WO2023184952A1

WO2023184952A1 - Method and apparatus for distinguishing indoor and outdoor terminals, and storage medium

Info

Publication number: WO2023184952A1
Application number: PCT/CN2022/127514
Authority: WO
Inventors: 金宁迪
Original assignee: 中兴通讯股份有限公司
Priority date: 2022-03-30
Filing date: 2022-10-26
Publication date: 2023-10-05
Also published as: CN116980826A

Abstract

Disclosed are a method and apparatus for distinguishing indoor and outdoor terminals, and a storage medium. The method comprises: acquiring first measurement data and second measurement data, wherein the first measurement data comprises data related to the position of a terminal to be distinguished, and the second measurement data comprises RSRP measured by said terminal, or comprises RSRP and RSRQ which are measured by said terminal; according to the first measurement data and a plurality of position partitions, which are obtained by means of division performed by a serving cell, determining a position partition to which the position of said terminal belongs; and according to an indoor/outdoor distinguishing threshold corresponding to the position partition to which the position of said terminal belongs, and the second measurement data, determining whether said terminal is an indoor terminal or an outdoor terminal, wherein each position partition of the serving cell corresponds to an indoor/outdoor distinguishing threshold, which is obtained according to a plurality of pieces of fourth measurement data of each position partition, which fourth measurement data comprises RSRP measured by a first terminal or comprises RSRP and RSRQ measured by the first terminal.

Description

Methods, devices and storage media for distinguishing indoor and outdoor terminals

Cross-references to related applications

This disclosure claims priority to Chinese patent application CN202210327032.7 titled "Method, device and storage medium for distinguishing indoor and outdoor terminals" submitted on March 30, 2022, the entire content of which is incorporated into this disclosure by reference.

Technical field

The present disclosure relates to the field of mobile communication technology, and in particular, to a method, device and storage medium for distinguishing indoor and outdoor terminals.

Background technique

For operators, it is very important to distinguish whether the terminal is indoors or outdoors based on wireless signal measurement data. When a user accesses an indoor substation, all wireless signal measurement data can be simply determined to be indoors. When users access a macro site, distinguishing indoor and outdoor terminals based on wireless signal measurement data is a difficult issue in the industry.

Contents of the invention

Embodiments of the present disclosure provide a method, device, and storage medium for distinguishing indoor and outdoor terminals.

In a first aspect, the present disclosure provides a method for distinguishing indoor and outdoor terminals. The method includes: acquiring first measurement data and second measurement data, where the first measurement data includes data related to the location of the terminal to be distinguished, so The second measurement data includes the reference signal received power RSRP measured by the terminal to be distinguished, or includes the RSRP and reference signal reception quality RSRQ measured by the terminal to be distinguished; according to the first measurement data and the multiple location partitions that the serving cell has been divided into, Determine the location partition to which the location of the terminal to be differentiated belongs; and determine the terminal to be differentiated to be an indoor terminal or an outdoor terminal according to the indoor and outdoor differentiation threshold corresponding to the location partition to which the location of the terminal to be differentiated belongs and the second measurement data, wherein Each location partition of the serving cell corresponds to an indoor and outdoor distinction threshold. The indoor and outdoor distinction threshold is obtained based on a plurality of fourth measurement data of each location partition under the serving cell. The fourth measurement data It includes the RSRP measured by the first terminal, or includes the RSRP and RSRQ measured by the first terminal.

In a second aspect, the present disclosure provides a device for distinguishing indoor and outdoor terminals. The device includes a communication circuit, a memory, and a processor. The communication circuit is used for communication; the memory is used for storing computer programs; and the processor is used for The computer program is executed and the method for distinguishing indoor and outdoor terminals as described above is implemented when the computer program is executed.

In a third aspect, the present disclosure provides a computer-readable storage medium that stores a computer program. When executed by a processor, the computer program causes the processor to implement the indoor and outdoor terminals as described above. Distinguishing method.

