Coexistence estimation method and apparatus based on wi-fi signals

Abstract

The operation method of the user device can include obtaining a first Wi-Fi RSSI corresponding to a nearby Wi-Fi network of the user device and a plurality of second Wi-Fi RSSIs corresponding to nearby Wi-Fi networks of each of other devices; inputting the first Wi-Fi RSSI and the plurality of second Wi-Fi RSSIs to a coexistence estimation model to estimate whether the other devices exist in the same space as the user device; generating a feedback dataset including the first Wi-Fi RSSI and the plurality of second Wi-Fi RSSIs based on feedback on the estimation result; generating a filtered dataset by filtering a pre-collected first Wi-Fi RSSI and a pre-collected plurality of second Wi-Fi RSSIs according to a preset condition; and updating the coexistence estimation model by using the feedback dataset and the filtered dataset.

Description

Technical Field

[0001] This disclosure relates to a method and apparatus for coexistence between Wi-Fi signal estimation devices and for optimizing an artificial intelligence model for estimating coexistence. Background Technology

[0002] Technology utilizing Wi-Fi signals has been used to estimate the location of devices in indoor environments. Furthermore, with the increasing use of artificial intelligence (AI) across various fields, it can also be applied to techniques for estimating the location of devices in indoor environments. However, even when using AI, the inference results may not always be reliable because they can be inaccurate depending on the user's specific environment. Therefore, user feedback can be used as training data, but it is difficult to ensure that training data suitable for the user's environment is based solely on user feedback. Summary of the Invention

[0003] Solution to the problem According to one aspect of this disclosure, a method of operating a user device can be provided. The method may include: obtaining a first Wi-Fi Received Signal Strength Indicator (RSSI) corresponding to a nearby Wi-Fi network of the user device. The method may include: obtaining a plurality of second Wi-Fi RSSIs corresponding to nearby Wi-Fi networks of each of other devices. The method may include: estimating whether the other devices exist in the same space as the user device by applying the first Wi-Fi RSSI and the plurality of second Wi-Fi RSSIs as input data to a coexistence estimation model. The method may include: receiving feedback regarding the estimation results. The method may include: generating a feedback dataset including the first Wi-Fi RSSI and the plurality of second Wi-Fi RSSIs based on the feedback. The method may include obtaining pre-collected first Wi-Fi RSSIs and a plurality of pre-collected second Wi-Fi RSSIs. The method may include: generating a filtered dataset by filtering the pre-collected first Wi-Fi RSSIs and the plurality of pre-collected second Wi-Fi RSSIs according to preset conditions. The method may include updating the coexistence estimation model using the feedback dataset and the filtered dataset.

[0004] According to one aspect of this disclosure, a user equipment may be provided. The user equipment may include: a communication interface; a memory storing one or more instructions; and one or more processors configured to execute the one or more instructions stored in the memory. The one or more processors may execute the one or more instructions to obtain a first Wi-Fi RSSI corresponding to a nearby Wi-Fi network of the user equipment. The one or more processors may execute the one or more instructions to obtain a plurality of second Wi-Fi RSSIs corresponding to nearby Wi-Fi networks of each of other devices. The one or more processors may execute the one or more instructions to estimate whether the other devices exist in the same space as the user equipment by applying the first Wi-Fi RSSI and the plurality of second Wi-Fi RSSIs as input data to a coexistence estimation model. The one or more processors may execute the one or more instructions to receive feedback regarding the estimation results. The one or more processors may execute the one or more instructions to generate a feedback dataset including the first Wi-Fi RSSI and the plurality of second Wi-Fi RSSIs based on the feedback. The one or more processors may execute the one or more instructions to obtain pre-collected first Wi-Fi RSSIs and a plurality of pre-collected second Wi-Fi RSSIs. The one or more processors may execute the one or more instructions to generate a filtered dataset by filtering a pre-collected first Wi-Fi RSSI and the plurality of pre-collected second Wi-Fi RSSIs according to preset conditions. The one or more processors may execute the one or more instructions to update the coexistence estimation model by using the feedback dataset and the filtered dataset.

[0005] According to one aspect of this disclosure, a computer-readable recording medium having a program recorded thereon is provided for performing any one of the methods described above and below in relation to the operation of a user device. Attached Figure Description

[0006] Figure 1 This is a diagram illustrating the operation performed by a user device to estimate its location indoors according to an embodiment of the present disclosure.

[0007] Figure 2 This is a diagram illustrating personalized operations for an artificial intelligence model used to estimate whether a user device exists in the same space as another device, according to an embodiment of the present disclosure.

[0008] Figure 3 This is a diagram illustrating the operation of a copresence estimation model used by a user device according to an embodiment of this disclosure.

[0009] Figure 4a This is a diagram illustrating the operation performed by a user device according to an embodiment of the present disclosure to obtain feedback on the results of a coexistence estimate.

[0010] Figure 4b This is a diagram illustrating the operation of generating feedback data performed by a user device according to an embodiment of the present disclosure.

[0011] Figure 5a This is a diagram illustrating data collection operations of a user device and another device according to embodiments of the present disclosure.

[0012] Figure 5b This is a diagram illustrating the operation of generating a filtered dataset performed by a user device according to an embodiment of the present disclosure.

[0013] Figure 6 This is a diagram illustrating a training dataset generated by a user device according to an embodiment of the present disclosure.

[0014] Figure 7a This is a flowchart illustrating a method of operating a user device when receiving feedback according to an embodiment of the present disclosure.

[0015] Figure 7b To show in more detail Figure 7a The flowchart of the operation.

[0016] Figure 8 This is a diagram illustrating the operations performed by a user device to generate a training dataset according to an embodiment of the present disclosure.

[0017] Figure 9 This is a diagram illustrating the operations performed by a user device to generate a training dataset according to an embodiment of the present disclosure.

[0018] Figure 10 This is a diagram illustrating operations performed by a user device using a coexistence estimation model according to an embodiment of the present disclosure.

[0019] Figure 11 This is a block diagram illustrating the configuration of a user device according to an embodiment of the present disclosure. Detailed Implementation

[0020] The terminology used in this specification will be briefly described, and this disclosure will be described in detail. In this disclosure, the expression "at least one of a, b, or c" may refer to "a", "b", "c", "a and b", "a and c", "b and c", "all of a, b, and c", or variations thereof.

[0021] The terms used in this disclosure have been selected from commonly used terms in general terms, taking into account their function in this disclosure; however, these terms may vary depending on the intent of those skilled in the art, precedent, or the emergence of new technologies. Additionally, in certain cases, terms of arbitrary choice by the applicant may be used, and in such cases, their meanings will be described in detail in the relevant descriptive section. Therefore, the terms used in this disclosure should be defined based on their meanings and the overall content of this disclosure, rather than simply on their names.

[0022] Unless the context clearly indicates otherwise, singular expressions may include plural expressions. The terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art described herein. Furthermore, although terms including ordinal numbers (such as “first” and “second”) may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used only to distinguish one element from another.

[0023] Throughout this specification, when a component is referred to as "including" an element, it will be understood that, unless otherwise stated to the contrary, other elements are not excluded and may be further included. Furthermore, terms such as "...unit" and "module" as used in this specification refer to a unit that performs at least one function or operation and can be implemented in hardware, software, or a combination of hardware and software.

[0024] In the following, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings to enable those skilled in the art to readily implement the disclosure. However, the present disclosure may be implemented in many different forms and is not limited to the embodiments described herein. Furthermore, in the drawings, portions irrelevant to the description have been omitted for clarity, and throughout the specification, the same elements are indicated by the same reference numerals.

[0025] The present disclosure will be described below with reference to the accompanying drawings.

[0026] Figure 1 This is a diagram illustrating the operation performed by a user device to estimate its location indoors according to an embodiment of the present disclosure.

[0027] Reference Figure 1 According to an embodiment, the user device 2000 can estimate its relative position to a plurality of other devices 100 in the room. For example, the user device 2000 can estimate whether the user device 2000 is located in the same space as each of the other devices 100 or in a different space from each of the other devices 100.

[0028] In embodiments, the term "space" may refer to a three-dimensional environment physically separated by spatial layout (e.g., floors, walls, columns, ceilings, etc.). For example, assuming a user's home environment, room A 110, room B 120, room C 130, and living room 140 may each be referred to as a space. Figure 1 In the example, when the smartphone is in living room 140 and the TV is in room B 120, the smartphone and the TV can be considered to exist in different spaces.

[0029] In this embodiment, user device 2000 and other devices 100 may be communicatively connected to interact with each other. For example, user device 2000 and other devices 100 may be connected to the same network (e.g., home Wi-Fi). Optionally, user device 2000 and other devices 100 may be connected to the same server (e.g., cloud server), but are not limited thereto.

[0030] User device 2000 may include various types of devices. For example, user device 2000 may be a mobile device (such as a tablet PC or smartphone). Other devices 100 may include various types of devices. Other devices 100 may include, for example, various household appliances such as washing machines, dryers, vacuum cleaners, robotic vacuum cleaners, air conditioners, laundry managers, air purifiers, and dishwashers, but are not limited thereto. In embodiments, a user may use user device 2000 to manage and control other devices 100. User device 2000 may receive user input and, based on the received user input, request information from or control multiple other devices 100.

[0031] In an embodiment, user device 2000 may estimate whether other devices 100 exist in the same space as the user device. In this case, user device 2000 may estimate the coexistence or non-coexistence between devices by using a coexistence estimation model as an artificial intelligence model. User device 2000 may optimize the coexistence estimation model to fit the user space. To optimize the coexistence estimation model, user device 2000 may collect and process data to generate training data.

