Wireless device and wireless communication method

Abstract

A wireless device according to the present invention is provided with: a control unit that generates a frame including an AIML data acquisition subfield that instructs transmission of data to a station (STA) corresponding to artificial intelligence / machine learning (AI / ML); and a communication unit that transmits the generated frame.

Description

Technical Field

[0001] The present disclosure relates to a wireless device and a wireless communication method. Background Art

[0002] Industry and academia are researching wireless LAN (Local Area Network) technologies for artificial intelligence (AI) and machine learning (ML) (for example, Non-Patent Document 1).

[0003] In the IEEE (the Institute of Electrical and Electronics Engineers) 802.11 section, a TIG (Topic Interest Group) related to AI / ML (hereinafter also referred to as AIML) was launched in July 2022 and research began (for example, non-patent document 2).

[0004] As one of the technologies being studied for wireless LAN applications, research on CSI compression with the purpose of reducing the amount of channel state information (CSI) feedback, as well as research on distributed channel access (Distributed channel access) for channel access optimization, beamforming optimization, etc. is underway (for example, non-patent document 3).

[0005] Prior art literature

[0006] Non-patent literature

[0007] Non-patent literature 1: S. Szott, K. Kosek-Szott, P. Gawlowicz, JT Gomez, B.Bellalta, A. Zubow, F. Dressler, "WiFi Meets ML: A Survey on Improving IEEE802.11 Performance with Machine Learning" IEEE Communications Surveys &Tutorials, vol.24, no.3, pp.1843-1893

[0008] Non-Patent Document 2: IEEE 802.11-22 / 847r3, AIML TIG July 2022 Agenda

[0009] Non-Patent Document 3: IEEE 802.11-22 / 950r2, Discussion on Connection between AI / ML & Wireless LAN Summary of the Invention

[0010] Methods and frame structures related to data collection required to perform AI / ML-oriented actions have not yet been studied.

[0011] A wireless device according to an embodiment of the present disclosure includes: a control unit that generates a frame including an AIML data collection subfield, wherein the AIML data collection subfield indicates the sending of data to a station corresponding to artificial intelligence / machine learning, i.e., STA, corresponding to AI / ML; and a communication unit that sends the generated frame.

[0012] A wireless communication method according to an embodiment of the present disclosure includes the following steps: generating a frame including an AIML data acquisition subfield, wherein the AIML data acquisition subfield indicates the sending of data for a station corresponding to artificial intelligence / machine learning, i.e., an STA corresponding to AI / ML; and sending the generated frame.

[0013] Furthermore, these broad or specific embodiments may be implemented by systems, apparatuses, methods, integrated circuits, computer programs, or recording media, or by any combination of systems, apparatuses, methods, integrated circuits, computer programs, and recording media.

[0014] The station (STA) that instructs data collection specifies the AIML Data Collection Subfield (AIML Data Collection Subfield) that instructs data collection for AI / ML and notifies each STA. The designated STA transmits the designated data.

[0015] STA can collect data required for AI / ML-oriented operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This diagram shows an example of the data collection process for AI / ML.

[0017] Figure 2 This diagram shows the interface names and functions in the data collection setup phase.

[0018] Figure 3 This diagram shows the interface names and functions in the data collection phase.

[0019] Figure 4 This diagram shows the interface names and functions at the data acquisition termination stage.

[0020] Figure 5 This diagram shows an example of sending an AIML data collection trigger frame from an AIML initiating STA to multiple AIML peer STAs.

[0021] Figure 6 This figure shows an example of a frame sequence when a beamforming transmitter (beamformer) collects measurement results of a sounding DNP for AIML measurement from a beamforming receiver (beamformee).

[0022] Figure 7 This figure shows another example of a frame sequence in which the beamforming transmitter collects measurement results of a DNP probe for AIML measurement from the beamforming receiver.

[0023] Figure 8 This is a diagram showing an example of the format of a trigger frame used for data acquisition.

[0024] Figure 9 This is a diagram showing the type of trigger frame corresponding to the trigger type subfield value (Trigger TypeSubfield value) specified by the trigger type (Trigger Type).

[0025] Figure 10 This diagram shows each function corresponding to a data collection function ID (Data Collection Function ID).

[0026] Figure 11 This is a diagram showing an example of the AIML model corresponding to the AIML model ID and the types of required information.

[0027] Figure 12 This is a diagram showing an example of the status corresponding to the data collection target ID and the type of required information.

[0028] Figure 13 This is a diagram showing an example of the format of a data collection frame.