Description of drawings

Figure 1 is a schematic flowchart of an embodiment of a method for distinguishing indoor and outdoor terminals according to the present disclosure;

Figure 2 is a schematic diagram of an embodiment of location partitioning of serving cells in the method of distinguishing indoor and outdoor terminals according to the present disclosure; and

FIG. 3 is a schematic structural diagram of an embodiment of a device for distinguishing indoor and outdoor terminals according to the present disclosure.

Detailed ways

The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only some, not all, of the embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of the present disclosure.

The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all contents and operations/steps, nor are they necessarily performed in the order described. For example, some operations/steps can also be decomposed, combined or partially merged, so the actual order of execution may change according to actual conditions.

In the following description, suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present disclosure and have no specific meaning in themselves. Therefore, "module", "component" or "unit" may be used interchangeably.

At present, when determining whether a terminal is indoors or outdoors, it is directly based on a fixed threshold obtained by statistics of all data in the serving cell, which can easily lead to misjudgment.

Referring to Figure 1, Figure 1 is a schematic flowchart of an embodiment of a method for distinguishing indoor and outdoor terminals of the present disclosure. The method includes: step S101, step S102 and step S103.

Step S101: Obtain first measurement data and second measurement data, the first measurement data includes data related to the location of the terminal to be distinguished; the second measurement data includes the reference signal received power RSRP measured by the terminal to be distinguished, or Including the RSRP and reference signal reception quality RSRQ measured by the terminal to be distinguished.

The first measurement data and the second measurement data both belong to wireless signal measurement data. These wireless signal measurement data can come from measurement reports (MR, Measure Report), minimized drive test data (MDT, Minimization of Drive Test), etc.

The first measurement data includes data related to the location of the terminal to be differentiated. According to the first measurement data, the location of the terminal to be differentiated in the serving cell can be learned.

In one embodiment, the first measurement data includes a first timing advance (TA, Timing Advance) and a first horizontal azimuth angle (hDoA, horizontal Direction of Arrival); or includes a first timing advance and a first timing advance of the serving cell. The first beam with the strongest RSRP; or the first neighboring cell including the first timing advance and the strongest RSRP.

The time advance TA can refer to the difference between the actual time when the terminal's signal reaches the base station and the time when the terminal's signal reaches the base station assuming that the distance between the terminal and the base station is 0; the base station determines the time of each terminal by measuring the terminal's uplink transmission. TA value, TA value can represent the distance between the terminal and the base station, the unit is Ts, 1Ts≈4.88 meters. The first time advance amount is the TA of the terminal to be distinguished measured by the base station.

The horizontal azimuth angle, also known as the horizontal direction of arrival, can refer to the connection direction between the base station and the terminal. This is based on true north as zero degrees and increasing clockwise as the reference standard. hDoA can represent the direction in which the terminal is located in the service cell. , the unit is °; in 5G 8TR and above, the base station can measure the horizontal azimuth angle. The first horizontal azimuth angle may be the connection direction between the base station and the terminal to be distinguished.

5G 8TR and above usually form multiple narrow beams covering different directions. The terminal can measure the signal strength of different beams of the serving cell. Among them, the beam with the strongest RSRP of the serving cell (StrongestBeam) can indicate the direction in which the terminal is located in the serving cell. The first beam with the strongest RSRP of the serving cell is the strongest beam (StrongestBeam) with the strongest RSRP of the serving cell measured by the terminal to be differentiated.

For 4G or 5G below 8TR, it is usually impossible to measure hDoA, and narrow beams will not be formed. In this case, the strongest RSRP neighbor cell (strongestnCellkey) can be used to characterize the direction in which the terminal is located in the serving cell. The first neighbor cell with the strongest RSRP can represent the direction in which the terminal to be distinguished is located in the serving cell.

Embodiments of the present disclosure can determine the location of the terminal to be differentiated in the serving cell based on the distance between the terminal to be differentiated and the base station and the direction in which the terminal to be differentiated is located in the serving cell.