[0032] The specific operations performed by the user device 2000 for collecting data for training the coexistence estimation model and fine-tuning the coexistence estimation model will be described in more detail with reference to the accompanying drawings and descriptions provided below.

[0033] Figure 2 This is a diagram illustrating personalized operations for an artificial intelligence model used to estimate whether a user device exists in the same space as another device, according to an embodiment of the present disclosure.

[0034] In operation S210, user equipment 2000 can obtain a Wi-Fi RSSI corresponding to a nearby Wi-Fi network. In this disclosure, the Wi-Fi RSSI received by user equipment 2000 may be referred to as the first Wi-Fi RSSI.

[0035] In an embodiment, the user device 2000 may obtain an RSSI value, which indicates the received strength of a Wi-Fi signal received through a communication circuit (e.g., a Wi-Fi card, etc.) included in the communication interface. The RSSI may be a value expressed in dBm.

[0036] In this embodiment, when multiple Wi-Fi routers or wireless access points (APs) are present near the user device 2000, multiple RSSI values ​​may be provided. For example, the RSSI may be a sequence of values ​​corresponding to nearby Wi-Fi networks.

[0037] During operation S220, user device 2000 can obtain multiple Wi-Fi RSSIs corresponding to the nearby Wi-Fi networks of each of the other devices. In this disclosure, the Wi-Fi RSSI received by a device other than user device 2000 may be referred to as the second Wi-Fi RSSI. In other words, to distinguish the Wi-Fi RSSI of user device 2000 from the Wi-Fi RSSI of any other device, the Wi-Fi RSSI of user device 2000 will be referred to as the first Wi-Fi RSSI, and the Wi-Fi RSSI of any other device will be referred to as the second Wi-Fi RSSI. However, both the first Wi-Fi RSSI and the second Wi-Fi RSSI essentially refer to the Wi-Fi RSSI normally obtained by the device.

[0038] In this embodiment, the number of other devices can be two or more. For example, user device 2000 can receive the Wi-Fi RSSI of device A from device A, which is another device, and receive the Wi-Fi RSSI of device B from device B, which is another device. In other words, user device 2000 can obtain multiple second Wi-Fi RSSIs corresponding to other devices respectively. Continuing the above example, the multiple second Wi-Fi RSSIs may include the Wi-Fi RSSI of device A and the Wi-Fi RSSI of device B.

[0039] In operation S230, user equipment 2000 can estimate whether other devices exist in the same space as user equipment 2000 by applying the first Wi-Fi RSSI and multiple second Wi-Fi RSSIs as input data to a coexistence estimation model.

[0040] In an embodiment, the coexistence estimation model can be an artificial intelligence model trained to receive the Wi-Fi RSSI of two devices as input and estimate whether the two devices exist in the same space.

[0041] User equipment 2000 can input input data, including a first Wi-Fi RSSI and a second Wi-Fi RSSI, into a coexistence estimation model. The plurality of second Wi-Fi RSSIs include the Wi-Fi RSSIs of various devices other than user equipment 2000. For example, the plurality of second Wi-Fi RSSIs may include the Wi-Fi RSSI of device A and the Wi-Fi RSSI of device B. For example, user equipment 2000 can input the first Wi-Fi RSSI and the Wi-Fi RSSI of device A from the plurality of second Wi-Fi RSSIs into the coexistence estimation model to estimate whether device A exists in the same space as user equipment 2000. Alternatively, for example, user equipment 2000 can input the first Wi-Fi RSSI and the Wi-Fi RSSI of device B from the plurality of second Wi-Fi RSSIs into the coexistence estimation model to estimate whether device B exists in the same space as user equipment 2000.

[0042] During operation S240, user device 2000 can receive feedback regarding the estimation results. User device 2000 can obtain user input from the user for inputting feedback.

[0043] In this embodiment, feedback may include positive feedback. Positive feedback can indicate that the estimation result of the coexistence estimation model is accurate. For example, user device 2000 may estimate that device A exists in the same space as user device 2000, or it may estimate that device A exists in a different space. When the estimation result of user device 2000 is accurate, the user may input user input indicating positive feedback.

[0044] In this embodiment, feedback may include negative feedback. Negative feedback may indicate that the estimation result of the coexistence estimation model is inaccurate. For example, user device 2000 may estimate that device B exists in the same space as user device 2000, or may estimate that device B exists in a different space. When the estimation result of user device 2000 is inaccurate, the user may input user input indicating negative feedback.

[0045] In an embodiment, user device 2000 may request feedback from the user. For example, user device 2000 may output a result estimating whether user device 2000 and another device (e.g., device A and / or device B) exist in the same space, and perform a feedback request function for requesting the accuracy / inaccuracy of the estimation result. In response to the feedback request, user device 2000 may obtain user input for inputting feedback regarding the estimation result of coexistence or non-coexistence.

[0046] In this embodiment, user device 2000 may be a mobile device (e.g., a smartphone, etc.). Alternatively, other devices may be devices with relatively low mobility (e.g., a TV, etc.). Therefore, the location information of another device (e.g., room A, room B, living room, etc.) may be pre-stored therein. This location information of the other device may be input by the user. In this embodiment, feedback may include the location information of user device 2000. User device 2000 may receive its current location information (e.g., room A, room B, living room, etc.). The current location information of user device 2000 may be used to match the location information of the other device.

[0047] During operation S250, the user device 2000 can generate a feedback dataset including a first Wi-Fi RSSI and multiple second Wi-Fi RSSIs based on the feedback.

[0048] In an embodiment, the user device may generate data pairs to be included in the feedback dataset based on the estimation results obtained in operation S230 and the user feedback obtained in operation S240. For example, user device 2000 may generate positive pairs, which are data pairs indicating that another device exists in the same space as user device 2000. Alternatively, for example, user device 2000 may generate negative pairs, which are data pairs indicating that another device exists in a different space than user device 2000.

[0049] In other words, the feedback dataset may include multiple data pairs, each data pair including {first Wi-Fi RSSI, second Wi-Fi RSSI}, and each data pair may be annotated with information indicating whether the device exists in the same space or in different spaces.

[0050] During operation S260, user equipment 2000 can obtain a first Wi-Fi RSSI that has been pre-collected and a plurality of second Wi-Fi RSSIs that have been pre-collected.

[0051] A first pre-collected Wi-Fi RSSI can be collected periodically or non-periodically from user equipment 2000. Multiple pre-collected second Wi-Fi RSSIs can be collected periodically or non-periodically from other devices. For example, the multiple pre-collected second Wi-Fi RSSIs may include Wi-Fi RSSIs pre-collected from device A and Wi-Fi RSSIs pre-collected from device B. User equipment 2000 can receive the pre-collected second Wi-Fi RSSIs from each of the other devices.

[0052] In this embodiment, operation S260 may be performed only when feedback from operation S240 is received. User device 2000 may perform operation S260 in response to receiving feedback. Based on the received feedback, user device 2000 may update the coexistence estimation model by performing operations S270 to S280 as described below.

[0053] In operation S270, the user device 2000 can generate a filtered dataset by filtering a first pre-collected Wi-Fi RSSI and a plurality of pre-collected second Wi-Fi RSSIs according to preset conditions.

[0054] In an embodiment, user device 2000 can use pre-collected first Wi-Fi RSSIs and multiple pre-collected second Wi-Fi RSSIs as input data to a coexistence estimation model. By using the coexistence estimation model, user device 2000 can estimate whether another device exists in the same space as user device 2000 at the time the Wi-Fi RSSIs were collected. For example, user device 2000 can input the Wi-Fi RSSI of device A from the pre-collected first Wi-Fi RSSIs and multiple pre-collected second Wi-Fi RSSIs into the coexistence estimation model to estimate whether device A exists in the same space as user device 2000 at a given time. Furthermore, for example, user device 2000 can input the Wi-Fi RSSI of device B from the pre-collected first Wi-Fi RSSIs and multiple pre-collected second Wi-Fi RSSIs into the coexistence estimation model to estimate whether device B exists in the same space as user device 2000 at a given time.

[0055] In one embodiment, preset conditions can be defined based on the number of devices present in the same space as user device 2000, and user device 2000 filters data according to these preset conditions. User device 2000 can determine whether to filter pre-collected first Wi-Fi RSSIs and multiple pre-collected second Wi-Fi RSSIs based on the estimated number of other devices present in the same space as user device. Figure 5a and Figure 5b The description further describes the preset conditions.

[0056] User device 2000 can generate a filtered dataset by filtering out bad data and leaving only good data from a pre-collected first Wi-Fi RSSI and multiple pre-collected second Wi-Fi RSSIs. The filtered dataset may include multiple data pairs, each data pair including {first Wi-Fi RSSI, second Wi-Fi RSSI}, and each data pair may be annotated with information indicating whether the device exists in the same space or in different spaces.

[0057] During operation S280, user device 2000 can update the coexistence estimation model by using the feedback dataset and the filtered dataset.

[0058] In this embodiment, the feedback dataset and the filtered dataset include Wi-Fi RSSI collected within the user's space. The user device 2000 can fine-tune the coexistence estimation model by using the feedback dataset and the filtered dataset as training datasets. The user device 2000 can increase the accuracy of coexistence estimation within the user's space by training with the feedback dataset. In this regard, it is difficult to ensure a large amount of feedback data, and it may take a long time to ensure a sufficient amount of data. By using a filtered dataset that complements the feedback dataset for training, the user device 2000 can increase the accuracy of the coexistence estimation model while allowing feedback to be reflected earlier.

