” of a target object or situation (e.g., correct interpretation of a car or confusion of rain with snow).

• Accuracy of sensing regarding the (i) size or dimensions of a target object (e.g., how big an object is) or the geographical area of a situation (e.g., the area within which rain falls) and (ii) location of a target object (e.g., a drone was sensed to be in location point “x”, while in reality it is in point “y”).

• Correct/estimated sensing quantity provided by the consumer (presence of a sensing target, position of a sensing target, velocity/ direction of a sensing target, motion rate of a target object etc.).

• Estimated sensing KPI/quality as defined in TR 22.837 (measure of correctness of a sensing quantity provided by the sensing service), e.g., detection/missed detection probability or positioning resolution/accuracy.

[0048] If the feedback from the sensing consumer indicates a performance drift, the SF may trigger re-training of the sensing AI/ML model, especially if more than one sensing consumer indicates model performance drift in the respective feedback. Model re-training takes place provided that the data quality control ensures that no issues related to collected sensing data can impact the AI/ML model performance.

[0049] An overview of the sensing feedback and its impact on the SF, showing the respective operations, is illustrated in Figure 7. The SF is optionally combined with the sensing AI/ML model that provides sensing inference, i.e., sensing result, to the sensing consumer upon request. Typically, the sensing consumer is an Application Service Provider (ASP) or an Application Function (AF). The SF selects and controls/configures the Transmission and Reception Points (TRPs) used for sensing target objects or situations and receiving sensing data related to a sensing request from a consumer. The SF processes the sensing data with the assistance of the sensing AI/ML model that provides inference and then (the SF) sends the obtained sensing result to the consumer.

[0050] The SF can request feedback from the sensing consumer related to the sensing result provided. The feedback from the sensing consumer can either be: (i) requested explicitly by the SF through the introduction of new signalling for this purpose, or (ii) it can be piggybacked onto the sensing notification as an additional attribute that requests the sensing consumer feedback. It shall be noted that the second option, i.e., the feedback being piggybacked, is only applicable in the case of subscription since the feedback report (the response from the sensing consumer) can then use the existing subscription signalling.

[0051] The SF request for feedback from the sensing consumer may contain one or more of the following:

• Time until feedback shall be generated, which can indicate the period to wait until the feedback is generated and then returned as either a separate message as soon as it is available or piggybacked at the first opportunity onto the conventional notification messages.

• Event identification for providing feedback, which can be related to the evaluation performance, i.e., provide feedback only when a performance metric surpasses or drops below a given limit or a combination of given limits.

• Immediate indication for providing feedback, i.e., when a sensing result is used, and the sensing consumer collects sufficient data to provide an evaluation. [0052] The sensing consumer uses the sensing result and evaluates it by comparing the sensing result prediction or perception (e.g., of a target object) to the “ground truth” data (i.e., the object observed or obtained via local means). The sources of ground truth data retrieved locally by the sensing consumer or supplied to the sensing consumer can be for example:

• Video and/or picture data from non-3GPP sources, e.g., a camera.

• Sensor network data which can provide specific measurements for a target object (e.g., car sensors) or environmental conditions, (e.g., pressure, temperature, sound, water flooding).

• Radar data if that is feasible.

• Application and/or vertical segment data, i.e., video, pictures, sensing and/or other measurements, etc., supplied by an AF.

[0053] In some embodiments, the sensing consumer, prior to a sensing request, together with a sensing request, or after a sensing request is granted for the sensing consumer, informs the network (e.g., the SF via the NEF) of the capability of the sensing consumer to provide feedback. The said capability indication may include:

• The type of sensing feedback (of an estimated/corrected sensing quantity) or an estimated sensing KPI/accuracy.

• The feedback type availability (for which sensing target tapes/object IDs, which sensing types, e.g., detection/ranging the consumer is capable of providing the said feedback).

• The feedback time availability (for which times the feedback capability is available for the consumer and/or with which margin of delay the consumer is capable of providing the said feedback).

• The accuracy of the feedback [e.g., in case a corrected sensing quantity is provided in the feedback, what is the accuracy of the estimated quantity provided by the consumer in the feedback],

• Some combination of two or more of the above.

[0054] In some embodiments the sensing consumer provides the capability information upon receiving a request for such capability information from the network. In some such embodiments, the consumer provides the capability information based on the requested capability information of the network. In some other embodiments, the consumer provides the capability indication prior to requesting a sensing service/information.

[0055] In some embodiments, the capability information includes at least one or multiple of:

• The type of supported feedback information by the consumer (i.e., indicating that the consumer is capable of providing the feedback information type for an indicated sensing result/sensing result type);

• Association to a sensing result/type, e.g., feedback on positioning of a target object including the true position of the sensing target or a deterministic (position error) or statistical error (mean squared error of the position value or sum error-squared) value of one or multiple target position information;

• A time pattern according to which the feedback can be provided by the consumer, e.g., after 10 seconds of an initial service request by the consumer or after 5 seconds of the sensing result being provided/exposed by the NW service to the consumer;

• The accuracy of the information provided in the feedback (e.g., the accuracy of the provided true position of a sensing target by the consumer);

• The areas, objects, object types for which the consumer is capable of providing the feedback, or a combination thereof.

[0056] In some embodiments, the capability information of the consumer for providing feedback information is tailored to a particular sensing service, i.e., is requested by the NW with the indication of a known sensing service. In some embodiments, the feedback capability information is provided upon a request of the network to provide feedback (e.g., when NW feedback request is not supported or partially supported by the consumer or supported with a different accuracy/KPI/latency).

[0057] The evaluation of a sensing result can be performed considering service performance parameters to form an evaluation feedback message for the SF. The SF analyses such feedback received and then determines, based on the frequency of a certain error or the magnitude of the deviation, whether to trigger a re-training of the sensing AI/ML model.

[0058] The re-training is performed by a sensing AI/ML model training function which can be collocated in the SF or can be a private vendor specific separate function (i.e., a function that provides training only for AI/ML models of the same vendor) that interacts with the SF.