The second measurement data includes the reference signal receiving power (RSRP, Reference Signal Receiving Power) measured by the terminal to be distinguished, or includes the RSRP and reference signal receiving quality (RSRQ, Reference Signal Receiving Quality) measured by the terminal to be distinguished.

Reference signal received power RSRP can refer to the average of the signal power received on all resource elements (REs, Resource Elements) carrying cell-specific reference signals on the frequency band considered for measurement, and is the main indicator reflecting the coverage of the serving cell. Antenna obstruction and hardware failure will cause weak signals, prone to call drops and reduced connection rates, and are used to check cell coverage blind spots and weak coverage areas.

Reference signal receiving quality (RSRQ, Reference Signal Receiving Quality) represents the receiving quality of the reference signal. This measurement is mainly used to rank different candidate cells based on signal quality and is used as input for handover and cell reselection decisions. RSRQ is defined as the ratio of N*RSRP/RSSI, where N is the number of resource blocks (RBs) of the RSSI measurement bandwidth. Received Signal Strength Indication (RSSI, Received Signal Strength Indication) is an indicator on the base station side. It measures the power average of all signals on the frequency and is used to determine the link quality and whether to increase the broadcast transmission intensity.

The strength of RSRP can very sensitively and fully reflect whether the antenna is blocked. The RSRP measured when the terminal is indoors is smaller than the RSRP measured when the terminal is outdoors. Of course, RSRP can also be combined with other measurement data that differs between indoor and outdoor terminals to increase the feasibility and accuracy of distinguishing indoor and outdoor terminals. For example: RSRP and RSRQ.

Step S102: Determine the location partition to which the location of the terminal to be distinguished belongs based on the first measurement data and the multiple location partitions into which the serving cell has been divided.

In the embodiment of the present disclosure, the serving cell has been divided into multiple location partitions in advance. According to the first measurement data, it can be learned which location partition of the serving cell the terminal to be differentiated is in.

Among them, there are many ways to divide the service cell into multiple location partitions. For example, the service cell can be manually divided into multiple location partitions, or the locations of multiple terminals in the service cell except the terminal to be distinguished can be counted and divided. Or segment the direction and distance to achieve location partitioning, etc. As shown in Figure 2, Figure 2 is a location partition achieved by dividing direction and distance.

Step S103: Determine that the terminal to be differentiated is an indoor terminal or an outdoor terminal according to the indoor and outdoor differentiation threshold corresponding to the location partition to which the terminal to be differentiated belongs and the second measurement data, wherein each location partition of the serving cell Corresponding to an indoor and outdoor differentiation threshold, the indoor and outdoor differentiation threshold is obtained based on a plurality of fourth measurement data of each location partition under the serving cell, and the fourth measurement data includes the RSRP measured by the first terminal, or Includes RSRP and RSRQ measured by the first terminal.

In the embodiment of the present disclosure, each location partition of the serving cell corresponds to an indoor-outdoor distinction threshold. That is to say, each location partition of the serving cell has obtained an indoor-outdoor distinction threshold in advance. The indoor and outdoor differentiation threshold is obtained based on a plurality of fourth measurement data of each location partition under the serving cell. The fourth measurement data includes the RSRP measured by the first terminal, or includes the RSRP and RSRQ measured by the first terminal. .