[0029] Figure 14 This is a diagram showing a definition example of the Type and Subtype subfields of the Frame Control field.

[0030] Figure 15This is a diagram showing a definition example of a control frame extension value (Control Frame Extension value).

[0031] Figure 16 This is a diagram showing the structure of a data collection action frame.

[0032] Figure 17 This is a diagram showing a structural example of a data collection information element.

[0033] Figure 18 This is a diagram showing the structure of STA.

[0034] Figure 19 This is a diagram showing the structure of another STA. DETAILED DESCRIPTION

[0035] According to one embodiment of the present disclosure, a communication device (also referred to as a STA (station)) can specify an AIML data collection subfield indicating data collection for AI / ML to notify each STA.

[0036] <Data Collection Process>

[0037] Figure 1 An example of the process of data collection for AI / ML is shown. Figure 1 The example process is composed of three phases: AIML data collection establishment phase, AIML data collection phase, and AIML data collection termination phase. The AIML initiator STA is the STA that instructs AIML to collect data, and the AIML peer STA is the STA that receives the instruction.

[0038] The AIML data collection establishment phase is a phase for setting up data collection for AI / ML. The AIML data collection phase is a phase for performing AIML data collection based on the AIML data collection trigger frame. The AIML data collection termination phase is a phase for terminating the data collection settings for AI / ML. Figure 1 In the AIML measurement termination phase, two processes are shown, namely, the process started from the AIML initiator STA and the process started from the AIML peer STA. In the AIML data collection termination phase, only one of the processes can be used.

[0039] SME (station management entity) represents a terminal management function, and MLME (MAC (Media Access Control) sublayer management entity) represents a MAC layer management function.

[0040] The AIML initiator STA is the STA that instructs AIML to collect data, and the AIML peer STA is the STA that receives the instruction to collect AIML data. The AIML initiator STA can perform Figure 1 Documented data collection process for AI / ML.

[0041] The process of AIML data collection and establishment phase is explained. Figure 2 Shown in Figure 1 The interface name (frame name) and function of the data acquisition establishment phase in the data acquisition process example.

[0042] First, the SME of the AIML initiator STA sends an MLME-AIMLDCSETUP.request to the MLME of the AIML initiator STA (S100). The MLME-AIMLDCSETUP.request is a frame requesting the sending of an AIML measurement setup request frame to the AIML peer STA.

[0043] The MLME of the AIML initiator STA that receives the MLME-AIMLDCSETUP.request sends an AIML data collection setup request frame to the MLME of the AIML peer STA (S101). The AIML data collection setup request frame is a frame that instructs the AIML peer STA on the setup of AIML data collection.

[0044] The MLME of the AIML peer STA that receives the AIML data collection setup request frame sends an MLME-AIMLDCSETUP.indication to the SME of the AIML peer STA (S102). The MLME-AIMLDCSETUP.indication is a frame indicating that the AIML data collection setup request frame has been received.

[0045] The SME of the AIML peer STA that receives the MLME-AIMLDCSETUP.indication sends an MLME-AIMLDCSETUP.response to the MLME of the AIML peer STA (S103). The MLME-AIMLDCSETUP.response is a response signal to the MLME-AIMLDCSETUP.indication and is a frame requesting the sending of an AIML Data Collection Setup Response frame.

[0046] The MLME of the AIML peer STA that receives MLME-AIMLDCSETUP.response sends an AIML data collection setup response frame to the MLME of the AIML initiator STA (S104). The AIML data collection setup response frame is a frame that responds to the AIML initiator STA whether the AIML peer STA accepts the AIML data collection setup.

[0047] The MLME of the AIML initiator STA that receives the AIML data collection setup response frame sends MLME-AIMLDCSETUP.confirm to the SME of the AIML initiator STA (S105). MLME-AIMLMSMTSETUP.confirm is a signal indicating that the AIML data collection setup response frame has been received.

[0048] The process of AIML data collection phase is explained. Figure 3 Shown in Figure 1 The interface names and functions of the data collection phase in the data collection process example.

[0049] First, the SME of the AIML initiator STA, having received the MLME-AIMLDCSETUP.confirm frame during the AIML data collection setup phase, sends an MLME-AIMLTBDCRQ.request to the MLME of the AIML initiator STA (S110). The MLME-AIMLTBDCRQ.request is a frame for the AIML peer STA requesting trigger-based AIML data collection. For example, the AIML data collection trigger frame is used to perform data collection for AIML.