[0059] The feedback from the consumer may include one or more of the following:

• False alarm ratio in detecting an erroneous event or target object or situation, i.e., a misperception.

• Missed-detection ratio of a missing an event, target object or situation considering the case of:

■ False positive, i.e., an event or situation did not occur, or an object did not exist, but the sensing result reported it erroneously.

■ False negative i.e., an event or situation did occur, or an object did exist, but the sensing result did not report.

• Deviation of dimensions of an object, i.e., report wrong size dimensions (at least 1 out of 3 dimensions) of an object, e.g., a car of length 2m instead of 1.2m.

• Deviation of mobility state of an object, i.e., stationary instead of mobile and vice versa.

• Deviation of speed an object or situation, e.g., speed of a car.

• Deviation of direction of an object or situation, e.g., direction of human, or a rain fall that moves.

• Position deviation related to a specific location, in relation to a route of an object, or with respect to a particular expected residing area.

• Area deviation related to a specific geographical area indicated for a sensing situation event, i.e., a fire is identified in a geographical area but with an inaccurate area size and shape.

• Service latency in delivering the sensing results or deviation of the expected delivery of sensing results, i.e., in case of an expected periodicity time schedule related to a subscription.

• Refresh rate mismatch ratio at which a sensing result was expected to be generated and was truly generated by the sensing AI/ML model inference.

• Reliability rate of the sensing service in terms of sensing reports interruption either considering

■ the service disruption time interval to the total subscription time and/or ■ the number of sensing results reports expected to the number of sensing results reports delivered.

• Optionally, data from the sensing consumer, e.g., using camera, pictures or other means that can identify objects, and/or events and/or situations based on the perception or based on statistical data (provide a percentage indication of accuracy related to objects and/or events and /or situations). This data can be used for example to:

■ verify the feedback in the SF,

■ check the performance accuracy AI/ML model,

■ train further the AI/ML model.

• Confidence degree deviation comparing the reported confidence degree to accuracy calculations after using the sensing result at the sensing consumer.

[0060] The notion of deviation can also be amended by including the direction of deviation, e.g., higher or lower direction from the indicated result, and can also be presented as a statistics measurement for a group of results.

[0061] The feedback from the consumer may include one or more of the following meta data to relate it to the initial sensing request or subscription:

• Sensing ID identifying the related sensing “job” (or sensing type) that the consumer requested or subscribed to.

• Object ID identifying the different objects of interest contained in the sensing result.

• Situation ID or Environment Condition ID(s) identifying the different situation or environment conditions contained in the sensing result.

• Transaction ID indicating the subscription identity (applied/valid only in case of sensing subscription) in all corresponding transactions towards the SF service consumer.

• Time window relating to the sensing result, where feedback is provided.

• Area or sub area relating to the sensing result, where feedback is provided.

• Timestamp of generating feedback towards the SF.

[0062] In case the sensing result was not used by the consumer, the consumer may not provide a feedback report but, instead, if feedback is request from the SF, the consumer may provide an indication that the sensing result was not used and, optionally, the reason for not using it.

[0063] The sensing consumer may provide regularly, i.e., periodically, feedback to the serving SF or upon meeting certain conditions, e.g. , threshold crossing, related to one or more feedback information, e.g., when the false alarm ratio surpasses a limited, or frequency ratio crossing of a certain event, i.e., occurs a more than or less than a specified number of times. Once the SF receives this feedback it will analyse it to determine whether there is a need to trigger re-training of the sensing AI/ML model.

[0064] For re-training the sensing AI/ML model there is a need to obtain new sensing data (from TRPs or data repository or data from another source) that can be used for the purpose of training. Preferably, this new sensing data needs to be related to: (i) the same Sensing ID or same category type of Sensing ID and/or (ii) the same sensing object ID type, or event type or situation type.

[0065] The procedures for requesting and receiving feedback from the sensing consumer (i.e., that can be an AF) are described below. Two different cases are considering depending upon whether the sensing consumer (i.e., AF) is trusted or untrusted.

[0066] Figure 8 illustrates the procedure for requesting and receiving feedback from a trusted sensing consumer and in particular identifies the following steps:

1. The SF service consumer requests sensing results from a sensing task by invoking Nsf Sensinglnfo Request or subscribes to or cancels a subscription to sensing results by invoking Nsf_SensingSubscription_Subscribe /Unsubscribe including the subscription Transaction ID.

The details of the Nsf_SensingInfo_ Request and Nsf_SensingSubscription_Subscribe/Unsubscribe services and the corresponding contents of the sensing exposure are known in the state-of-the-art.

2. When a request or a subscription for a sensing result is received, the SF collects radio signals, i.e., sensing data, to determine the sensing target(s).

3. The SF then derives the sensing result with the assistance of a sensing AI/ML model that is either co-located with or operating in close coordination via vendor specific interaction. 4. The SF responds by invoking Nsf Sensinglnfo Request response or the Nsf_SensingSubscription_Notify with the sensing result. If the SF provides a sensing termination, then the consumer cancels the sensing result subscription by invoking Nsf_SensingSubscription_Unsubscribe.

The details of the Nsf_SensingInfo_ Request response and Nsf_SensingSubscription_Notify services and the corresponding contents of the sensing exposure are known in the state-of-the-art.

The SF can also request the sensing consumer to evaluate the sensing result and provide feedback. The request for feedback can either be piggybacked on the existing Nsf_SensingSubscription_Notify or it can be explicitly requested with a separate message by introducing a new service Nsf_SensingFeedback_Request. In either case, the SF needs to indicate the time schedule or event conditions for providing feedback.

5. The sensing consumer uses the sensing result and then evaluates it by correlating the predicted sensing result related to a sensing target with the ground truth data obtained locally considering, e.g., video, pictures, or other sensing means to identify objects, events, or situations. The consumer then generates a feedback report to send it back to the SF.

6. The sensing consumer provides the feedback report to the SF once the indicated reporting time or event conditions are met by invoking either the new service Nsf_SensingFeedback_Request response, if the original request was a separate message, or otherwise it piggybacks the feedback report into the Nsf_SensingSubscription_Subscribe. If the SF provided a sensing termination, then the consumer cancels the sensing result subscription by invoking the Nsf_SensingSubscription_Unsubscribe and may piggyback the feedback report if the reporting time or event conditions are met.