[0059] In one embodiment, user device 2000 may assign higher weights to the feedback dataset than to the filtered dataset. User device 2000 can update the coexistence estimation model using these weights, so that insufficient feedback data is reflected in a higher proportion.

[0060] Figure 3 This is a diagram illustrating the operation of a coexistence estimation model used by a user device according to an embodiment of this disclosure.

[0061] In this disclosure, unless otherwise stated, the term "model" refers to coexistence estimation model 300. Coexistence estimation model 300 may be an artificial intelligence model trained to receive input data 310 including pairs of data from two different devices and output an estimate of whether the two different devices exist in the same space or different spaces.

[0062] Reference Figure 3 User device 2000 can perform inference operations by inputting input data 310 into coexistence estimation model 300.

[0063] In an embodiment, input data 310 may include a first Wi-Fi RSSI 312 and a second Wi-Fi RSSI 314. The first Wi-Fi RSSI 312 may correspond to a nearby Wi-Fi network of the user device 2000, and the second Wi-Fi RSSI 314 may correspond to a nearby Wi-Fi network of another device. Figure 3In the example, the first Wi-Fi RSSI 312 indicates the signal strength received by user device 2000 from each of ten wireless access points near user device 2000, and the second Wi-Fi RSSI 314 indicates the signal strength received by the other device from each of ten wireless access points near the other device. User device 2000 can input input data 310, including the first Wi-Fi RSSI 312 and the second Wi-Fi RSSI 314, into the coexistence estimation model 3000 to estimate whether user device 2000 and the other device exist in the same space. In this case, the Wi-Fi RSSI for each pair used for coexistence estimation can be obtained from the respective devices within the same time period.

[0064] In embodiments, the coexistence estimation model 300 can be implemented using deep neural network architectures and artificial intelligence algorithms for performing classification tasks, or it can be implemented by modifying known deep neural network architectures and artificial intelligence algorithms. For example, the coexistence estimation model 300 can be implemented by a deep neural network model including one or more multilayer perceptrons (MLPs) (which include layers containing weights), and can be implemented by a deep neural network model based on a transformer architecture including an attention mechanism, but is not limited thereto.

[0065] In an embodiment, the coexistence estimation model 300 may be a pre-trained model. The coexistence estimation model 300 can be trained using correct data including Wi-Fi RSSI data pairs. The correct data may be annotated with information indicating whether two devices exist in the same space. In this case, Wi-Fi RSSI data pairs labeled as "same space" may be referred to as positive pairs, and Wi-Fi RSSI data pairs labeled as "different spaces" may be referred to as negative pairs.

[0066] The term "pre-trained model" can be referred to by various expressions that indicate the same or similar concepts. For example, a pre-trained model can be referred to by expressions such as "base model," "pre-fine-tuned model," and "pre-updated model," but is not limited to the examples above.

[0067] In one embodiment, user device 2000 may generate data for updating coexistence estimation model 300. User device 2000 may generate a training dataset for personalizing coexistence estimation model 300 by using data collected when the user device operates in the user's space. User device 2000 may fine-tune the base model using the training dataset. In other words, user device 2000 may optimize coexistence estimation model 300 to operate appropriately in the user's space.

[0068] The data used to update the coexistence estimation model 300 may include feedback data generated based on user feedback, as well as filtered data obtained by filtering out high-quality data from pre-collected data. Specific operations performed by the user device 2000 to generate the data for updating the coexistence estimation model 300 will be described in detail in the description of the accompanying drawings below.

[0069] Furthermore, the optimization of coexistence estimation model 300 aims to improve the performance of coexistence estimation in the user's space. Therefore, the updated coexistence estimation model 300 can be referred to as an "optimized model," "personalized model," "customized model," "fine-tuned model," "updated model," etc., and can also be referred to by various expressions indicating the same or similar concepts as the examples above.

[0070] Figure 4a This is a diagram illustrating the operation performed by a user device according to an embodiment of the present disclosure to obtain feedback on the results of a coexistence estimate.

[0071] In an embodiment, user device 2000 may estimate whether each of a plurality of other devices exists in the same space as user device 2000. Figure 4b An example is shown where device A 400 in another device is estimated to coexist or not and feedback data is generated.

[0072] In one embodiment, user device 2000 may perform a coexistence estimation task to infer whether device A 400 exists in the same space as user device 2000. The coexistence estimation task may be initiated based on user input used to perform the coexistence estimation function.

[0073] User device 2000 can estimate whether device A 400 exists in the same space as user device 2000 by inputting the Wi-Fi RSSI of user device 2000 and the Wi-Fi RSSI of device A 400 into coexistence estimation model 410. User device 2000 can obtain feedback on the estimation result. The feedback may include information indicating that the estimation result is inaccurate (or information indicating that the estimation result is accurate). In addition, the feedback may include the location information of user device 2000 and / or the location information of device A 400.

[0074] Referring to the first example 402, user device 2000 exists in a different space than device A 400. User device 2000 can input a first Wi-Fi RSSI A 420, which is the Wi-Fi RSSI of user device 2000, and a second Wi-Fi RSSI A 430, which is the Wi-Fi RSSI of device A 400, into the coexistence estimation model 410. At this time, the estimation result of the coexistence estimation model 410 can be output as "same space". Because user device 2000 and device A 400 exist in different spaces, the estimation result in the first example 402 is an incorrect prediction.

[0075] Referring to the second example 404, user device 2000 exists in the same space as device A 400. User device 2000 can input the first Wi-Fi RSSI B 422, which is the Wi-Fi RSSI of user device 2000, and the second Wi-Fi RSSI B 432, which is the Wi-Fi RSSI of device A 400, into the coexistence estimation model 410, and obtain the output "same space" as the estimation result. Because user device 2000 and device A 400 exist in the same space, the estimation result in the second example 404 is a correct prediction.

[0076] User device 2000 can obtain feedback on the estimation results. Feedback can be obtained in various ways. For example, after the estimation results are output, user device 2000 can receive user input indicating feedback on the estimation results. Alternatively, for example, user device 2000 can output the estimation results and also output a user interface for requesting feedback on the estimation results.

[0077] In an embodiment, feedback may include information indicating that the estimation result is inaccurate and / or the location information of user device 2000. When the feedback includes information indicating that the estimation result is inaccurate, user device 2000 may configure a negative pair based on the feedback. The negative pair includes the Wi-Fi RSSI of user device 2000 and the Wi-Fi RSSI of a plurality of other devices estimated to exist in the same space as user device 2000. The term "negative pair" is a tag indicating that two devices exist in different spaces. Furthermore, when the feedback includes the location information of user device 2000, user device 2000 may configure a positive pair based on the feedback. The positive pair includes the Wi-Fi RSSI of user device 2000 and the Wi-Fi RSSI of a plurality of other devices having location information corresponding to the location information of user device 2000. The term "positive pair" is a tag indicating that two devices exist in the same space. In this case, user device 2000 may receive the location information of a plurality of other devices.

[0078] Referring again to the first example 402, the estimation result in the first example 402 indicates that device A 400 exists in the same space as user device 2000. Because this is an incorrect prediction, the feedback may include information indicating that the estimation result is inaccurate. In this case, user device 2000 may configure a negative pair including a first Wi-Fi RSSI A 420 and a second Wi-Fi RSSI A 430 based on the feedback, wherein the first Wi-Fi RSSI A 420 is the Wi-Fi RSSI of user device 2000, and the second Wi-Fi RSSI A 430 is the Wi-Fi RSSI of device A 400 estimated to exist in the same space as user device 2000. Furthermore, user device 2000 may identify devices with location information corresponding to the location information of user device 2000 among devices other than device A 400, and generate a positive pair of the first Wi-Fi RSSI and the second Wi-Fi RSSI.

[0079] In embodiments, the feedback may include information indicating that the estimation result is accurate. When the feedback includes information indicating that the estimation result is accurate, user device 2000 may configure an affirmative pair including the Wi-Fi RSSI of user device 2000 and the Wi-Fi RSSI of another device based on the feedback. For example, when feedback regarding the estimation result is received in the second example 404, user device 2000 may configure an affirmative pair including a first Wi-Fi RSSI B 422 and a second Wi-Fi RSSI B 432, wherein the first Wi-Fi RSSI B 422 is the Wi-Fi RSSI of user device 2000 and the second Wi-Fi RSSI B 432 is the Wi-Fi RSSI of device A 400.

[0080] Figure 4b This is a diagram illustrating the operation of generating feedback data performed by a user device according to an embodiment of the present disclosure.

[0081] In an embodiment, user device 2000 may generate a feedback dataset 440 based on feedback, which includes a first Wi-Fi RSSI and a second Wi-Fi RSSI of another device.

[0082] In embodiments, multiple other devices may be provided. For example, the multiple other devices may include device A and device B. Feedback data A442 may be obtained based on feedback regarding the estimated coexistence or non-coexistence between user device 2000 and device A. In this case, feedback data A442 may include {first Wi-Fi RSSI A, second Wi-Fi RSSI A} of user device 2000 and device A, as well as feedback information. Similarly, feedback B may include {first Wi-Fi RSSI B, second Wi-Fi RSSI B} of user device 2000 and device B, as well as feedback information.