[0050] The MLME of the AIML initiator STA that receives the MLME-AIMLTBDCRQ.request sends an AIML data collection trigger frame to the MLME of the AIML peer STA (S111). The AIML data collection trigger frame specifies the format of AIML data collection to the AIML peer STA and includes an AIML data collection subfield.

[0051] The MLME of the AIML peer STA that receives the AIML Data Collection Trigger frame sends an AIML Data Collection Report frame to the MLME of the AIML initiator STA (S112). The AIML Data Collection Report frame is a frame that reports the data collection results of the AIML data collection to the initiator STA. The AIML Data Collection Report frame is sent in the format specified in the AIML Data Collection Trigger frame.

[0052] The MLME of the AIML peer STA that receives the AIML data collection trigger frame sends an MLME-AIMLTBREPORTRQ.confirm to the SME of the AIML peer STA (S113). The MLME-AIMLTBREPORTRQ.confirm is a frame that reports the result of sending the AIML data collection report frame.

[0053] The MLME of the AIML initiator STA that receives the AIML data collection report frame sends an MLME-AIMLTBDCRQ.confirm to the SME of the AIML initiator STA (S114). The MLME-AIMLTBDCRQ.confirm is a frame indicating that the AIML data collection report frame has been received.

[0054] Figure 1 The example in which the MLME notifies the SME of the received data collection result report via MLME-AIMLTBDCRQ.confirm is shown. However, the measurement results may also be notified via an external application or a higher layer.

[0055] Figure 1 While the example shows the measurement results being transmitted to the target STA, it is also possible to utilize the measurement results without transmitting them. Alternatively, it is possible to both transmit the measurement results to the target STA and utilize the measurement results at the source STA. The SME or MLME may include an application that utilizes the measurement results.

[0056] Regarding the AIML data collection termination phase, the process starting from the AIML initiator STA and the process starting from the AIML peer STA are explained. Figure 4 Shown in Figure 1 The interface name and function of the data collection termination phase in the data collection process example.

[0057] When the AIML measurement termination phase starts from the AIML initiator STA, first, the SME of the AIML initiator STA sends an MLME-AIMLDCTERMINATION.request to the MLME of the AIML initiator STA (S130). The MLME-AIMLDCTERMINATION.request is a frame requesting the sending of an AIML Data Collection Setup Termination frame.

[0058] The MLME of the AIML initiator STA that receives the MLME-AIMLDCTERMINATION.request sends an AIML data collection setup termination frame to the MLME of the AIML peer STA (S131). The AIML data collection setup termination frame is a frame that instructs the cancellation of the setting of AIML data collection.

[0059] The MLME of the AIML peer STA that receives the AIML data collection setup termination frame sends an MLME-AIMLDCTERMINATION.indication to the SME of the AIML peer STA (S132). The MLME-AIMLDCTERMINATION.indication is a frame indicating that the AIML data collection setup termination frame has been received.

[0060] The MLME of the AIML peer STA that receives the AIML data collection establishment termination frame sends an Ack to the MLME of the AIML initiator STA (S133). Ack is an acknowledgment frame.

[0061] The MLME of the AIML initiator STA that receives the Ack sends MLME-AIMLDCTERMINATION.confirm to the SME of the AIML initiator STA (S134). MLME-AIMLDCTERMINATION.confirm is a frame indicating that the AIML data collection setup termination frame has been received and the AIML data collection setting has been released.

[0062] When the AIML measurement termination phase starts from the AIML peer STA, first, the SME of the AIML peer STA sends an MLME-AIMLDCTERMINATION.request to the MLME of the AIML peer STA (S140).

[0063] The MLME of the AIML peer STA that receives the MLME-AIMLDCTERMINATION.request sends an AIML data collection setup termination frame to the MLME of the AIML initiator STA (S141).

[0064] The MLME of the AIML initiator STA that receives the AIML data collection establishment termination frame sends an MLME-AIMLDCTERMINATION.indication to the SME of the AIML initiator STA (S142).

[0065] Furthermore, the MLME of the AIML initiator STA that receives the AIML data collection establishment termination frame sends an Ack to the MLME of the AIML peer STA (S143).

[0066] The MLME of the AIML peer STA that receives the Ack sends MLME-AIMLDCTERMINATION.confirm to the SME of the AIML peer STA (S144).

[0067] Through the above process, a node can specify the data collection format for AI / ML to other nodes.