7. The SF receives the feedback from the sensing consumer and analyses it. If the feedback indicates that there is a performance deviation beyond the pre-defined limits, i.e., there is a model drift, then it triggers model re-training and the process continues with steps 8 and 9. Otherwise these steps, i.e., steps 8 and 9, are skipped.

8. If the model re-training is triggered, the SF collects the corresponding data for the purpose of re-training. This data can be fresh sensing data from the corresponding TRPs, and/or historic data that is stored in a repository, e.g., ADRF, to assist training among other matters, and/or data provided from non-3GPP or other data sources either trusted or untrusted via exposure function, e.g., NEF.

9. The SF re-trains the sensing AI/ML model and validates it, or assists a vendor specific function (that is in close coordination with the SF) to perform re-training and validation.

10-12. The SF continues to collect new sensing data (after model re-training) to derive new sensing results with the assistance of the sensing AI/ML model. The SF then provides the new sensing result to the sensing consumer that subscribed using the

Nsf SensingSubscription Notify and that carries the corresponding Transaction ID and Feedback request (if needed).

[0067] Figure 9 illustrates the procedure for requesting and receiving feedback from an untrusted sensing consumer and in particular identifies the following steps:

0. A Network Exposure Function (NEF) controls the sensing exposure mapping among the untrusted sensing consumers (i.e., AF) using an identifier (i.e., the subscription Transaction ID) with allowed sensing tasks and associated inbound as well as outbound restrictions.

An untrusted sensing consumer can be configured with the appropriated NEF to subscribe to sensing results, with the allowed sensing tasks and with the allowed inbound restrictions (i.e., parameters and/or parameter values) for requesting sensing results from each sensing task.

1. The untrusted sensing consumer requests to receive sensing results by invoking Nnef SensingExposure Fetch, a service that is defined similarly to conventional fetch service operations as defined in TS 23.502. If the sensing request is authorized by the NEF, the NEF proceeds with the following steps [otherwise the request is rejected.].

The details related to Nnef SensingExposure Fetch service.

2. Based on the request from the untrusted sensing consumer, the NEF requests sensing results by invoking the Nsf Sensinglnfo Request. The details related to Nsf_SensingInfo_Request service.

If the parameters and/or parameters values of the untrusted AF request comply with the inbound restriction in the sensing exposure mapping, NEF forwards the request to the respective SF. Otherwise, NEF may apply restrictions to the request related to parameters or parameter values based on operator configuration and/or may apply parameter mapping (e.g., geographical ordered coordinates mapping to TA(s)/Cell-id(s)).

The NEF records the association of the sensing request from the untrusted sensing consumer and the sensing request sent to the SF. The NEF selects the appropriate SF using the conventional discovery procedures defined in TS 23.501 (i.e., with the assumption that SFs register their capabilities with the NRF).

3. When a request or a subscription for a sensing result is received, the SF collects radio signals, i.e., sensing data, to determine the sensing target(s).

4. The SF then derives the sensing result with the assistance of a sensing AI/ML model that is either co-located or are in close coordination via vendor specific interaction.

5. The SF responds to the NEF with the sensing result by invoking the Nsf_SensingInfo_Request response or the Nsf_SensingSubscription_Notify. If the SF provides a sensing termination, then the consumer cancels the sensing result subscription by invoking Nsf_SensingSubscription_Unsubscribe.

6. When the NEF receives the response or notification that contains the sensing result or a sensing termination notification from the SF, the NEF forwards it to the untrusted sensing consumer by invoking the Nnef SensingExposure Fetch response or Nnef_SensingExposure_Notify. The NEF forwards also the request for feedback, which is either piggybacked on the existing Nnef_SensingExposure_Notify or is included in a separate message by introducing a new service Nnef_SensingFeedback_Fetch.

The NEF may apply outbound restrictions to the notifications to the untrusted sensing consumer (e.g., restrictions to parameters or parameter values) based on sensing exposure mapping and may apply parameter mapping for external usage (e.g., convert TA(s), Cell- id(s) to geographical area coordinates).

7. The sensing consumer uses the sensing result and then evaluates it by correlating the predicted sensing result related to a sensing target with the ground truth data obtained locally considering, e.g., video, pictures, or other sensing means to identify objects, events, or situations. The consumer then generates a feedback report to send back to the SF.

8. The sensing consumer provides the feedback report to the NEF once the indicated reporting time or event conditions are met by invoking either the new service Nnef SensingFeedback Fetch response if the original request was a separate message or otherwise it piggybacks the feedback report into the Nnef_SensingExposure_Subscribe. If the SF provided a sensing termination, then the consumer cancels the sensing result subscription by invoking the Nnef_SensingExposure_Unsubscribe and may piggyback the feedback report if the reporting time or event conditions are met.

9. The NEF may apply inbound restrictions and perform exposure mappings before it forwards the feedback report to the SF by invoking either the new service

Nsf SensingFeedback Request response if the original request was a separate message or otherwise it piggybacks the feedback report into the Nsf_SensingSubscription_Subscribe. If the SF provided a sensing termination, then the NEF forwards the consumer cancelation subscription by invoking the Nsf_SensingSubscription_Unsubscribe and may piggyback the feedback report if the reporting time or event conditions are met.

10. The SF receives the feedback from the sensing consumer and analyses it. If the feedback indicates that there is a performance deviation beyond the pre-defined limits, i.e., there is a model drift, then it triggers model re-training and the process continues with steps 11 and 12. Otherwise, there the model re-training steps, i.e., steps 11 and 12, are skipped.

11. If the model re-training is triggered, the SF collects the corresponding data for the purpose of re-training. This data can be fresh sensing data from the corresponding TRPs, and/or historic data that is stored in a repository, e.g., ADRF, to assist training among other matters, and/or data provided from non-3GPP or other data sources either trusted or untrusted via exposure function, e.g., NEF.