[0083] User equipment 2000 may generate a feedback dataset 440, in which a first Wi-Fi RSSI and each of a plurality of second Wi-Fi RSSIs are paired and matched. In this regard, when user equipment 2000 estimates coexistence or non-coexistence with each of a plurality of other devices, feedback may be received only for some of the estimation results of the plurality of other devices. In this case, user equipment 2000 may include only the data corresponding to the feedback in the feedback dataset 440. For example, feedback may be obtained regarding the result of estimating coexistence or non-coexistence between user equipment 2000 and device A, and feedback may be obtained regarding the result of estimating coexistence or non-coexistence between user equipment 2000 and device B, while feedback regarding the result of estimating coexistence or non-coexistence between user equipment 2000 and device C may not be obtained. In this case, feedback dataset 440 may include only feedback data A 442 and feedback data B 444, which correspond to the devices for which the feedback is obtained by user equipment 2000.

[0084] Figure 5a This is a diagram illustrating data collection operations of a user device and another device according to embodiments of the present disclosure.

[0085] exist Figure 5a and Figure 5b In the description, it is assumed that the multiple devices corresponding to the second Wi-Fi RSSI are located in different spaces from each other. Figure 5a A specific example is shown where device A is in room A, device B is in the living room, device C is in room B, and device D is in room C.

[0086] In this embodiment, the user device 2000 may continuously collect a first Wi-Fi RSSI corresponding to a nearby Wi-Fi network. The user device 2000 may periodically or non-periodically store the first Wi-Fi RSSI. The first Wi-Fi RSSI stored by continuous collection may be referred to as "pre-collected first Wi-Fi RSSI 510".

[0087] Furthermore, each of the other devices can continuously collect a second Wi-Fi RSSI corresponding to the nearby Wi-Fi network of each device. The second Wi-Fi RSSI collected and stored continuously can be referred to as "pre-collected second Wi-Fi RSSI 520". The pre-collected second Wi-Fi RSSI 520 can include the second Wi-Fi RSSIs of multiple other devices. For example, the pre-collected second Wi-Fi RSSI 520 can include the second Wi-Fi RSSI 522 of device A, the second Wi-Fi RSSI 524 of device B, and so on.

[0088] In one embodiment, user device 2000 may receive pre-collected second Wi-Fi RSSI 520 from another device. User device 2000 can generate an original dataset 530 comprising {first Wi-Fi RSSI, second Wi-Fi RSSI} pairs by matching pre-collected first Wi-Fi RSSI 510 with pre-collected second Wi-Fi RSSI 520. User device 2000 may filter out bad data from the original dataset 530 based on preset conditions, retaining only good data. (See also...) Figure 5b The operation of filtering data performed by user device 2000 is further described.

[0089] Figure 5b This is a diagram illustrating the operation of generating a filtered dataset performed by a user device according to an embodiment of the present disclosure.

[0090] In an embodiment, the user device 2000 can generate a filtered dataset 540 by filtering a first Wi-Fi RSSI 510 and a plurality of second Wi-Fi RSSIs 520 pre-collected according to preset conditions.

[0091] User device 2000 can perform inference operations for a coexistence estimation model by applying pre-collected first Wi-Fi RSSI 510 and multiple pre-collected second Wi-Fi RSSI 520 as input data to the coexistence estimation model. For example, user device 2000 can estimate whether device A exists in the same space as user device 2000 by applying the pre-collected first Wi-Fi RSSI 510 and pre-collected second Wi-Fi RSSI 522 of device A to the coexistence estimation model. Furthermore, user device 2000 can estimate whether device B exists in the same space as user device 2000 by using the pre-collected first Wi-Fi RSSI 510 and pre-collected second Wi-Fi RSSI 524 of device B, and can estimate whether device C exists in the same space as user device 2000 by using the pre-collected first Wi-Fi RSSI 510 and pre-collected second Wi-Fi RSSI 526 of device C.

[0092] User device 2000 may filter data based on the estimation results of a coexistence estimation model. User device 2000 may determine whether to filter pre-collected first Wi-Fi RSSIs and multiple pre-collected second Wi-Fi RSSIs based on the number of devices among multiple other devices that are estimated to exist in the same space as user device 2000.

[0093] In an embodiment, the preset conditions for determining whether to filter data after the user device 2000 performs coexistence estimation on multiple other devices may be as follows.

[0094] When the number of other devices estimated to exist in the same space as user device 2000 is 1, user device 2000 may be configured to include a positive pair of the first Wi-Fi RSSI and the second Wi-Fi RSSI of the device estimated to exist in the same space as user device 2000, configure a negative pair of the first Wi-Fi RSSI and the second Wi-Fi RSSI of the remaining devices, and include the positive and negative pairs in the filtered dataset 540.

[0095] When the number of devices in other devices that are estimated to exist in the same space as user device 2000 is 2 or more, user device 2000 may classify the estimate as a potential error case and include the first Wi-Fi RSSI and the second Wi-Fi RSSI used for inference in the preliminary dataset 560.

[0096] When the number of devices in other devices that are estimated to exist in the same space as user device 2000 is 0, user device 2000 can filter the first Wi-Fi RSSI and the second Wi-Fi RSSI used for inference.

[0097] For example, referring to the first example 552 of the estimation result, the estimation result indicates that user device 2000 exists in the same space as device A and in a different space from devices B and C. In this case, because devices A, B, and C are in different spaces from each other, the data in the estimation result of the first example 552 is reliable good data. That is, user device 2000 exists in the same space as device A and in a different space from devices B and C, and the inference of the coexistence estimation model is accurate. Therefore, user device 2000 can be configured with positive pairs including the first Wi-Fi RSSI and the second Wi-Fi RSSI corresponding to device A, negative pairs including the first Wi-Fi RSSI and the second Wi-Fi RSSI corresponding to device B, and the first Wi-Fi RSSI and the second Wi-Fi RSSI corresponding to device C, and good data pairs are included in the filtered dataset 540.

[0098] Additionally, for example, referring to the second example 554 of the estimation result, the estimation result indicates that user device 2000 exists in the same space as device A and device B and in a different space than device C. In this case, because device A, device B, and device C are in different spaces from each other, the data in the estimation result of the second example 554 includes errors that indicate potential errors that may occur in the user's actual usage environment. In this case, user device 2000 may include a first Wi-Fi RSSI and a second Wi-Fi RSSI for inference in the preliminary dataset 560. In embodiments, the performance of the coexistence estimation model can be improved as user device 2000 updates the coexistence estimation model. Therefore, at some point after continuous updates, the data included in the preliminary dataset 560 can also be good data that can be used to update the coexistence estimation model. After the coexistence estimation model is updated, user device 2000 may re-examine the data in the preliminary dataset 560. User device 2000 can perform the coexistence estimation task by using the data in the preliminary dataset 560. In this case, when the number of other devices estimated to exist in the same space as user device 2000 is 1, user device 2000 may include the first Wi-Fi RSSI and the second Wi-Fi RSSI used for inference in the filtered dataset 540.

[0099] Additionally, for example, referring to the third example 554 of the estimation results, the estimation results indicate that user device 2000 exists in a different space than device A, device B, and device C. That is, as in the third example 554, when no device is estimated to exist in the same space, user device 2000 does not use the first Wi-Fi RSSI and the second Wi-Fi RSSI used for inference to update the coexistence estimation model.

[0100] By generating a filtered dataset 540, user device 2000 can ensure the absolute correctness of the first Wi-Fi RSSI and the second Wi-Fi RSSI, which can be used to fine-tune the coexistence estimation model. User device 2000 can improve the performance of the spatial estimation model for user space by updating the coexistence estimation model using the filtered dataset 540.

[0101] In this respect, although Figure 5b An example of providing three devices in addition to user device 2000 is shown, but the number of other devices is not limited to this. In other words, two or more other devices may be provided. When the number of devices estimated to exist in the same space as the user device is 1, user device 2000 can ensure the affirmative pairing of the first Wi-Fi RSSI and the second Wi-Fi RSSI.

[0102] Figure 6 This is a diagram illustrating a training dataset generated by a user device according to an embodiment of the present disclosure.

[0103] In one embodiment, user device 2000 may generate training dataset 600. User device 2000 may fine-tune coexistence estimation model 610 using training dataset 600.

[0104] The training dataset 600 may include the filtered dataset 602 and the feedback dataset 604.

[0105] The filtered dataset 602 may include pre-collected Wi-Fi RSSIs filtered according to preset conditions, consisting of {first Wi-Fi RSSI, second Wi-Fi RSSI} data pairs. These data pairs may be positive pairs indicating the same space or negative pairs indicating different spaces. This has already been stated above. Figure 5a and Figure 5b The description describes the operation of generating the filtered dataset 602 performed by the user device 2000, therefore, its repeated description will be omitted.

[0106] Feedback dataset 604 may include data pairs {first Wi-Fi RSSI, second Wi-Fi RSSI} generated based on the feedback. These data pairs may be positive pairs indicating the same space or negative pairs indicating different spaces. This has already been stated above. Figure 4aand Figure 4b The description describes the operation of generating feedback dataset 604 performed by user device 2000, therefore, its repeated description will be omitted.

[0107] To enable the user device 2000 to fine-tune the coexistence estimation model 610, a sufficient amount of data is required in the training dataset 600. However, feedback data, which serves as high-quality data for training, is collected while using the user device 2000; therefore, the amount of such data is less than the amount of continuously collected data, and collecting a sufficient amount of data requires a significant amount of time. In addition to the feedback data, the user device 2000 can continuously filter the pre-collected data and include the filtered data in the training dataset 600, thereby enabling the feedback data to be quickly reflected in the coexistence estimation model 610.