Various methods can be used to obtain the indoor and outdoor differentiation thresholds based on the plurality of fourth measurement data of each location partition under the serving cell. In the embodiment of the present disclosure, the indoor and outdoor distinction threshold can be used to distinguish indoor and outdoor terminals, and its form can be diverse. Different methods are used to obtain the indoor and outdoor distinction thresholds, and the methods are different. For example, a simple statistical method can be used for multiple fourth measurement data. In this case, the indoor and outdoor differentiation threshold can be a simple indoor and outdoor differentiation threshold value; for another example, a training method can be used for multiple fourth measurement data. At this time, the indoor and outdoor distinction threshold can be a trained classifier for distinguishing indoor and outdoor terminals; for another example, a Gaussian mixture model can be used for multiple fourth measurement data. When the data is one-dimensional RSRP, the indoor and outdoor distinction threshold It can be the mean of the two means corresponding to the two fitted Gaussian distributions (that is, taking the mean of the two means); for another example, a Gaussian mixture model can be used for multiple fourth measurement data. When the data is two-dimensional data, such as RSRP and RSRQ, the fitted Gaussian distribution is two-dimensional, and the mean is a two-dimensional vector. At this time, the indoor and outdoor distinction threshold can be a straight line (that is, the mean of the two Gaussian distributions in the two-dimensional space is each one point, and the two points are connected. The vertical line of the line), the straight line divides the two-dimensional space (RSRP, RSRQ) into two parts. The side with the larger RSRP is the outdoor side, and the side with the smaller RSRP is the indoor side.

Compared with the related art in which all terminals to be differentiated in the serving cell adopt a unified fixed threshold, the embodiment of the present disclosure divides the serving cell into multiple location partitions. Each location partition corresponds to an indoor and outdoor differentiation threshold, which is determined based on the first measurement data. The location partition to which the location of the terminal to be differentiated belongs, and then the second measurement data can be compared with the indoor and outdoor differentiation threshold corresponding to the location partition to which the location of the terminal to be differentiated belongs to determine whether the terminal to be differentiated is an indoor terminal or an outdoor terminal. Since the service The community is finely divided into multiple location partitions. Each location partition uses different indoor and outdoor distinction thresholds instead of a unified fixed threshold. This makes the indoor and outdoor distinction thresholds corresponding to each location partition more in line with the actual situation of the location partition. It can more accurately distinguish indoor and outdoor terminals in the location zone.

The details of dividing the service cell into multiple location partitions are described in detail below.

In one embodiment, the plurality of location partitions of the serving cell are divided according to a plurality of third measurement data under the serving cell, and the third measurement data includes data related to the location of the first terminal. .

The embodiment of the present disclosure divides the serving cell according to the location of each first terminal under the serving cell to obtain multiple location partitions, which can make the multiple location partitions more consistent with the actual distribution of the first terminal in the serving cell, thereby enabling more accurate determination The location partition to which the location of the terminal to be differentiated belongs.

In one embodiment, the third measurement data includes a third time advance and a third horizontal azimuth angle; or includes a third time advance and a third beam of the serving cell with the strongest RSRP; or includes a third time advance The third neighbor cell with the strongest RSRP of the volume and serving cell.

In one embodiment, in order to ensure that there is a certain amount of third measurement data in each location partition for subsequent statistics, and to ensure the efficiency of serving cell division, the third measurement data can be discretized.

That is, step S102, before determining the location partition to which the location of the terminal to be distinguished belongs based on the first measurement data and the multiple location partitions divided by the serving cell, may also include: step A1 and step A2.

Step A1: Discretize the third time advance and the third horizontal azimuth angle in each third measurement data under the serving cell, respectively, to obtain multiple sets of discretized time advance and horizontal azimuth angles.

Step A2: Divide the serving cell according to the multiple sets of discretized time advances and horizontal azimuth angles to obtain multiple location partitions.

Multiple sets of discretized time advances and horizontal azimuth angles can respectively divide the serving cell by distance and angle, so that the serving cell can be divided into multiple location partitions.

For the discretization of the third horizontal azimuth angle in each third measurement data, hdoaGroup=round(hdoa/t ₁ )*t ₁ , round(.) is rounding, t ₁ is a parameter, which is determined according to the actual situation. For example, the default value is Value t ₁ =10.

For the discretization of the third time advance in each third measurement data, TAGroup=round(TA/t ₂ )*t ₂ , t ₂ is a parameter, which is determined according to the actual situation, for example, the default value is t ₂ =4.

At this time, the location partition key of the serving cell is: sCellkey_hdoaGroup_TAGroup.