12. The SF re-trains the sensing AI/ML model and validates it or assists a vendor specific function (that is in close coordination with the SF) to perform re-training and validation.

13-16. The SF continues to collect new sensing data (after model re-training) to derive new sensing results with the assistance of the sensing AI/ML model. The SF then provides via NEF the new sensing result to the sensing consumer that subscribed using the

Nsf SensingSubscription Notify and including the corresponding Transaction ID and Feedback request. The NEF forwards this to the sensing consumer using Nnef_SensingExposure_Notify.

[0068] It shall be noted that the feedback request, i.e., Nsf SensingFeedback Request, can also be in the form of a subscription, i.e., Nsf_SensingFeedback_Subscribe/Unsubscribe, to request feedback for a time-period on a regular time schedule and/or upon a specific event, e.g., performance threshold crossing.

[0069] In some embodiments, the used AI/ML model receiving/utilizing the said feedback information may utilize the said feedback information as an input information for the purpose of:

• inference/deriving the sensing results of a sensing task,

• for predicting/estimating the quality of a sensing service/task [e.g., a defined sensing task/request],

• predicting/estimating the quality/suitability of the sensing nodes involved in sensing operations,

• training/learning for performing inference/deriving the sensing results of a sensing task,

• training/learning for performing predicting/estimating the quality of a sensing service/task [e.g., a defined sensing task/request],

• training/learning for performing predicting/estimating the quality/suitability of the sensing nodes involved in sensing operations,

• or a combination thereof.

[0065] In some embodiments, the said AI/ML model is one of:

• an internal SF model,

• part of NWDAF,

• part of the RAN (an AI/ML model in a gNB performing sensing measurement and/or processing of the said sensing measurements), and

• part of a UE (an AI/ML model in a UE performing sensing measurement and/or processing of the said sensing measurements). [0070] The embodiments presented here, as well as other embodiments of the invention, provide a mechanism to improve over time the quality of sensing results obtained and presented by a sensing function of a wireless communication system. Given that a number, potentially a large number, of sensing customers may provide feedback to the sensing function based on a variety of means, e.g. result comparison with video data generated by cameras, end users, radar etc, learning improvements can be rapid and huge.

[0071] In some embodiments, different feedback types (e.g., any of the above-mentioned feedback types) may be provided (and requested by the network) by the consumer for a particular instance of a sensing result (for position information of a target, estimated and exposed to the consumer at a single time instance and/or for a single target/point), for multiple or group of sensing result instances (e.g., instances of the exposed sensing results to the consumer over an indicated period of time).

[0072] In one example, when the sensing result of a sensing service is a position of an object, the obtained/estimated position at the time instance T1 is exposed to the consumer as an instance of a sensing result. The same derivation/estimation and/or exposure of the sensing result as a position of the sensed object is further done for T2-TN time instances. In this example, the feedback from the consumer may include correct/true position or the position error (when such information later becomes apparent for the consumer via some other sensing/observation means) of the object separately for individual instances of the sensing result. Alternatively, group feedback for multiple of the sensing results at multiple time instances (e.g., an average error, error variance, error of all sensing results as a list, etc.) may be provided.

[0073] In some embodiments, the feedback is a deterministic measure (e.g., an indication of a false positive in one or more instances of sensing results, or a position error/displacement of a sensing result compared to a true value), or may be a statistical measure (e.g., an experienced sensing KPI as defined in TR 22.837, e.g., positioning/velocity accuracy, MD/FA rate, mean squared error of a position, etc.).

[0074] In some embodiments statistical error feedback is generated based on metrics different from that of TR 22.837, for example in order to embed more information (e.g., directional information of position and/or velocity error or deviation) of the nature of the error statistics. In one example, the average error of a position estimate is reported as an average position displacement, including magnitude and direction. In another example, the average velocity error is provided as a feedback including a magnitude and direction of the velocity error.

[0075] In some embodiments, the sensing consumer receives an indication of one or more criteria according to which it shall send the feedback, for example:

• Is the positioning error is above a threshold, in case of a FA, MD, or in case the FA and/or MD exceeds a threshold in a window of an indicated instances of detection sensing results? or

• Is a pattern of error present among one or multiple metrics of the measurement results provided by the network?

[0076] Figure 1 illustrates an example of a wireless communications system 100 in accordance with aspects of the present disclosure. The wireless communications system 100 may include one or more NE 102, one or more UEs 104, and a core network (CN) 106. The wireless communications system 100 may support various radio access technologies. In some implementations, the wireless communications system 100 may be a 4G network, such as an LTE network or an LIE- Advanced (LIE- A) network. In some other implementations, the wireless communications system 100 may be a NR network, such as a 5G network, a 5G- Advanced (5G-A) network, or a 5G ultrawideband (5G-UWB) network. In other implementations, the wireless communications system 100 may be a combination of a 4G network and a 5G network, or other suitable radio access technology including Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20. The wireless communications system 100 may support radio access technologies beyond 5G, for example, 6G. Additionally, the wireless communications system 100 may support technologies, such as time division multiple access (TDMA), frequency division multiple access (FDMA), or code division multiple access (CDMA), etc.

[0077] The one or more Network Entities (NE) 102 may be dispersed throughout a geographic region to form the wireless communications system 100. One or more of the NEs 102 described herein may be or include or may be referred to as a network node, a base station, a network function, a radio access network (RAN), a NodeB, an eNodeB (eNB), a next-generation NodeB (gNB), or other suitable terminology. An NE 102 and a UE 104 may communicate via a communication link, which may be a wireless or wired connection. For example, an NE 102 and a UE 104 may perform wireless communication (e.g., receive signaling, transmit signaling) over a Uu interface.

[0078] An NE 102 may provide a geographic coverage area for which the NE 102 may support services for one or more UEs 104 within the geographic coverage area. For example, an NE 102 and a UE 104 may support wireless communication of signals related to services (e.g., voice, video, packet data, messaging, broadcast, etc.) according to one or multiple radio access technologies. In some implementations, an NE 102 may be moveable, for example, a satellite associated with a non-terrestrial network (NTN). In some implementations, different geographic coverage areas 112 associated with the same or different radio access technologies may overlap, but the different geographic coverage areas may be associated with different NE 102.