[0108] In an embodiment, the operation of generating a training dataset 600, performed by the user device 2000, can be initiated based on feedback received by the user device 2000. For example, after a user uses the user device 2000 to estimate whether another device exists in the same space as the user device, feedback regarding the estimation result can be received from the user. In this case, in response to receiving feedback, the user device 2000 can generate a training dataset 600 including a feedback dataset 604 and a filtered dataset 602, and update the coexistence estimation model. (See also...) Figure 7a and Figure 7b To describe this aspect further.

[0109] Figure 7a This is a flowchart illustrating a method of operating a user device when receiving feedback according to an embodiment of the present disclosure.

[0110] During operation S710, the user equipment 2000 can continuously collect and store Wi-Fi RSSI (first Wi-Fi RSSI). The first Wi-Fi RSSI can be collected periodically or non-periodically when the user equipment 2000 is in standby or active state.

[0111] In operation S715, another device 700 can continuously collect and store Wi-Fi RSSIs (second Wi-Fi RSSIs). One or more other devices 700 may be present. When this other device 700 is in standby or active state, it can collect the second Wi-Fi RSSIs periodically or non-periodically. When multiple other devices 700 are provided, each device can continuously collect Wi-Fi RSSIs. For example, devices A and B, which are different from each other, can each continuously collect second Wi-Fi RSSIs representing nearby Wi-Fi networks.

[0112] When operating the S720, the user equipment 2000 can recognize that feedback has been received.

[0113] In this embodiment, the operation can be performed before operation S720. Figure 2 Operations S210 to S230 are performed. In other words, user device 2000 can estimate whether the other device 700 exists in the same space as user device 2000 by inputting the first Wi-Fi RSSI of user device 2000 and the second Wi-Fi RSSI of the other device 700 into the coexistence estimation model. User device 2000 can receive user input for providing feedback on the estimation result. When no feedback is received, user device 2000 performs operation S710 again. When feedback is received, user device 2000 can perform operations S730 and S740.

[0114] In an embodiment, when feedback is received, the user device 2000 may generate a feedback dataset based on the feedback. The feedback dataset may include feedback data containing at least one {first Wi-Fi RSSI, second Wi-Fi RSSI}.

[0115] In operation S730, based on the feedback received, user device 2000 may request a second Wi-Fi RSSI from the other device 700. When multiple other devices 700 are provided, user device 2000 may request a second Wi-Fi RSSI from each of the multiple other devices 700.

[0116] In operation S735, the other device 700 can identify a data request from the user device 2000. When no data request is identified, the other device 700 again executes operation S715. When a data request is identified, the other device 700 can send a pre-collected second Wi-Fi RSSI to the user device 2000 (operation S745). The pre-collected second Wi-Fi RSSI can be collected in operation S715.

[0117] In operation S740, user equipment 2000 can obtain a pre-collected first Wi-Fi RSSI. The pre-collected first Wi-Fi RSSI can be collected in operation S710.

[0118] In operation S750, user device 2000 can generate a filtered dataset based on the inference results of the coexistence estimation model. User device 2000 can generate the filtered dataset by filtering pre-collected first Wi-Fi RSSI and pre-collected second Wi-Fi RSSI. (See reference...) Figure 7b Further describe the specific operations included in operation S750.

[0119] When operating the S760, the user device 2000 can integrate the filtered dataset and the feedback dataset. The user device 2000 can generate a training dataset that includes the filtered dataset and the feedback dataset.

[0120] In operation S770, user device 2000 may additionally update the coexistence estimation model. User device 2000 can fine-tune the coexistence estimation model using the newly generated training dataset, thereby optimizing the spatial estimation model to suit the user's space. After updating the coexistence estimation model, user device 2000 may again perform operation S710 to collect the first Wi-Fi RSSI. When feedback is subsequently received again, user device 2000 may perform operations S720 to S770 to update the coexistence estimation model again.

[0121] In this embodiment, each time feedback is received, the user device 2000 can repeatedly generate a training dataset and update the coexistence estimation model.

[0122] In this embodiment, the user device 2000 may repeatedly generate a training dataset and update the coexistence estimation model based on preset conditions. For example, the user device 2000 may update the coexistence estimation model whenever feedback is received a preset number of times N. However, the preset conditions are not limited to this, and various conditions triggered by the receipt of feedback may be defined as preset conditions.

[0123] Figure 7b To show in more detail Figure 7a The flowchart of the operation.

[0124] Figure 7b Operations S751 to S756 are described Figure 7a The detailed operation of operation S750 is described. Therefore, it can be performed before operation S751. Figure 7a Operations S710 to S740.

[0125] In operation S751, user equipment 2000 generates a data pair including one of the first Wi-Fi RSSI and the second Wi-Fi RSSI of the other device.

[0126] User equipment 2000 can obtain a first Wi-Fi RSSI that has been collected in advance and a second Wi-Fi RSSI that has been collected in advance from other devices, and generate a data pair of the first Wi-Fi RSSI and the second Wi-Fi RSSI. For example, user equipment 2000 can generate a data pair {first Wi-Fi RSSI, second Wi-Fi RSSI A} that matches the Wi-Fi RSSI of user equipment 2000 and the Wi-Fi RSSI of device A, and generate a data pair {first Wi-Fi RSSI, second Wi-Fi RSSI B} that matches the Wi-Fi RSSI of user equipment 2000 and the Wi-Fi RSSI of device B.

[0127] In operation S752, user device 2000 can perform inference operations by inputting data pairs into the coexistence estimation model. For example, user device 2000 can input data pairs {first Wi-Fi RSSI, second Wi-Fi RSSI A} into the coexistence estimation model to perform inference operations to estimate whether device A exists in the same space as user device 2000.

[0128] In operation S753, user device 2000 checks whether inference has been completed for all data pairs. For example, inference may have been performed for the data pair {first Wi-Fi RSSI, second Wi-Fi RSSI A}, but inference may not have been performed for the data pair {first Wi-Fi RSSI, second Wi-Fi RSSI B}. In this case, user device 2000 may repeat operation S752 to estimate whether device B exists in the same space as user device 2000. User device 2000 may repeat operation S752 until inference is completed for all other devices. When inference is completed for all data pairs and the coexistence estimate for all other devices is obtained, user device 2000 may execute operation S754.

[0129] In operation S754, as a result of inference, user device 2000 can identify whether only one data pair exists in the same space. When only one data pair exists in the same space, user device 2000 can perform operation S755 to store the data pair used for inference in a filtered dataset. For example, as a result of inference, it can be estimated that device A exists in the same space as user device 2000, and it can be estimated that device B exists in a different space than user device 2000. In this case, user device 2000 can include the data pair used for inference in the filtered dataset. In other cases, user device 2000 can perform operation S756 to store the data pair used for inference in a preliminary dataset. For example, both device A and device B can be estimated to exist in the same space as user device 2000. In this case, user device 2000 can filter the data pairs used for inference and include the filtered data pairs in the preliminary dataset. The data pairs included in the preliminary dataset are not directly used to update the current coexistence estimation model, but can be used to update the coexistence estimation model in the future. For example, after the coexistence estimation model is updated, user device 2000 can perform a coexistence estimation task by using data pairs included in the initial dataset. In this case, when the number of devices estimated to exist in the same space as user device 2000 is 1, user device 2000 can include the data pairs used for inference in the filtered dataset.

[0130] Figure 8 This is a diagram illustrating the operations performed by a user device to generate a training dataset according to an embodiment of the present disclosure.

[0131] exist Figure 8 The description states that device A exists in room A, device B exists in room C, device C exists in room C, and user device 2000 is an example of a mobile device.

[0132] When user device 2000 is a mobile device, the amount of data collected can vary for each device. For example, when user device 2000 is present in room B for an extended period, a relatively large number of data pairs between user device 2000 and device B can be collected. Therefore, even within the filtered dataset 800 generated by user device 2000 by filtering pre-collected first Wi-Fi RSSIs and pre-collected second Wi-Fi RSSIs of user device 2000 according to preset conditions, the amount of data for each device may vary. User device 2000 can sample the data in the filtered dataset 800 to reduce data variation within the training dataset when updating the coexistence estimation model.

[0133] In an embodiment, user device 2000 may classify multiple second Wi-Fi RSSIs that match the first Wi-Fi RSSI of the user device on a per-device basis. For example, user device 2000 may classify data pairs included in the filtered dataset 800 into dataset 810 for device A, dataset 820 for device B, and dataset 830 for device C. As a result of the classification, dataset 810 for device A may include data pairs in which the first Wi-Fi RSSI and the second Wi-Fi RSSI of device A are matched; dataset 820 for device B may include data pairs in which the first Wi-Fi RSSI and the second Wi-Fi RSSI of device B are matched; and dataset 830 for device C may include data pairs in which the first Wi-Fi RSSI and the second Wi-Fi RSSI of device C are matched.

[0134] User device 2000 can sample data pairs to be included in the filtered dataset based on classification results. For example, user device 2000 can sample data based on the median of the number of data pairs matched on a per-device basis. Specifically, when dataset 810 of device A contains two data pairs, dataset 820 of device B contains eight data pairs, and dataset 830 of device C contains one data pair, user device 2000 can set the median of 2 as the number of samples. Therefore, sampled dataset 812 of device A and sampled dataset 822 of device B each contain two data pairs, and sampled dataset 832 of device C contains one data pair. Because dataset 830 of device C contains fewer data pairs than the number of samples, all data is used. In this respect, the criteria for sampling data by user device 2000 are not limited to the median of the number of data pairs. For example, the average, preset value, etc., can be used.