The embodiment of the present disclosure divides the plurality of third measurement data into multiple groups through discretization. Each group corresponds to a pair of discretized time advance and horizontal azimuth (hdoaGroup_TAGroup), and multiple groups of discretized time advance and horizontal azimuth. Corner can be used to divide the service area into multiple location partitions.

Alternatively, step S102, before determining the location partition to which the location of the terminal to be distinguished belongs based on the first measurement data and the multiple location partitions divided by the serving cell, may also include: step B1 and step B2.

Step B1: Discretize the third time advance in each third measurement data under the serving cell to obtain multiple discretized time advances.

Step B2: Divide the serving cell according to multiple discretized time advances and multiple third beams to obtain multiple location partitions.

Multiple third beams of the serving cell with the strongest RSRP can divide the serving cell by angle, and multiple discretized time advances can divide the serving cell by distance. In this way, the serving cell can be divided to obtain multiple positions. Partition.

At this time, the location partition key of the serving cell is: sCellkey_StrongestBeam_TAGroup.

Alternatively, step S102, before determining the location partition to which the location of the terminal to be distinguished belongs according to the first measurement data and the multiple location partitions into which the serving cell is divided, may further include: steps C1 and step C2.

Step C1: Discretize the third time advance in each third measurement data under the serving cell to obtain multiple discretized time advances.

Step C2: Divide the serving cell according to multiple discretized time advances and multiple third neighboring cells to obtain multiple location partitions.

Multiple third neighboring cells with the strongest RSRP of the serving cell can divide the serving cell in angles, and multiple discretized time advances can divide the serving cell in distance. In this way, the serving cell can be divided into multiple Location partitioning.

At this time, the location partition key of the serving cell is: sCellkey_strongestnCellkey_TAGroup.

The details of determining the indoor and outdoor distinction thresholds are explained below.

In one embodiment, a Gaussian mixture model of clustering is used to accurately determine the indoor and outdoor differentiation threshold.

Step S103: Before determining that the terminal to be differentiated is an indoor terminal or an outdoor terminal according to the indoor and outdoor differentiation threshold corresponding to the location partition to which the terminal to be differentiated belongs and the second measurement data, the step may further include: steps S104 and Step S105.

Step S104: Obtain the outdoor Gaussian distribution and the indoor Gaussian distribution of each location partition using a plurality of fourth measurement data and a Gaussian mixture model of each location partition under the serving cell.

Step S105: Determine the indoor and outdoor differentiation threshold of each location partition based on the outdoor Gaussian distribution and indoor Gaussian distribution of each location partition.

The Gaussian mixture model uses the Gaussian probability density function (normal distribution curve) to accurately quantify things. It is a model based on the Gaussian probability density function (normal distribution curve) that decomposes things into several. Determining the indoor and outdoor distinction threshold through the Gaussian mixture model can make the indoor and outdoor distinction threshold more accurate.

In one embodiment, in order to avoid manual participation and avoid manual acquisition of training data for indoor and outdoor labels, the plurality of fourth measurement data for each location partition under the service cell do not have indoor and outdoor labels; using unsupervised learning, Determine the threshold for indoor and outdoor differentiation.

It can be divided into two situations. The first situation is: the fourth measurement data includes the RSRP and RSRQ of the serving cell measured by the first terminal; at this time, step S103, the use of each location partition under the serving cell A plurality of fourth measurement data and a Gaussian mixture model are used to obtain the outdoor Gaussian distribution and indoor Gaussian distribution of each location partition, which may include: sub-step S103A1, sub-step S103A2 and sub-step S103A3.

Sub-step S103A1: Discretize the RSRP and RSRQ in each fourth measurement data in each location partition, respectively, to obtain multiple pairs of discretized RSRP and RSRQ value pairs.

Sub-step S103A2: Count the frequency of occurrence of each pair of discretized RSRP and RSRQ value pairs in each location partition.

Sub-step S103A3: Use the frequency of occurrence of each pair of discretized RSRP and RSRQ value pairs in each location partition as well as multiple pairs of discretized RSRP and RSRQ value pairs as input, and use an unsupervised learning method to simulate the Gaussian mixture model. Combined, the two-dimensional outdoor Gaussian distribution and the two-dimensional indoor Gaussian distribution of each location partition are obtained.