[0079] The one or more UEs 104 may be dispersed throughout a geographic region of the wireless communications system 100. A UE 104 may include or may be referred to as a remote unit, a mobile device, a wireless device, a remote device, a subscriber device, a transmitter device, a receiver device, or some other suitable terminology. In some implementations, the UE 104 may be referred to as a unit, a station, a terminal, or a client, among other examples. Additionally, or alternatively, the UE 104 may be referred to as an Internet-of- Things (loT) device, an Internet-of-Everything (loE) device, or machine-type communication (MTC) device, among other examples.

[0080] A UE 104 may be able to support wireless communication directly with other UEs 104 over a communication link. For example, a UE 104 may support wireless communication directly with another UE 104 over a device-to-device (D2D) communication link. In some implementations, such as vehicle-to-vehicle (V2V) deployments, vehicle-to- everything (V2X) deployments, or cellular-V2X deployments, the communication link 114 may be referred to as a sidelink. For example, a UE 104 may support wireless communication directly with another UE 104 over a PC5 interface.

[0081] An NE 102 may support communications with the CN 106, or with another NE 102, or both. For example, an NE 102 may interface with other NE 102 or the CN 106 through one or more backhaul links (e.g., SI, N2, N2, or network interface). In some implementations, the NE 102 may communicate with each other directly. In some other implementations, the NE 102 may communicate with each other or indirectly (e.g., via the CN 106). In some implementations, one or more NE 102 may include subcomponents, such as an access network entity, which may be an example of an access node controller (ANC). An ANC may communicate with the one or more UEs 104 through one or more other access network transmission entities, which may be referred to as a radio heads, smart radio heads, or transmission-reception points (TRPs).

[0082] The CN 106 may support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The CN 106 may be an evolved packet core (EPC), or a 5G core (5GC), which may include a control plane entity that manages access and mobility (e.g., a mobility management entity (MME), an access and mobility management functions (AMF)) and a user plane entity that routes packets or interconnects to external networks (e.g., a serving gateway (S-GW), a Packet Data Network (PDN) gateway (P-GW), or a user plane function (UPF)). In some implementations, the control plane entity may manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management (e.g., data bearers, signal bearers, etc.) for the one or more UEs 104 served by the one or more NE 102 associated with the CN 106.

[0083] The CN 106 may communicate with a packet data network over one or more backhaul links (e.g., via an SI, N2, N2, or another network interface). The packet data network may include an application server. In some implementations, one or more UEs 104 may communicate with the application server. A UE 104 may establish a session (e.g., a protocol data unit (PDU) session, or the like) with the CN 106 via an NE 102. The CN 106 may route traffic (e.g., control information, data, and the like) between the UE 104 and the application server using the established session (e.g., the established PDU session). The PDU session may be an example of a logical connection between the UE 104 and the CN 106 (e.g., one or more network functions of the CN 106).

[0084] In the wireless communications system 100, the NEs 102 and the UEs 104 may use resources of the wireless communications system 100 (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers)) to perform various operations (e.g., wireless communications). In some implementations, the NEs 102 and the UEs 104 may support different resource structures. For example, the NEs 102 and the UEs 104 may support different frame structures. In some implementations, such as in 4G, the NEs 102 and the UEs 104 may support a single frame structure. In some other implementations, such as in 5G and among other suitable radio access technologies, the NEs 102 and the UEs 104 may support various frame structures (i.e., multiple frame structures). The NEs 102 and the UEs 104 may support various frame structures based on one or more numerologies.

[0085] One or more numerologies may be supported in the wireless communications system 100, and a numerology may include a subcarrier spacing and a cyclic prefix. A first numerology (e.g., /r=0) may be associated with a first subcarrier spacing (e.g., 15 kHz) and a normal cyclic prefix. In some implementations, the first numerology (e.g., /r=0) associated with the first subcarrier spacing (e.g., 15 kHz) may utilize one slot per subframe. A second numerology (e.g., /r=l) may be associated with a second subcarrier spacing (e.g., 30 kHz) and a normal cyclic prefix. A third numerology (e.g., /r=2) may be associated with a third subcarrier spacing (e.g., 60 kHz) and a normal cyclic prefix or an extended cyclic prefix. A fourth numerology (e.g., /r=3) may be associated with a fourth subcarrier spacing (e.g., 120 kHz) and a normal cyclic prefix. A fifth numerology (e.g., /r=4) may be associated with a fifth subcarrier spacing (e.g., 240 kHz) and a normal cyclic prefix.

[0086] A time interval of a resource (e.g., a communication resource) may be organized according to frames (also referred to as radio frames). Each frame may have a duration, for example, a 10 millisecond (ms) duration. In some implementations, each frame may include multiple subframes. For example, each frame may include 10 subframes, and each subframe may have a duration, for example, a 1ms duration. In some implementations, each frame may have the same duration. In some implementations, each subframe of a frame may have the same duration.

[0087] Additionally or alternatively, a time interval of a resource (e.g., a communication resource) may be organized according to slots. For example, a subframe may include a number (e.g., quantity) of slots. The number of slots in each subframe may also depend on the one or more numerologies supported in the wireless communications system 100. For instance, the first, second, third, fourth, and fifth numerologies (i.e., /r=0, jU=l, /r=2, jU=3, /r=4) associated with respective subcarrier spacings of 15 kHz, 30 kHz, 60 kHz, 120 kHz, and 240 kHz may utilize a single slot per subframe, two slots per subframe, four slots per subframe, eight slots per subframe, and 16 slots per subframe, respectively. Each slot may include a number (e.g., quantity) of symbols (e.g., OFDM symbols). In some implementations, the number (e.g., quantity) of slots for a subframe may depend on a numerology. For a normal cyclic prefix, a slot may include 14 symbols. For an extended cyclic prefix (e.g., applicable for 60 kHz subcarrier spacing), a slot may include 12 symbols. The relationship between the number of symbols per slot, the number of slots per subframe, and the number of slots per frame for a normal cyclic prefix and an extended cyclic prefix may depend on a numerology. It should be understood that reference to a first numerology (e.g., /i =0) associated with a first subcarrier spacing (e.g., 15 kHz) may be used interchangeably between subframes and slots.