[0135] By sampling data pairs included in the filtered dataset 800, the user device 2000 can reduce the variation in the data included in the filtered dataset 800. The filtered dataset 800 can be integrated with the feedback dataset to generate a training dataset for updating the coexistence estimation model.

[0136] Figure 9 This is a diagram illustrating the operations performed by a user device to generate a training dataset according to an embodiment of the present disclosure.

[0137] In one embodiment, the user device 2000 can generate a filtered dataset by filtering a pre-collected first Wi-Fi RSSI and a plurality of pre-collected second Wi-Fi RSSIs according to preset conditions. In this case, with... Figure 5b Unlike other examples, two or more other devices can exist in the same space. For example, Figure 9 The illustration shows devices A, B, and C in room A, device D in room B, and user device 2000 as an example of a mobile device.

[0138] In an embodiment, the user device 2000 can perform inference operation 900 of the coexistence estimation model by applying a pre-collected first Wi-Fi RSSI and a plurality of pre-collected second Wi-Fi RSSIs as input data to the coexistence estimation model.

[0139] For example, user equipment 2000 can estimate whether device A exists in the same space as user equipment 2000 by applying a pre-collected first Wi-Fi RSSI and a pre-collected second Wi-Fi RSSI of device A to a coexistence estimation model. Furthermore, user equipment 2000 can estimate whether devices B, C, and D exist in the same space as user equipment 2000 by using the pre-collected first Wi-Fi RSSI and the pre-collected second Wi-Fi RSSI of each of devices B, C, and D.

[0140] User device 2000 may filter data based on the estimation results of a coexistence estimation model. When two or more of a plurality of other devices exist in a space, user device 2000 may determine whether to filter pre-collected first Wi-Fi RSSI and pre-collected second Wi-Fi RSSI based on information about the plurality of other devices and the number of devices estimated to exist in the same space as user device 2000.

[0141] For example, device information for multiple other devices (i.e., device A, device B, and device C) may also include information indicating that the device is in room A.

[0142] Referring to the first example 910 of the estimation results, the estimation results in the first example 910 indicate that user device 2000 exists in the same space as device A, device B, and device C, and in a different space from device D. In this case, because there is information indicating that device A, device B, and device C exist in the same space as each other, the data in the estimation results of the first example 910 is reliable good data. That is, user device 2000 exists in the same space as device A, device B, and device C, and in a different space from device D, and the inference of the coexistence estimation model is accurate. Therefore, user device 2000 can include the {first Wi-Fi RSSI, second Wi-Fi RSSI} data pair used for the inference in the first example 910 in the filtered dataset.

[0143] Referring to the second example 920 of the estimation results, the estimation results in the second example 920 indicate that user device 2000 exists in a different space from device A, device B, and device C, but in the same space as device D. In this case, because there is information indicating that device A, device B, and device C exist in the same space as each other, the data in the estimation results of the second example 920 is reliable good data. That is, user device 2000 exists in a different space from device A, device B, and device C, but in the same space as device D, and the inference of the coexistence estimation model is accurate. Therefore, user device 2000 can include the {first Wi-Fi RSSI, second Wi-Fi RSSI} data pair used for the inference in the second example 920 in the filtered dataset.

[0144] Referring to the third example 930, the estimation result in the third example 930 indicates that user device 2000 exists in the same space as device A and device B, and in a different space from device C and device D. In this case, because there is information indicating that device A, device B, and device C exist in the same space as each other, the data in the estimation result of the third example 930 is an accurate estimate of more than most (2 out of 3) of the data. Therefore, user device 2000 can include the {first Wi-Fi RSSI, second Wi-Fi RSSI} data pairs used for inference in the third example 930 in the filtered dataset.

[0145] Referring to the fourth example 940 and the fifth example 950 of the estimation results, the data in the estimation results of the fourth example 940 is less than the majority (1 out of 3) of the data that is accurately estimated, and the data in the estimation results of the fifth example 950, which estimates that devices A and D exist in different spaces, exist in the same space, are therefore considered unusable data. Therefore, the data pairs used in the inference in the fourth example 940 and the fifth example 950 may not be included in the filtered dataset.

[0146] In an embodiment, when the number of devices in the same space among other devices is 2 or more, the user device 2000 may assign the weights used for sampling to the first Wi-Fi RSSI-second Wi-Fi RSSI pair based on the estimation results of the coexistence estimation model.

[0147] For example, referring to the first example 910 of the estimation results, the estimation results in the first example 910 are accurate estimation results, and there exist three affirmative pairs that user device 2000 is inferred to exist in the same space as device A, device B, and device C, respectively. Therefore, user device 2000 may assign a first weight (e.g., 2) as a relatively high weight to the {first Wi-Fi RSSI, second Wi-Fi RSSI} data pairs used in the inference in the first example 910.

[0148] For example, referring to the second example 920, where the estimation result is accurate, and there exists a positive pair that user device 2000 is inferred to exist in the same space as device D. Therefore, user device 2000 may assign a second weight (e.g., 1) lower than the first weight to the {first Wi-Fi RSSI, second Wi-Fi RSSI} data pair used in the inference in the second example 920.

[0149] For example, referring to the third example 930, the estimation result in the third example 930 is an accurate estimate of more than the majority (2 out of 3) of the results. In this case, because the estimation result is not perfectly accurate, the user device 2000 may assign a third weight (e.g., 0.66) lower than the first and second weights to the {first Wi-Fi RSSI, second Wi-Fi RSSI} data pair used in the inference in the third example 930.

[0150] In an embodiment, weights can be used when the user device 2000 generates a filtered dataset. For example, the user device 2000 can sample data based on weights. Specifically, the user device 2000 can sort data pairs in order of weight and sample the N data pairs with high weights to configure the filtered dataset. Alternatively, the user device 2000 can configure the filtered dataset by sampling data pairs proportionally to their weights.

[0151] Figure 10 This is a diagram illustrating operations performed by a user device using a coexistence estimation model according to an embodiment of the present disclosure.

[0152] In this embodiment, user device 2000 can control multiple other devices. For example, user device 2000 can interact with other devices in the user's home. These other devices in the home and user device 2000 can be communicatively connected to each other. For example, user device 2000 and other devices can be connected to a home network or a server (e.g., a cloud server).

[0153] During operation S1010, user device 2000 can perform home device control functions. User device 2000 can receive user input for performing home device control functions. Home device control functions can be provided through application 1010. For example, multiple home devices registered in a smart home application can be controlled through the application.

[0154] In operation S1020, user device 2000 can display the inference results obtained by using a coexistence estimation model. User device 2000 can estimate devices existing in the same space as user device 2000's current location and display the estimation results on the screen. For example, user device 2000 can display devices identified as existing in the same space as user device 2000, along with information about those devices. For example, when device A is identified as existing in the same space as the user, and information about device A is registered indicating that the device exists in room A, user device 2000 can display on the screen the device inferred to exist in the same space as the user. Based on user input for selecting another device displayed on the screen, user device 2000 can control the operation of that other device. For example, when the other device is a TV, operations such as turning the TV on / off, changing channels, adjusting volume, and running applications can be performed via user device 2000.

[0155] In operation S1030, user device 2000 may receive user feedback. In an embodiment, the inference result obtained in operation S1020 using the coexistence estimation model may be inaccurate. In this case, the user may input feedback into user device 2000. For example, user device 2000 may provide a user interface that can evaluate the accuracy / inaccuracy of the inference result. User device 2000 may store feedback information based on user input. In an embodiment, user device 2000 may receive user input from the user for location information of the input device.

[0156] In operation S1040, user device 2000 can generate a feedback dataset. The operation of generating the feedback dataset performed by user device 2000 has already been described above in the description of the previous figures, therefore, for the sake of brevity, its repeated description will be omitted.

[0157] In operation S1045, user device 2000 can generate a filtered dataset. The filtered dataset can be generated by filtering pre-collected Wi-Fi RSSI data. The operation of generating the filtered dataset performed by user device 2000 has already been described above in the description of the preceding figures; therefore, for the sake of brevity, its repeated description will be omitted.

[0158] In operation S1050, user device 2000 can update the coexistence estimation model. User device 2000 can fine-tune the coexistence estimation model using a training dataset that includes the feedback dataset and the filtered dataset. The operation of updating the coexistence estimation model performed by user device 2000 has already been described above in the description of the previous figures, therefore, for the sake of brevity, its repeated description will be omitted.

[0159] Figure 11 This is a block diagram illustrating the configuration of a user device according to an embodiment of the present disclosure.

[0160] In an embodiment, the user device 2000 may include a communication interface 2100, a memory 2200, and a processor 2300.

[0161] The communication interface 2100 may include communication circuitry. The communication interface 2100 may use at least one of the following data communication methods: wired LAN, wireless LAN, Wi-Fi, Bluetooth, ZigBee, Wi-Fi Direct (WFD), Infrared Data Association (IrDA), Bluetooth Low Energy (BLE), Near Field Communication (NFC), Wireless Broadband Internet (WiBro), Global Microwave Access Interoperability (WiMAX), Shared Radio Access Protocol (SWAP), Wireless Gigabit Alliance (WiGig), and RF communication. The communication interface 2100 may be implemented by including multiple modules (e.g., a Wi-Fi module, etc.) for implementing the aforementioned communication methods.

[0162] The communication interface 2100 can send and receive data to and from other devices for performing operations of the user device 2000. For example, the user device 2000 can send and receive various data (device information and Wi-Fi RSSI information) used by the user device 2000 to interact with other devices through the communication interface 2100.