[0068] The following shows examples of frame sequences of AIML data collection trigger frames and AIML data collection report frames in three AI / ML data collection phases. The AIML data collection report frame can be a TB PPDU (Trigger-based PLCP (Physical Layer Convergence Procedure) Protocol Data Unit).

[0069] <Example 1>

[0070] Figure 5 An example of sending an AIML data collection trigger frame from an AIML initiator STA to multiple AIML peer STAs (eg, AIML peer STA1 and AIML peer STA2) is shown.

[0071] In the AIML data collection trigger frame, each AIML peer STA is assigned an ID and a data collection subfield for AI / ML. Each AIML peer STA responds with the assigned data collection subfield. Figure 5In the example shown, after the AIML data collection trigger frame is sent, each AIML peer STA sends a data collection report frame after a SIFS (Short Inter Frame Space) has passed. Thus, AIML peer STA1 and AIML peer STA2 simultaneously send AIML data collection report frames. Alternatively, each AIML peer STA may send the frames sequentially or after a specified delay. Furthermore, while an example is shown in which an AIML peer STA sends an AIML data collection report frame only once, it may also be specified that the frames are sent periodically.

[0072] <Example 2>

[0073] Figure 6 This figure shows an example of a frame sequence in which a beamforming transmitter (beamformer) collects measurement results of a sounding DNP (null data PPDU) for AIML-oriented measurements from a beamforming receiver (beamformee). The beamforming transmitter is an STA that performs beamforming and transmits, and the beamforming receiver is an STA that receives the beamformed transmission.

[0074] exist Figure 1 In the process, instead of sending the AIML data collection trigger frame, the following processing is performed, that is, first sending an AIML NDP announcement that specifies the format of the sounding NDP for AIML, and after a SIFS after the AIML NDP announcement is sent, sending the AIML sounding NDP as the sounding NDP for AIML, and after a SIFS after the AIML sounding NDP is sent, sending a BFRP (Beamforming Report Poll) trigger frame to request the feedback of AIML Compressed Beamforming / CQI (AIML Compressed Beamforming / CQI) as the measurement result of the AIML sounding NDP. Figure 6 In the example shown in Figure 1, feedback is received from multiple STAs (AIML Beamformer Receiver 1 and AIML Beamformer Receiver 2) using a BFRP trigger frame. Each beamformer receiver transmits AIML Compressed Beamforming / CQI a SIFS after receiving the BFRP trigger frame. Consequently, AIML Compressed Beamforming / CQI is transmitted simultaneously from multiple beamformer receivers.

[0075] <Example 3>

[0076] Figure 7Another example of a frame sequence is shown in which a beamforming transmitter collects DNP measurement results for AIML-oriented measurements from a beamforming receiver. The beamforming transmitter is an STA that performs beamforming and transmits, and the beamforming receiver is an STA that receives the beamformed transmission.

[0077] exist Figure 1 In the embodiment, instead of sending the AIML data collection trigger frame, the following processing is performed, that is, first sending an AIML NDP announcement specifying the format of the sounding NDP for AIML, and sending the AIML sounding NDP as the sounding NDP for AIML after SIFS after the sending of the AIML NDP announcement. After SIFS after the sending of the AIML sounding NDP, feedback of AIML compressed beamforming / CQI as the measurement result of the AIML sounding NDP is received from a specific STA (e.g., AIML beamforming receiver 1). After SIFS after receiving the AIML compressed beamforming / CQI, the beamforming sender sends a beamforming report poll and receives feedback of AIML compressed beamforming / CQI as the measurement result of the AIML sounding NDP from another STA (e.g., AIML beamforming receiver 2). After SIFS after receiving the beamforming report poll, the other STA (e.g., beamforming receiver 2) sends feedback of AIML compressed beamforming / CQI.

[0078] As described above, it is possible to instruct each STA to collect data for AI / ML.

[0079] <Implementation Method 1>

[0080] In Embodiment 1, when the trigger type of a trigger frame is a specific value (e.g., 8, which is a currently undefined value), the frame is defined as instructing AIML data collection. Here, an undefined value refers to a value that has not been defined previously but may be newly defined in the future, and is sometimes also referred to as a reserved value or a disregarded value.

[0081] Figure 8 The following table shows an example of the trigger frame format used for data acquisition. The common information (Common Info) of the trigger frame includes the trigger type. The trigger type specifies the type of trigger frame.

[0082] Figure 9 The type (variant) of the trigger frame corresponding to the trigger type subfield value specified by the trigger type is shown in FIG. Figure 9As shown, for example, when the value of the trigger type is 8 which is currently an undefined value, a data collection function subfield (Data Collection Function subfield) is included. Figure 9 An example of trigger type 8 is shown in FIG, but it can also be defined to other undefined values.