[0088] In the wireless communications system 100, an electromagnetic (EM) spectrum may be split, based on frequency or wavelength, into various classes, frequency bands, frequency channels, etc. By way of example, the wireless communications system 100 may support one or multiple operating frequency bands, such as frequency range designations FR1 (410 MHz - 7.125 GHz), FR2 (24.25 GHz - 52.6 GHz), FR3 (7.125 GHz - 24.25 GHz), FR4 (52.6 GHz - 114.25 GHz), FR4a or FR4-1 (52.6 GHz - 71 GHz), and FR5 (114.25 GHz - 300 GHz). In some implementations, the NEs 102 and the UEs 104 may perform wireless communications over one or more of the operating frequency bands. In some implementations, FR1 may be used by the NEs 102 and the UEs 104, among other equipment or devices for cellular communications traffic (e.g., control information, data). In some implementations, FR2 may be used by the NEs 102 and the UEs 104, among other equipment or devices for short-range, high data rate capabilities.

[0089] FR1 may be associated with one or multiple numerologies (e.g., at least three numerologies). For example, FR1 may be associated with a first numerology (e.g., /r=0), which includes 15 kHz subcarrier spacing; a second numerology (e.g., /r=l), which includes 30 kHz subcarrier spacing; and a third numerology (e.g., /r=2), which includes 60 kHz subcarrier spacing. FR2 may be associated with one or multiple numerologies (e.g., at least 2 numerologies). For example, FR2 may be associated with a third numerology (e.g., /r=2), which includes 60 kHz subcarrier spacing; and a fourth numerology (e.g., /r=3), which includes 120 kHz subcarrier spacing.

[0090] Figure 10 illustrates an example of a processor 200 in accordance with aspects of the present disclosure. The processor 200 may be an example of a processor configured to perform various operations in accordance with examples as described herein. The processor 200 may include a controller 202 configured to perform various operations in accordance with examples as described herein. The processor 200 may optionally include at least one memory 204, which may be, for example, an L1/L2/L3 cache. Additionally, or alternatively, the processor 200 may optionally include one or more arithmetic-logic units (ALUs) 206. One or more of these components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses).

[0091] The processor 200 may be a processor chipset and include a protocol stack (e.g., a software stack) executed by the processor chipset to perform various operations (e.g., receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) in accordance with examples as described herein. The processor chipset may include one or more cores, one or more caches (e.g., memory local to or included in the processor chipset (e.g., the processor 200) or other memory (e.g., random access memory (RAM), read-only memory (ROM), dynamic RAM (DRAM), synchronous dynamic RAM (SDRAM), static RAM (SRAM), ferroelectric RAM (FeRAM), magnetic RAM (MRAM), resistive RAM (RRAM), flash memory, phase change memory (PCM), and others).

[0092] The controller 202 may be configured to manage and coordinate various operations (e.g., signaling, receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) of the processor 200 to cause the processor 200 to support various operations in accordance with examples as described herein. For example, the controller 202 may operate as a control unit of the processor 200, generating control signals that manage the operation of various components of the processor 200. These control signals include enabling or disabling functional units, selecting data paths, initiating memory access, and coordinating timing of operations.

[0093] The controller 202 may be configured to fetch (e.g., obtain, retrieve, receive) instructions from the memory 204 and determine subsequent instruction(s) to be executed to cause the processor 200 to support various operations in accordance with examples as described herein. The controller 202 may be configured to track memory address of instructions associated with the memory 204. The controller 202 may be configured to decode instructions to determine the operation to be performed and the operands involved. For example, the controller 202 may be configured to interpret the instruction and determine control signals to be output to other components of the processor 200 to cause the processor 200 to support various operations in accordance with examples as described herein. Additionally, or alternatively, the controller 202 may be configured to manage flow of data within the processor 200. The controller 202 may be configured to control transfer of data between registers, arithmetic logic units (ALUs), and other functional units of the processor 200.

[0094] The memory 204 may include one or more caches (e.g., memory local to or included in the processor 200 or other memory, such RAM, ROM, DRAM, SDRAM, SRAM, MRAM, flash memory, etc. In some implementations, the memory 204 may reside within or on a processor chipset (e.g., local to the processor 200). In some other implementations, the memory 204 may reside external to the processor chipset (e.g., remote to the processor 200). [0095] The memory 204 may store computer-readable, computer-executable code including instructions that, when executed by the processor 200, cause the processor 200 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. The controller 202 and/or the processor 200 may be configured to execute computer-readable instructions stored in the memory 204 to cause the processor 200 to perform various functions. For example, the processor 200 and/or the controller 202 may be coupled with or to the memory 204, the processor 200, the controller 202, and the memory 204 may be configured to perform various functions described herein. In some examples, the processor 200 may include multiple processors and the memory 204 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories, which may, individually or collectively, be configured to perform various functions herein.

[0096] The one or more ALUs 206 may be configured to support various operations in accordance with examples as described herein. In some implementations, the one or more ALUs 206 may reside within or on a processor chipset (e.g., the processor 200). In some other implementations, the one or more ALUs 206 may reside external to the processor chipset (e.g., the processor 200). One or more ALUs 206 may perform one or more computations such as addition, subtraction, multiplication, and division on data. For example, one or more ALUs 206 may receive input operands and an operation code, which determines an operation to be executed. One or more ALUs 206 be configured with a variety of logical and arithmetic circuits, including adders, subtractors, shifters, and logic gates, to process and manipulate the data according to the operation. Additionally, or alternatively, the one or more ALUs 206 may support logical operations such as AND, OR, exclusive-OR (XOR), not-OR (NOR), and not-AND (NAND), enabling the one or more ALUs 206 to handle conditional operations, comparisons, and bitwise operations.