Discretize RSRP and RSRQ in each fourth measurement data in each location partition:

RSRPGroup=round(RSRP/t ₃ )*t ₃

RSRQGroup=round(RSRQ/t ₄ )*t ₄

Among them, t ₃ and t ₄ are parameters, which are determined according to the actual situation. For example, the default values are t ₃ =5 and t ₄ =2.

Then count the frequency of occurrence of each pair of discretized RSRP and RSRQ values (RSRPGroup, RSRQGroup) in each location partition, and record it as cnt. x is a set of discretized value pairs (RSRPGroup, RSRQGroup), with a total of N value pairs (RSRPGroup, RSRQGroup), and n is the frequency set of each pair of value pairs (RSRPGroup, RSRQGroup). Among them (RSRPGroup _j , RSRQGroup _j ) represents the jth value pair (RSRPGroup, RSRQGroup), and cnt _j represents the frequency of the jth value pair (RSRPGroup, RSRQGroup).

Set the generated value pairs

and frequency set

As the input of the Gaussian mixture model, fit the distribution P(x) of the indoor and outdoor signal vector x = (RSRP, RSRQ) ^T of a location partition.

Among them, K=2 is the number of sub-Gaussian models in the Gaussian mixture model, D=2 is the data dimension, α _k is the probability that the measured data belongs to the k-th sub-Gaussian model, φ(x|μ _k ,∑ _k ) is the k-th sub-Gaussian model The probability density function of the sub-Gaussian model, μ _k is the data mean vector of the k-th sub-Gaussian model, ∑ _k is the covariance matrix of the k-th sub-Gaussian model, the superscripts (0), (i-1), (i) represents the parameters updated in the 0th, i-1, and i iterations respectively. The 0th iteration parameters are the preset initial values and can be set arbitrarily. The default setting is

The first element (μ _1,1 , μ _2,1 ) in the mean vector of the above Gaussian distribution 1 and Gaussian distribution 2 is the mean corresponding to RSRP, and the second element (μ _1,2 , μ _2,2 ) is RSRQ the corresponding mean. When determining the indoor and outdoor thresholds, take the first element in the mean vector, that is, the mean corresponding to RSRP, compare the size of the first element (μ _1,1 , μ _2,1 ) in the mean vector, and compare the size of the first element in the mean vector The large Gaussian distribution is the outdoor Gaussian distribution, and the small Gaussian distribution of the first element in the mean vector is the indoor Gaussian distribution. The second element (μ _1,2 , μ _2,2 ) in the mean vector of Gaussian distribution 1 and Gaussian distribution 2 is the mean value corresponding to RSRQ, which can be used to test the rationality of Gaussian distribution 1 and Gaussian distribution 2. Under normal circumstances , the second element in the mean vector determined to be the outdoor Gaussian distribution (i.e., the mean corresponding to the RSRQ of the outdoor Gaussian distribution) should be greater than the second element in the mean vector determined to be the indoor Gaussian distribution (i.e., the mean corresponding to the RSRQ of the indoor Gaussian distribution) mean); if the second element in the mean vector determined to be the outdoor Gaussian distribution (i.e., the mean corresponding to the RSRQ of the outdoor Gaussian distribution) is less than or equal to the second element in the mean vector determined to be the indoor Gaussian distribution (i.e., the mean value corresponding to the indoor Gaussian distribution The mean value corresponding to the RSRQ of Gaussian distribution), then Gaussian distribution 1 and Gaussian distribution 2 are unreasonable, and the location partition cannot distinguish indoor and outdoor terminals.

The second case is: the fourth measurement data includes the first RSRP and the first RSRQ of the serving cell measured by the first terminal and the second RSRP and the second RSRQ of the neighboring cell with the strongest RSRP; that is, the embodiment of the present disclosure , the fourth measurement data includes not only the first RSRP and the first RSRQ of the serving cell measured by the first terminal, but also includes the second RSRP and second RSRQ of the neighboring cell with the strongest RSRP measured by the first terminal.