[0163] Memory 2200 may store instructions, data structures, and program code that can be read by processor 2300. One or more memories 2200 may exist. In the disclosed embodiments, operations performed by processor 2300 can be implemented by executing the instructions or code of a program stored in memory 2200.

[0164] The memory 2200 may include non-volatile memory such as read-only memory (ROM) (e.g., programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), or electrically erasable programmable read-only memory (EEPROM)), flash memory (e.g., memory card or solid-state drive (SSD)) and analog recording type (e.g., hard disk drive (HDD), magnetic tape, or optical disc), as well as volatile memory such as random access memory (RAM) (e.g., dynamic random access memory (DRAM) or static random access memory (SRAM)).

[0165] The memory may store data, instructions, and programs that enable the user device 2000 to operate. For example, the memory 2200 may store the coexistence estimation module 2210, the training data management module 2220, and the device management module 2230.

[0166] Processor 2300 can control the overall operation of user device 2000. For example, processor 2300 can control the overall operation of user device 2000 by executing one or more instructions of a program stored in memory 2200. One or more processors 2300 may be present.

[0167] Processor 2300 can estimate whether user device 2000 and another device exist in the same space by executing coexistence estimation module 2210. Coexistence estimation module 2210 may include a coexistence estimation model, as well as data and code for operating the coexistence estimation model. The operation of using the coexistence estimation model performed by user device 2000 has already been described above, so for the sake of brevity, its repeated description will be omitted.

[0168] The processor 2300 can generate a training dataset by executing the training data management module 2220. The training data management module can collect the Wi-Fi RSSI of the user device 2000 and the Wi-Fi RSSI of other devices. The training data management module 2220 can generate a feedback dataset based on feedback received from the user. Furthermore, the training data management module 2220 can continuously filter pre-collected data to generate a filtered dataset. When the filtered dataset is generated, the coexistence estimation module 2210 can be used to obtain inference data from the pre-collected data. The operation of generating training data performed by the user device 2000 has already been described above; therefore, for the sake of brevity, its repeated description will be omitted.

[0169] The processor 2300 can manage multiple devices through the execution device management module 2230. The device management module 2230 can send and receive data for interacting with the devices. The device management module 2230 can send user input input to the user device 2000 to another device, send control commands to another device for controlling that device, and receive device information from another device. The operations performed by the user device 2000 for interacting with other devices have already been described above; therefore, for the sake of brevity, their repeated description will be omitted.

[0170] In this regard, the modules stored in memory 2200 described above have been provided for ease of description, and this disclosure is not necessarily limited thereto. Other modules may be added to implement the above embodiments, some of which may be implemented as a single module, or any of which may be implemented by being divided into multiple modules.

[0171] In one embodiment, one or more processors 2300 may include at least one of a central processing unit (CPU), a graphics processing unit (GPU), an accelerated processing unit (APU), an integrated many-core processor (MIC), a digital signal processor (DSP), and a neural processing unit (NPU). One or more processors 2300 may be implemented as an integrated system-on-a-chip (SoC) including one or more electronic components. Each of the one or more processors 2300 may be implemented as a separate hardware (H / W).

[0172] When the method according to embodiments of this disclosure includes multiple operations, the multiple operations may be executed by one processor 2300 or by multiple processors 2300. For example, when the first operation, the second operation, and the third operation are performed by the method according to the embodiments, the first operation, the second operation, and the third operation may all be executed by the first processor, or the first operation and the second operation may be executed by the first processor (e.g., a general-purpose processor) and the third operation may be executed by a second processor (e.g., an AI-specific processor). Here, an example of the second processor may be an AI-specific processor, and the AI-specific processor may perform operations for training / inference of an AI model. However, embodiments of this disclosure are not limited thereto.

[0173] One or more processors 2300 according to this disclosure may be implemented as single-core processors or multi-core processors.

[0174] When the method according to embodiments of the present disclosure includes multiple operations, the multiple operations may be executed by one or more cores included in one or more processors 2300.

[0175] Furthermore, although not in Figure 11As shown, however, user device 2000 may also include additional components for performing operations of embodiments of this disclosure. For example, user device 2000 may also include a display, camera, microphone, input / output interface, etc.

[0176] This disclosure provides a user device and a method for operating the same, wherein, in an environment where the user device interacts with multiple other devices, the user device can estimate whether the user device exists in the same space as the other devices. Furthermore, a method is provided for generating a training dataset for personalizing a coexistence estimation model and using the training dataset to ensure that the coexistence estimation model performs correctly in the user's environment. The technical problems addressed by this disclosure are not limited to those described above, and other technical problems not mentioned herein will be clearly understood by those skilled in the art from the description in this specification.

[0177] According to one aspect of this disclosure, a method of operating a user device may be provided. The method may include obtaining a first Wi-Fi RSSI corresponding to a nearby Wi-Fi network of the user device.

[0178] The method may include obtaining multiple second Wi-Fi RSSIs corresponding to the nearby Wi-Fi networks of each of the other devices.

[0179] The method may include estimating the presence of other devices in the same space as the user device by applying a first Wi-Fi RSSI and multiple second Wi-Fi RSSIs as input data to a coexistence estimation model.

[0180] The method may include receiving feedback on the estimation results. The method may also include generating a feedback dataset based on the feedback, including a first Wi-Fi RSSI and multiple second Wi-Fi RSSIs.

[0181] The method may include obtaining a first Wi-Fi RSSI that has been pre-collected and multiple second Wi-Fi RSSIs that have been pre-collected.

[0182] The method may include generating a filtered dataset by filtering a first pre-collected Wi-Fi RSSI and multiple pre-collected second Wi-Fi RSSIs according to preset conditions.

[0183] This method may include updating the coexistence estimation model by using a feedback dataset and a filtered dataset.

[0184] Feedback may include the location information of the user device and information indicating that the estimation results are inaccurate.

[0185] Generating a feedback dataset may include configuring a negation pair based on the feedback, which includes the first Wi-Fi RSSI and the second Wi-Fi RSSI of the other devices estimated to exist in the same space as the user device.

[0186] Generating a feedback dataset may include: configuring affirmative pairs based on the feedback, which include a first Wi-Fi RSSI and a second Wi-Fi RSSI of a device that has location information corresponding to the location information of the user device.

[0187] The generated filtered dataset may include: using a pre-collected first Wi-Fi RSSI and multiple pre-collected second Wi-Fi RSSIs as input data to apply to the coexistence estimation model.

[0188] The dataset for generating the filter may include: determining whether to filter a first pre-collected Wi-Fi RSSI and multiple pre-collected second Wi-Fi RSSIs based on the number of other devices estimated to exist in the same space as the user device.

[0189] The dataset for generating the filter may include: when the number of other devices estimated to exist in the same space as the user device is 1, a configuration including a positive pair of a first Wi-Fi RSSI and a second Wi-Fi RSSI of a device estimated to exist in the same space as the user device, and a configuration including a negative pair of the first Wi-Fi RSSI and the second Wi-Fi RSSI of the remaining devices.

[0190] The generated filtered dataset may include: on a per-device basis, classifying multiple pre-collected second Wi-Fi RSSIs of other devices that match the user device's pre-collected first Wi-Fi RSSI.

[0191] The generated filtered dataset may include sampling the first Wi-Fi RSSI-second Wi-Fi RSSI pair to be included in the filtered dataset based on the classification results.

[0192] The dataset for generating the filter may include: when the number of devices in the same space among other devices is 2 or more, assigning weights for sampling to the first Wi-Fi RSSI-second Wi-Fi RSSI based on the estimation results of the coexistence estimation model.

[0193] Updating the coexistence estimation model may include assigning higher weights to the feedback dataset than to the filtered dataset.

[0194] Updating the coexistence estimation model may include updating the coexistence estimation model by using weights.

[0195] According to one aspect of this disclosure, a user equipment may be provided. The user equipment may include: a communication interface; a memory for storing one or more instructions; and one or more processors configured to execute one or more instructions stored in the memory.

[0196] One or more processors may execute one or more instructions to obtain a first Wi-Fi RSSI corresponding to a nearby Wi-Fi network of the user device.

[0197] One or more processors can execute one or more instructions to obtain multiple second Wi-Fi RSSIs corresponding to the nearby Wi-Fi networks of each other in other devices.

[0198] One or more processors may execute one or more instructions to estimate the presence of other devices in the same space as the user device by applying a first Wi-Fi RSSI and multiple second Wi-Fi RSSIs as input data to a coexistence estimation model.

[0199] One or more processors can execute one or more instructions to receive feedback on the estimation results.

[0200] One or more processors can execute one or more instructions to generate a feedback dataset that includes a first Wi-Fi RSSI and multiple second Wi-Fi RSSIs based on the feedback.

[0201] One or more processors can execute one or more instructions to obtain a first Wi-Fi RSSI that has been pre-collected and multiple second Wi-Fi RSSIs that have been pre-collected.

[0202] One or more processors can execute one or more instructions to generate a filtered dataset by filtering a first pre-collected Wi-Fi RSSI and a plurality of pre-collected second Wi-Fi RSSIs according to preset conditions.

[0203] One or more processors can execute one or more instructions to update the coexistence estimation model using a feedback dataset and a filtered dataset.

[0204] Feedback may include the location information of the user device and information indicating that the estimation results are inaccurate.

[0205] One or more processors may execute one or more instructions to configure a negation pair based on feedback, the negation pair including a first Wi-Fi RSSI and a second Wi-Fi RSSI of a device estimated to exist in the same space as the user device.