[0097] The processor 200 may support wireless communication in accordance with examples as disclosed herein. The processor 200 may be configured to or be operable to support a means for receiving a first request to perform a sensing operation, wherein the sensing operation comprises analyzing a set of reflected signals in the wireless communication system to obtain information associated with an environment in proximity to a set of devices in the wireless communication system, transmit a sensing result to a sensing consumer, wherein the sensing result is based at least in part on the sensing operation, transmit a second request for feedback associated with the sensing result from the sensing consumer, receive the feedback from the sensing consumer based at least in part on the second request, and trigger an update of a sensing model or a sensing operability based at least in part on the received feedback from the sensing consumer.

[0098] Figure 11 illustrates an example of a NE 300 in accordance with aspects of the present disclosure. The NE 300 may include a processor 302, a memory 304, a controller 306, and a transceiver 308. The processor 302, the memory 304, the controller 306, or the transceiver 308, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.

[0099] The processor 302, the memory 304, the controller 306, or the transceiver 308, or various combinations or components thereof may be implemented in hardware (e.g., circuitry). The hardware may include a processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure. [0100] The processor 302 may include an intelligent hardware device (e.g., a general- purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof). In some implementations, the processor 302 may be configured to operate the memory 304. In some other implementations, the memory 304 may be integrated into the processor 302. The processor 302 may be configured to execute computer-readable instructions stored in the memory 304 to cause the NE 300 to perform various functions of the present disclosure.

[0101] The memory 304 may include volatile or non-volatile memory. The memory 304 may store computer-readable, computer-executable code including instructions when executed by the processor 302 cause the NE 300 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 304 or another type of memory. Computer-readable media includes both non- transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or specialpurpose computer.

[0102] In some implementations, the processor 302 and the memory 304 coupled with the processor 302 may be configured to cause the NE 300 to perform one or more of the functions described herein (e.g., executing, by the processor 302, instructions stored in the memory 304). For example, the processor 302 may support wireless communication at the NE 300 in accordance with examples as disclosed herein.

[0103] The NE 300 may be configured to support a means for receiving a first request to perform a sensing operation, wherein the sensing operation comprises analyzing a set of reflected signals in the wireless communication system to obtain information associated with an environment in proximity to a set of devices in the wireless communication system, transmitting a sensing result to a sensing consumer, wherein the sensing result is based at least in part on the sensing operation, transmitting a second request for feedback associated with the sensing result from the sensing consumer, receiving the feedback from the sensing consumer based at least in part on the second request, and triggering an update of a sensing model or a sensing operability based at least in part on the received feedback from the sensing consumer. [0104] The controller 306 may manage input and output signals for the NE 300. The controller 306 may also manage peripherals not integrated into the NE 300. In some implementations, the controller 306 may utilize an operating system such as iOS®, ANDROID®, WINDOWS®, or other operating systems. In some implementations, the controller 306 may be implemented as part of the processor 302.

[0105] In some implementations, the NE 300 may include at least one transceiver 308. In some other implementations, the NE 300 may have more than one transceiver 308. The transceiver 308 may represent a wireless transceiver. The transceiver 308 may include one or more receiver chains 310, one or more transmitter chains 312, or a combination thereof.

[0106] A receiver chain 310 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 310 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 310 may include at least one amplifier (e.g., a low-noise amplifier (LNA)) configured to amplify the received signal. The receiver chain 310 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 310 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.

[0107] A transmitter chain 312 may be configured to generate and transmit signals (e.g., control information, data, packets). The transmitter chain 312 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM), frequency modulation (FM), or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM). The transmitter chain 312 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 312 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.

[0108] An external network equipment implementing, for example a sensing customer function, may have the same or a similar architecture to the Network Equipment of Figure 11. [0109] Figure 12 illustrates a flowchart of a method in accordance with aspects of the present disclosure. The operations of the method may be implemented by a NE as described herein. In some implementations, the NE may execute a set of instructions to control the function elements of the NE to perform the described functions.

[0110] At 401, the method may include receiving a first request to perform a sensing operation, wherein the sensing operation comprises analyzing a set of reflected signals in the wireless communication system to obtain information associated with an environment in proximity to a set of devices in the wireless communication system. The operations of 401 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 401 may be performed by a NE as described with reference to Figure 11.

[0111] At 402, the method may include transmitting a sensing result to a sensing consumer, wherein the sensing result is based at least in part on the sensing operation. The operations of 402 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 402 may be performed by a NE as described with reference to Figure 11.

[0112] At 403, the method may include transmitting a second request for feedback associated with the sensing result from the sensing consumer. The operations of 403 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 403 may be performed a NE as described with reference to Figure 11.

[0113] At 404, the method may include receiving the feedback from the sensing consumer based at least in part on the second request. The operations of 405 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 405 may be performed a NE as described with reference to Figure 11.

[0114] At 405, the method may include triggering an update of a sensing model or a sensing operability based at least in part on the received feedback from the sensing consumer. The operations of 406 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 406 may be performed a NE as described with reference to Figure 11. [0115] Figure 13 illustrates a flowchart of a method in accordance with aspects of the present disclosure. The operations of the method may be implemented by apparatus as described herein. In some implementations, the apparatus may execute a set of instructions to control the function elements of the apparatus to perform the described functions.

[0116] At 501, the method may include sending to the network entity a first request to perform a sensing operation, wherein the sensing operation comprises analyzing a set of reflected signals in the wireless communication system to obtain information associated with an environment in proximity to a set of devices in the wireless communication system. The operations of 501 may be performed in accordance with examples as described herein.

[0117] At 502, the method may include receiving a sensing result from the network entity, wherein the sensing result is based at least in part on the sensing operation. The operations of 502 may be performed in accordance with examples as described herein.

[0118] At 503, the method may include receiving from the network entity a second request for feedback associated with the sensing result from the sensing consumer. The operations of 503 may be performed in accordance with examples as described herein.

[0119] At 504, the method may include sending feedback to the network entity based at least in part on the second request. The operations of 504 may be performed in accordance with examples as described herein.

[0120] It should be noted that the methods described herein describe possible implementation, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.