[0083] If the trigger type indicates data collection (Trigger Type subfield value = 8), the CommonInfo field contains a list of data collection functions. The list of data collection functions includes the number of users and the data collection functions for each user. The data collection function list is the information sent in the AIML Data Collection subfield.

[0084] The data collection function ID is used to indicate the data collection function. Figure 10 The table shows the data collection function (function variant) corresponding to the data collection function ID. For example, ID=0 is for CSI compression for AIML, ID=1 is for channel access for AIML, ID=2 is for beamforming for AIML, and ID=3 is for beam management for AIML. Functions other than AIML can also be defined in this table.

[0085] The contents of the user information list, which includes user information 1 through n, are determined based on the data collection function specified for each user in the data collection function list. Here, n is the number of users. User information n includes, for example, a node ID, an AIML model ID, and an AIML data collection purpose.

[0086] The node for which the user information n is set is specified by the node ID.

[0087] The AIML model representing the learning method, etc. and the type of required information are specified in accordance with the AIML model ID information. The type of required information may also be specified using a separate table. Figure 11 The following table shows examples of AIML model types (learning types: AIML Model variants) and required information types (Request Info Variant) corresponding to AIML model IDs. For example, AIML model ID = 0 is supervised learning, AIML model ID = 1 is reinforcement learning, and AIML model ID = 2 is unsupervised learning. The required information type can be determined for each learning type or universally for all learning types.

[0088] Alternatively, the configuration information of the AIML model may be determined corresponding to the AIML model ID. Regarding the configuration information of the AIML model, the configuration object may be specified by AP (Access Point) or Non-AP STA, or by the aforementioned node ID.

[0089] In the data collection purpose, the AIML states such as training, inference, monitoring, selection, and update, as well as the type of information required in each state are specified according to the data collection purpose ID. Figure 12 An example of the state (AIML Data Collection Purpose variant) and the type of required information (Request Info variant) corresponding to the data collection purpose ID (AIML Data Collection PurposeID) is shown in the figure. The type of required information can also be determined by a table. For example, AIML Data Collection Purpose ID=0 is training, AIML Data Collection Purpose ID=1 is reasoning, AIML Data Collection Purpose ID=2 is monitoring, AIML Data Collection Purpose ID=3 is selection, and AIML Data Collection Purpose ID=4 is updating. Regarding the type of required information, the type of information can be determined separately for each data collection purpose, or the type of information can be determined universally for all data collection purposes.

[0090] Although described as user information or a user information list, it can also be referred to as STA information, per STA information (Per STA Info), or a STA information list. Although it is assumed here that the elements of user information n include the node ID, AIML model ID, and AIML data collection purpose, it can also be composed within the trigger-dependent user information (Trigger Dependent User Info) within the user information field.

[0091] In this way, when the trigger type of the trigger frame is a specific value, it is defined as a frame including a data acquisition subfield, and a data acquisition function list is set, thereby enabling the data acquisition format for AI / ML to be specified for each user.

[0092] <Implementation Method 2>

[0093] In implementation mode 2, when the subtype value or the control frame extension value (Control Frame Extension value) of the frame control field is a specific value (for example, the subtype value is 0001 or the control frame extension value is 1100, etc. (these are currently undefined values)), it is defined as a frame indicating AIML data collection.

[0094] Figure 13 An example of the format of a data acquisition frame is shown in FIG. The data acquisition frame includes a frame control field. The frame control field includes type and subtype subfields.

[0095] Figure 14 The definition example of the type and subtype subfield of the frame control field is shown in FIG. Figure 14 As shown in FIG, when the subtype value of the frame control field is 0001, which is currently an undefined value, it is defined as a frame containing a data acquisition subfield. Figure 14 An example of a subtype value of 0001 is shown in FIG, but it can also be defined on other undefined values.

[0096] When the subtype value of the frame control field is 0110, it has a control frame extension value. Figure 15 The following shows an example of the definition of the control frame extension value. It can be, for example Figure 15 As shown, when the control frame extension value is 1100, which is currently an undefined value, the frame is defined as including the data acquisition subfield. This figure shows an example of the control frame extension value being 1100, but it can also be defined to other currently undefined values.

[0097] As mentioned above, when the subtype value of the frame control field or the control frame extension value is a specific value, a data collection function list is included. The data collection function list includes the number of users and the data collection function of each user. The content of the data collection function ID is the same as Figure 10 The same as the embodiment 1 shown.