[0206] One or more processors may execute one or more instructions to configure a positive pair based on feedback, the positive pair including a first Wi-Fi RSSI and a second Wi-Fi RSSI of a device having location information corresponding to the location information of the user device.

[0207] One or more processors can execute one or more instructions to apply pre-collected first Wi-Fi RSSIs and multiple pre-collected second Wi-Fi RSSIs as input data to a coexistence estimation model.

[0208] One or more processors may execute one or more instructions to determine whether to filter a first pre-collected Wi-Fi RSSI and multiple pre-collected second Wi-Fi RSSIs based on the number of devices in other devices estimated to exist in the same space as the user device.

[0209] One or more processors can execute one or more instructions to configure a positive pair of a first Wi-Fi RSSI and a second Wi-Fi RSSI of a device estimated to exist in the same space as the user device, when the number of such devices is 1, and the configuration includes a negative pair of the first Wi-Fi RSSI and the second Wi-Fi RSSI of the remaining devices.

[0210] One or more processors may execute one or more instructions to classify, on a per-device basis, multiple pre-collected second Wi-Fi RSSIs of other devices that match a pre-collected first Wi-Fi RSSI of a user device.

[0211] One or more processors may execute one or more instructions to sample a first Wi-Fi RSSI-second Wi-Fi RSSI pair to be included in the filtered dataset based on the classification results.

[0212] When the number of devices located in the same space in other devices is 2 or more, one or more processors can execute one or more instructions to assign weights for sampling to the first Wi-Fi RSSI-second Wi-Fi RSSI based on the estimation results of the coexistence estimation model.

[0213] One or more processors can execute one or more instructions to assign higher weights to the feedback dataset than to the filtered dataset.

[0214] One or more processors can execute one or more instructions to update the coexistence estimation model by using weights.

[0215] Furthermore, embodiments of this disclosure can be implemented in the form of a recording medium including computer-executable instructions, such as a program module executed by a computer. A computer-readable medium can be any available medium accessible to a computer, and includes both volatile and non-volatile media, as well as both removable and non-removable media. Additionally, a computer-readable medium can include computer storage media and communication media. Computer storage media includes both volatile and non-volatile media, and both removable and non-removable media, implemented using any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Communication media typically include other data, such as computer-readable instructions, data structures, or program modules, that modulate data signals.

[0216] Furthermore, computer-readable storage media may be provided in the form of non-transitory storage media. Here, "non-transitory storage media" refers to a tangible device and does not include signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently in a storage medium and cases where data is temporarily stored in a storage medium. For example, "non-transitory storage media" may include buffers for temporarily storing data.

[0217] According to embodiments, the methods according to the various embodiments disclosed herein can be provided by being included in a computer program product. The computer program product can be traded as a commercial product between a seller and a buyer. The computer program product can be distributed in the form of a machine-readable storage medium (e.g., an optical disc read-only memory (CD-ROM)), or distributed online (e.g., downloaded or uploaded) through an app store, or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product (e.g., a downloadable application) can be at least temporarily generated or temporarily stored in a machine-readable storage medium (such as the memory of a manufacturer's server, an app store's server, or a relay server).

[0218] The foregoing description of this disclosure is provided for illustrative purposes, and it will be understood by those skilled in the art that various changes in form and detail may be readily made therein without departing from the technical spirit or essential characteristics of this disclosure. Therefore, it should be understood that the above embodiments are illustrative in all respects and not restrictive. For example, each element described as a single type may be implemented in a distributed manner, and similarly, elements described as distributed may be implemented in a combined manner.

[0219] The scope of this disclosure is defined by the appended claims rather than the foregoing detailed description, and all changes or modifications within the scope of the claims and their equivalents shall be construed as being included within the scope of this disclosure.

Claims

1. A method of operating a user device, the method comprising: Obtain the first Wi-Fi RSSI corresponding to the nearby Wi-Fi network of the user device; Obtain multiple second Wi-Fi RSSIs corresponding to the nearby Wi-Fi networks of each of the other devices; The presence of the other device in the same space as the user device is estimated by applying the first Wi-Fi RSSI and the plurality of second Wi-Fi RSSIs as input data to the coexistence estimation model. Receive feedback on the estimation results; Based on the feedback, a feedback dataset including the first Wi-Fi RSSI and the plurality of second Wi-Fi RSSIs is generated; Obtain the first pre-collected Wi-Fi RSSI and multiple pre-collected second Wi-Fi RSSIs; A filtered dataset is generated by filtering a pre-collected first Wi-Fi RSSI and the plurality of pre-collected second Wi-Fi RSSIs according to preset conditions; as well as The coexistence estimation model is updated by using the feedback dataset and the filtered dataset.

2. The method according to claim 1, wherein, The feedback includes the location information of the user device and information indicating that the estimation result is inaccurate.

3. The method according to claim 2, wherein, Generating a feedback dataset includes: configuring a negation pair based on the feedback, the negation pair including a first Wi-Fi RSSI and a second Wi-Fi RSSI of a device among the other devices that is estimated to exist in the same space as the user device.

4. The method according to claim 2, wherein, Generate a feedback dataset, including: configuring affirmative pairs based on the feedback, wherein the affirmative pairs include a first Wi-Fi RSSI and a second Wi-Fi RSSI of a device among the other devices that has location information corresponding to the location information of the user device.

5. The method according to claim 1, wherein, Generate the filtered dataset, including: The pre-collected first Wi-Fi RSSI and the plurality of pre-collected second Wi-Fi RSSIs are used as input data in the coexistence estimation model; and Based on the number of devices among the other devices that are estimated to exist in the same space as the user device, it is determined whether to filter the pre-collected first Wi-Fi RSSI and the plurality of pre-collected second Wi-Fi RSSI.

6. The method according to claim 5, wherein, The generated filtered dataset includes: when the number of devices among the other devices estimated to exist in the same space as the user device is 1, configuring positive pairs including a first Wi-Fi RSSI and a second Wi-Fi RSSI of the device estimated to exist in the same space as the user device, and configuring negative pairs including the first Wi-Fi RSSI and the second Wi-Fi RSSI of the remaining devices.

7. The method according to claim 5, wherein, Generate the filtered dataset, including: On a per-device basis, the plurality of pre-collected second Wi-Fi RSSIs of the other devices that match the pre-collected first Wi-Fi RSSI of the user device are classified; and Based on the classification results, the first Wi-Fi RSSI-second Wi-Fi RSSI pair to be included in the filtered dataset is sampled.

8. A user equipment, comprising: Communication interface; Memory, which stores one or more instructions; as well as One or more processors are configured to execute the one or more instructions stored in the memory. Wherein, the one or more processors execute the one or more instructions to perform the following operations: Obtain the first Wi-Fi RSSI corresponding to the nearby Wi-Fi network of the user device. Obtain multiple second Wi-Fi RSSIs corresponding to the nearby Wi-Fi networks of each of the other devices. The presence of the other device in the same space as the user device is estimated by applying the first Wi-Fi RSSI and the plurality of second Wi-Fi RSSIs as input data to the coexistence estimation model. Receive feedback on the estimation results. Based on the feedback, a feedback dataset including the first Wi-Fi RSSI and the plurality of second Wi-Fi RSSIs is generated. Obtain the first pre-collected Wi-Fi RSSI and multiple pre-collected second Wi-Fi RSSIs. A filtered dataset is generated by filtering pre-collected first Wi-Fi RSSIs and multiple pre-collected second Wi-Fi RSSIs according to preset conditions. The coexistence estimation model is updated by using the feedback dataset and the filtered dataset.

9. The user equipment according to claim 8, wherein, The feedback includes the location information of the user device and information indicating that the estimation result is inaccurate.

10. The user equipment according to claim 9, wherein, The one or more processors execute the one or more instructions to perform the following operation: based on the feedback, configure a negation pair, the negation pair including a first Wi-Fi RSSI and a second Wi-Fi RSSI of a device among the other devices estimated to exist in the same space as the user device.

11. The user equipment according to claim 9, wherein, The one or more processors execute the one or more instructions to perform the following operation: based on the feedback, configure a positive pair, the positive pair including a first Wi-Fi RSSI and a second Wi-Fi RSSI of a device among the other devices having location information corresponding to the location information of the user device.

12. The user equipment according to claim 8, wherein, The one or more processors execute the one or more instructions to perform the following operations: The pre-collected first Wi-Fi RSSI and the plurality of pre-collected second Wi-Fi RSSIs are used as input data to apply to the coexistence estimation model, and Based on the number of devices among the other devices that are estimated to exist in the same space as the user device, it is determined whether to filter the pre-collected first Wi-Fi RSSI and the plurality of pre-collected second Wi-Fi RSSI.

13. The user equipment according to claim 12, wherein, The one or more processors execute the one or more instructions to perform the following operations: when the number of the other devices estimated to exist in the same space as the user device is 1, configure an affirmative pair including a first Wi-Fi RSSI and a second Wi-Fi RSSI of the device estimated to exist in the same space as the user device, and configure a negative pair including the first Wi-Fi RSSI and the second Wi-Fi RSSI of the remaining devices.

14. The user equipment according to claim 12, wherein, The one or more processors execute the one or more instructions to perform the following operations: On a per-device basis, the pre-collected second Wi-Fi RSSIs of the other devices that match the pre-collected first Wi-Fi RSSI of the user device are classified, and Based on the classification results, the first Wi-Fi RSSI-second Wi-Fi RSSI pair to be included in the filtered dataset is sampled.

15. A computer-readable recording medium having a program recorded thereon for performing the method of any one of claims 1 to 7 on a computer.

Images