[0121] The description herein is provided to enable a person having ordinary skill in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to a person having ordinary skill in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein but is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. A network entity of a wireless communication system, the network entity comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the network entity to: receive a first request to perform a sensing operation, wherein the sensing operation comprises analyzing a set of reflected signals in the wireless communication system to obtain information associated with an environment in proximity to a set of devices in the wireless communication system; transmit a sensing result to a sensing consumer, wherein the sensing result is based at least in part on the sensing operation; transmit a second request for feedback associated with the sensing result from the sensing consumer; receive the feedback from the sensing consumer based at least in part on the second request; and trigger an update of a sensing model or a sensing operability based at least in part on the received feedback from the sensing consumer.

2. The network entity according to claim 1, wherein the second request comprises a subscription to receive the feedback in response to an occurrence of an event, and wherein the subscription corresponds to a previous subscription of the network entity to the sensing consumer.

3. The network entity according to claim 1, wherein the second request comprises an on-demand request.

4. The network entity according to any preceding claim, wherein the at least one processor is further configured to cause the network entity to: receive from the sensing consumer an indication prior to, during, or after receiving the feedback, wherein the indication comprises: a type of feedback; an availability of the type of feedback; a duration for reporting the feedback; or an accuracy value of the feedback, or a combination thereof.

5. The network entity according to any preceding claim, wherein the second request comprises timing information for generating and transmitting the feedback, or wherein the second request comprises event information associated with an evaluation performance parameter.

6. The network entity according to any preceding claim, wherein the second request is a dedicated request, or wherein the request is included in the sensing result notification signaling.

7. The network entity according to any preceding claim, wherein the feedback comprises at least one evaluation performance parameter associated with one or more of: a sensing accuracy of the sensing result based at least in part on a presence or an absence of a target sensing object or a sensing event; a sensing perception of a target sensing object or a target sensing event; a sensing accuracy associated with a geometry of the target sensing object or a location of the target sensing object, or both; a sensing mobility characteristic associated with a mobility state of the sensing objection, a speed of the sensing object, or a direction of the sensing target object, or a combination thereof; a sensing service characteristic associated with a latency of the sensing result, a sensing refresh rate of the sensing result, or a reliability of the sensing result; and an indication that the sensing result was not used including optionally the reason why the sensing result was not used; or a combination thereof.

8. The network entity according to any preceding claim, wherein the feedback comprises a confidence score associated with a set of evaluation performance parameters included in the feedback.

9. The network entity according to any preceding claim, wherein the feedback comprises collected data from the sensing consumer, and wherein the at least one processor is further configured to cause the network entity to verify a set of evaluation of performance parameters included in the feedback based at least in part on the collected data from the sensing consumer.

10. The network entity according to any preceding claim, wherein the feedback comprises at least one evaluation performance parameter and wherein the at least one processor is further configured to cause the network entity to associate the at least one evaluation performance parameter with one or more of: a first identifier associated with the sensing operation; a second identifier of a target object or an event that corresponds to the target object; a third identifier that indicates a relation of the sensing result and the feedback; a time window related to the sensing result, the time window being associated with a period over which the sensing customer used the result or a period over which the sensing customer collected the feedback; a geographical area related to the sensing result; or a timestamp related to the feedback.

11. The network entity according to any preceding claim, wherein the sensing consumer comprises an application function, AF.

12. The network entity of claim 11, further comprising: an interface configured to cause the network entity to: output, to a network exposure function, NEF, sensing signaling exchanged with the AF.

13. The network entity according to any preceding claim, wherein the sensing model or other functionality used to determine the sensing result is an Artificial Intelligence or Machine Learning model.

14. A method performed by a network entity of a wireless communication system, the method comprising: receiving a first request to perform a sensing operation, wherein the sensing operation comprises analyzing a set of reflected signals in the wireless communication system to obtain information associated with an environment in proximity to a set of devices in the wireless communication system; transmitting a sensing result to a sensing consumer, wherein the sensing result is based at least in part on the sensing operation; transmitting a second request for feedback associated with the sensing result from the sensing consumer; receiving the feedback from the sensing consumer based at least in part on the second request; and triggering an update of a sensing model or a sensing operability based at least in part on the received feedback from the sensing consumer.

15. The method according to claim 14, wherein the second request comprises a subscription to receive the feedback in response to an occurrence of an event, and wherein the subscription corresponds to a previous subscription of the network entity to the sensing consumer.

16. The network entity according to claim 14, wherein the second request comprises an on-demand request.

17. The method according to any of claims 14 to 16 and comprising: receiving from the sensing consumer an indication prior to, during, or after receiving the feedback, wherein the indication comprises: a type of feedback; an availability of the type of feedback; a duration for reporting the feedback; or an accuracy value of the feedback, or a combination thereof.

18. The method of any one of claims 14 to 17, wherein the second request comprises timing information for generating and transmitting the feedback, or wherein the second request comprises event information associated with an evaluation performance parameter.

19 Apparatus for use external to a wireless communication system and having an interface for communicating with a network entity of the wireless communication system, the apparatus configured to operate as a sensing consumer and comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the apparatus to: send to the network entity a first request to perform a sensing operation, wherein the sensing operation comprises analyzing a set of reflected signals in the wireless communication system to obtain information associated with an environment in proximity to a set of devices in the wireless communication system; receive a sensing result from the network entity, wherein the sensing result is based at least in part on the sensing operation; receive from the network entity a second request for feedback associated with the sensing result from the sensing consumer; and send feedback to the network entity based at least in part on the second request.

20. A method performed by apparatus external to a wireless communication system and having an interface for communicating with a network entity of the wireless communication system, the apparatus configured to operate as a sensing consumer, and the method comprising: sending to the network entity a first request to perform a sensing operation, wherein the sensing operation comprises analyzing a set of reflected signals in the wireless communication system to obtain information associated with an environment in proximity to a set of devices in the wireless communication system; receiving a sensing result from the network entity, wherein the sensing result is based at least in part on the sensing operation; receiving from the network entity a second request for feedback associated with the sensing result from the sensing consumer; and sending feedback to the network entity based at least in part on the second request.