[0098] In addition, the content of the user information list including user information 1 to n is also the same as that in implementation mode 1. User information 1 to n includes, for example, node ID, AIML model ID information (AIML Model ID) and data collection purpose (AIML DataCollection Purpose). The content of user information 1 to n is determined according to the data collection function of each user specified in the data collection function list. Regarding the content of user information n, it can be that it includes the same content as in implementation mode 1. It can be that the AIML model ID information is Figure 11 The content shown, the purpose of data collection is Figure 12 The content shown.

[0099] In this way, when the subtype value of the frame control field or the control frame extension value is a specific value, it is defined as a frame containing a data acquisition function list. By setting the data acquisition function list, the data acquisition format for AI / ML can be specified for each user.

[0100] <Implementation Method 3>

[0101] In the third embodiment, when the category (Category) of an action frame (Action frame) is a specific value (for example, 38 which is an undefined value at present), it is defined as a frame instructing data acquisition.

[0102] Figure 16 The structure of the Data Collection Action frame is shown in Figure 1. The action frame contains categories, data collection actions, and data collection elements. The code is defined according to the content of the category field. Figure 16 As shown in FIG, when the category code is 38 (which is currently an undefined value), it is defined as a data acquisition action frame. Figure 16 An example of code 38 is shown in FIG, but it can also be defined to other undefined values.

[0103] If the category is Data Collection, set the Data Collection Action field. The Data Collection Action field defines actions related to data collection, such as Data Collection Request or Data Collection Report. For example, in Figure 16 In the data collection action field, the value of 0 is defined as a data collection request, and the value of 1 is defined as a data collection report.

[0104] The content of the data collection elements (Data Collection Elements) is determined based on whether it is a data collection request or a data collection report.

[0105] In the case of a data collection request, the content of the data collection element is the same as in implementation 1, including a data collection function list and a user information list. The user information list includes user information 1 to n. User information 1 to n includes, for example, a node ID, AIML model ID information (AIML Model ID) and a data collection purpose (AIML Data CollectionPurpose). The AIML model ID information can be Figure 11 The content shown, the purpose of data collection is Figure 12 The content shown.

[0106] In the case of a data collection report, the content of the data collection element is the content of the report indicated in the data collection request.

[0107] In this way, when the type of the action frame is a specific value, it is defined that the action frame includes information on data collection, thereby enabling each user to specify a data collection format for AI / ML.

[0108] <Implementation Method 4>

[0109] In the fourth embodiment, the data collection information element indicating the AIML data collection is notified by a management frame.

[0110] Figure 17 The structure example of the data collection information element is shown in FIG. Alternatively, an element can be identified as a data collection information element by defining an element ID or an element ID extension (Element ID Extension) to a specific value that is an undefined value. Figure 17 As shown, the data collection information element includes a data collection function list and a user information list. The contents of the data collection function list and the user information list are the same as those in implementation 1. The data collection function list includes the number of users and the data collection function of each user. The data collection function is represented by the data collection function ID. Figure 10 The user information list includes user information 1 to n. User information 1 to n includes, for example, node ID, AIML model ID information (AIML Model ID) and data collection purpose (AIML Data Collection Purpose). It can be that the AIML model ID information is Figure 11 The content shown, the purpose of data collection is Figure 12 The content shown.

[0111] The data collection information element constructed in the above manner is included in management frames such as beacon frames, association request / response frames, probe request / response frames, and action frames for notification.

[0112] In this way, by notifying the data collection information element including the information on data collection using the management frame, it is possible to specify the data collection format for AI / ML for each user.

[0113] The interface names (frame names), fields, or subfield names described in Embodiments 1 to 4 may be other names.

[0114] Figure 18 18 shows the structure of STA 1800. STA 1800 includes a control unit 1801, a transmission unit 1802, and a reception unit 1803.

[0115] The control unit 1801 (e.g., corresponding to a control circuit) controls the transmission unit 1802 and the reception unit 1803 based on a signal received by the reception unit 1803 or a signal input from an input unit (not shown) of the STA. Both the SME and the MLME are functions present in the control unit 1801. In another example, the control unit 1801 may include the functions of the MLME and also include a portion of the functions of the SME. In other words, some or all of the functions of the SME may be executed in another communication device other than the STA (not shown, for example, another STA, another access point (AP), a wireless local area network (LAN) controller, a multi-AP coordinator, a cloud server, software as a service (SaaS), or a virtual machine (VM)).

[0116] The transmitting unit 1802 (eg, corresponding to a transmitting circuit) transmits a signal to a counterpart STA.

[0117] The receiving unit 1803 (corresponding to a receiving circuit, for example) receives a signal from a counterpart STA.

[0118] The transmitting unit 1802 and the receiving unit 1803 may be integrated to constitute a communication unit.

[0119] Figure 19 The structure of another STA 1900 is shown. Another STA 1900 includes a control unit 1901 and a communication circuit 1902. The control unit 1901 includes the functions of an SME. The communication circuit 1902 communicates with the other STA (e.g., STA 1800). The control unit 1901 and the communication circuit 1902 can communicate using the communication primitives (messages, signals) between the SME and the MLME described in each embodiment. The control unit 1901 may include a CPU 1911, a memory 1912, and a storage device 1913. The CPU 1911 performs the functions of the SME. The memory 1912 is used when the CPU 1911 performs processing. The storage device 1913 stores software related to the functions of the SME (e.g., binary, executable file, program code, container image). In order to perform the functions of the SME, the CPU 1911 may transfer the software stored in the storage device 1913 to the memory 1912.

[0120] Although the embodiments have been described above with reference to the accompanying drawings, the present disclosure is not limited to these embodiments. It is obvious that those skilled in the art will be able to conceive of various variations or modifications within the scope of the claims. It should be understood that these variations or modifications also fall within the technical scope of the present disclosure. In addition, the various structural elements in the embodiments may be arbitrarily combined without departing from the scope of the present disclosure.

[0121] In the above embodiments, the term "part" used for each component can be replaced by other terms such as "circuitry", "assembly", "device", "unit" or "module".

[0122] The present disclosure can be implemented by software, hardware, or software in collaboration with hardware. The functional blocks used in the description of the above embodiments may also be partially or wholly implemented as an LSI (Large Scale Integration) as an integrated circuit, and the processes described in the above embodiments may also be partially or wholly controlled by one LSI or a combination of LSIs. The LSI may be composed of individual chips, or may be composed of one chip in a manner that includes part or all of the functional blocks. The LSI may also include data input and output. Depending on the degree of integration, the LSI is sometimes also referred to as an "IC (Integrated Circuit)", "system LSI", "super LSI", or "extra LSI".

[0123] Integrated circuit implementation is not limited to LSIs; it can also be achieved using dedicated circuits, general-purpose processors, or dedicated processors. Alternatively, FPGAs (Field Programmable Gate Arrays), which can be programmed after LSI fabrication, or reconfigurable processors (RPs), which allow reconfiguration of the connections and settings of circuit blocks within the LSI, can be utilized. The present disclosure can also be implemented as digital or analog processing.

[0124] Furthermore, if semiconductor technology advances or other technologies evolve and a technology for integrated circuits emerges that replaces LSIs, it would be possible to use this technology to integrate functional blocks. There is also the possibility of applying biotechnology, etc.

[0125] The present disclosure can be implemented in all types of devices, equipment, and systems (collectively referred to as "communication devices") that have communication capabilities. A communication device may also be a wireless communication device (also referred to as a "wireless device"). A communication device may also include a wireless transceiver and processing / control circuitry. The wireless transceiver may also include a receiving unit and a transmitting unit, or perform the functions of these units. The wireless transceiver (transmitting unit, receiving unit) may also include an RF (Radio Frequency) module and one or more antennas. The RF module may also include an amplifier, an RF modulator / demodulator, or similar devices. Non-limiting examples of communication devices include: telephones (mobile phones, smartphones, etc.), tablet computers, personal computers (PCs) (laptops, desktops, notebook computers, etc.), cameras (digital cameras, digital video cameras, etc.), digital players (digital audio / video players, etc.), wearable devices (wearable cameras, smart watches, tracking devices, etc.), game consoles, e-book readers, telehealth / telemedicine (telehealth / medical prescription) devices, vehicles or transportation vehicles with communication capabilities (cars, airplanes, ships, etc.), and combinations of the above devices.

[0126] Communication devices are not limited to portable or mobile devices. They also include all types of devices, equipment, and systems that cannot be portable or fixed. Examples include smart home devices (such as appliances, lighting, smart meters or meters, control panels, etc.), vending machines, and all other "things" that can exist on an IoT (Internet of Things) network.

[0127] Communication includes data communication via a cellular system, a wireless LAN (Local Area Network) system, a communication satellite system, etc., as well as data communication via a combination of these systems.

[0128] Furthermore, the communication device also includes devices such as controllers and sensors that are connected or coupled to the communication equipment performing the communication functions described in the present invention. For example, the communication device may include a controller or sensor that generates control signals or data signals used by the communication equipment performing the communication functions of the communication device.

[0129] In addition, the communication device includes infrastructure equipment that communicates with or controls the above-mentioned non-limiting various devices, such as base stations, access points, and all other devices, equipment, and systems.

[0130] Furthermore, in recent years, CPS (Cyber ​​Physical Systems) has attracted much attention in IoT (Internet of Things) technology as a new concept that creates new added value through information collaboration between physical and cyber spaces. This CPS concept can also be adopted in the above-mentioned embodiment.

[0131] Specifically, as a basic CPS configuration, for example, edge servers located in physical space can be connected to cloud servers located in cyberspace via a network, with distributed processing performed by processors installed on both servers. The data processed by the edge servers or cloud servers is preferably generated on a standardized platform. Using this standardized platform improves the efficiency of building systems that include various sensor systems or IoT application software.

[0132] (1) A wireless device according to an embodiment of the present disclosure includes: a control unit that generates a frame including an AIML data collection subfield, wherein the AIML data collection subfield indicates the transmission of data to a station (STA) corresponding to artificial intelligence / machine learning, i.e., AI / ML; and a communication unit that transmits the generated frame.

[0133] (2) In a wireless device according to an embodiment of the present disclosure, in the wireless device of (1), when the trigger type is a specific value, the frame is defined as

[0134] (3) In a wireless device according to an embodiment of the present disclosure, in the wireless device of (2), the frame includes a data acquisition function and user information, the data acquisition function includes a data acquisition function ID and a data acquisition function, the user information includes an AIML model ID and an AIML data acquisition purpose, the AIML model ID includes an AIML model, i.e., a learning type, and a type of required information, and the AIML data acquisition purpose includes an AIML state and a type of required information

[0135] (4) In the wireless device of one embodiment of the present disclosure, in the wireless device of (1), the frame is defined when a subtype value or a control frame extension value of a frame control field is a specific value.

[0136] (5) In the wireless device according to one embodiment of the present disclosure, in the wireless device according to (1), when the type of the action frame is a specific value, the frame is defined.

[0137] (6) In the wireless device of one embodiment of the present disclosure, in the wireless device of (1), the frame is defined in a management frame.

[0138] (7) A wireless communication method according to an embodiment of the present disclosure includes the following steps: generating a frame including an AIML data acquisition subfield, wherein the AIML data acquisition subfield indicates the sending of data to a station corresponding to artificial intelligence / machine learning, i.e., a STA corresponding to AI / ML; and sending the generated frame.

[0139] The disclosures of the specification, drawings, and abstract of Japanese patent application No. 2023-014580 filed on February 2, 2023 are incorporated herein by reference in their entirety.

[0140] Industrial Applicability

[0141] One embodiment of the present disclosure is useful for wireless devices.

[0142] Description of Reference Numerals

[0143] 1801, 1901 Control Department

[0144] 1802 Sending Department

[0145] 1803 Receiving Department

[0146] 1902 Communication Circuit

[0147] 1911 CPU

[0148] 1912 Memory

[0149] 1913 Storage Device

Claims

1. A wireless device comprising: a control unit, generating a frame including an AIML data collection subfield, wherein the AIML data collection subfield instructs a station (STA) corresponding to artificial intelligence / machine learning (i.e., AI / ML) to send data; and The communication unit transmits the generated frame.

2. The wireless device according to claim 1, wherein In case the trigger type is a specific value, the frame is defined.

3. The wireless device according to claim 2, wherein: The frame contains data collection functions and user information, The data collection function has a data collection function ID and a data collection function, The user information includes the AIML model ID and the AIML data collection purpose. The AIML model ID contains the AIML model, i.e. the learning type and the type of information required. The AIML data collection purpose includes the status of AIML and the type of required information.

4. The wireless device according to claim 1, wherein In case that the subtype value or the control frame extension value of the frame control field is a specific value, the frame is defined.

5. The wireless device according to claim 1, wherein When the type of the action frame is a specific value, the frame is defined. The wireless device according to claim 1 , wherein: The frames are defined in management frames.

7. A wireless communication method comprising the following steps: generating a frame including an AIML data collection subfield, wherein the AIML data collection subfield indicates data transmission to a station corresponding to artificial intelligence / machine learning, i.e., AI / ML; and The generated frame is transmitted.

Images