At this time, step S103, using a plurality of fourth measurement data and a Gaussian mixture model for each location partition under the serving cell to obtain the outdoor Gaussian distribution and indoor Gaussian distribution for each location partition may include: sub-step S103B1 , sub-step S103B2, sub-step S103B3 and sub-step S103B4.

Sub-step S103B1: Obtain the mean RSRP of the first RSRP and the second RSRP and the mean RSRQ of the first RSRQ and the second RSRQ in each fourth measurement data in each location partition.

That is, the first RSRP and the second RSRP in each fourth measurement data are summed, and then the average is obtained to obtain the mean RSRP. The first RSRQ and the second RSRQ in each fourth measurement data are summed, and then the average is obtained. RSRQ.

Sub-step S103B2: Discretize each mean RSRP and mean RSRQ in each location partition, respectively, to obtain multiple pairs of discretized RSRP and RSRQ value pairs.

Sub-step S103B3: Count the frequency of occurrence of each pair of discretized RSRP and RSRQ value pairs in each location partition.

Sub-step S103B4: Use the frequency of occurrence of each pair of discretized RSRP and RSRQ value pairs in each location partition as well as multiple pairs of discretized RSRP and RSRQ value pairs as input, and use an unsupervised learning method to simulate the Gaussian mixture model. Combined, the two-dimensional outdoor Gaussian distribution and the two-dimensional indoor Gaussian distribution of each location partition are obtained.

In one embodiment, in order to ensure the accuracy of the indoor and outdoor differentiation thresholds, it is determined whether an abnormality occurs when determining the indoor and outdoor differentiation thresholds. If an abnormality occurs, the location partition cannot differentiate between indoor and outdoor terminals. That is, the method further includes: step S106.

Step S106: If there is an abnormality in the fitting of the Gaussian mixture model corresponding to the location partition, it is determined that indoor terminals and outdoor terminals cannot be distinguished in the location partition.

Wherein, the abnormal situation includes that the frequency of occurrence of each pair of discretized RSRP and RSRQ value pairs in the location partition is less than the first preset quantity threshold, or the number of pairs of discretized RSRP and RSRQ value pairs (i.e., the number of pairs of value pairs) logarithm) is less than the second preset quantity threshold.

When the frequency of occurrence of each pair of discretized RSRP and RSRQ value pairs in the location partition is less than the first preset quantity threshold, or the number of discretized pairs of RSRP and RSRQ value pairs is less than the second preset quantity threshold, it means that the number of discretized pairs of RSRP and RSRQ values in the location partition is less than the second preset quantity threshold. Fourth, there is too little measurement data to ensure that the subsequent distribution can be accurately fitted. At this time, the two Gaussian distributions fail to fit, and indoor and outdoor terminals cannot be distinguished in this location partition.

That is, in order to ensure that the subsequent distribution can be accurately fitted, the following two conditions need to be met.

Condition 1: (RSRPGroup, RSRQGroup) The frequency of value pairs should be ≥t ₅ , where t ₅ is a parameter (i.e., the first preset quantity threshold), which is determined according to the actual situation. For example, the default value is t ₅ =100.

Condition 2: The number of value pairs that satisfy condition 1 should be ≥t ₆ , where t ₆ is a parameter (ie, the second preset quantity threshold), which is determined according to the actual situation. For example, the default value is t ₆ =5.

Alternatively, the abnormal situation includes that the weight of any one of the two Gaussian distributions obtained by fitting is less than a preset weight threshold.

One of the two Gaussian distributions is an outdoor Gaussian distribution and the other is an indoor Gaussian distribution. If the weight of any one of the two Gaussian distributions is less than the preset weight threshold, it can be explained that the fourth measurement used to fit the two Gaussian distributions The data is unbalanced. The number of first terminals located indoors is very different from the number of first terminals located outdoors. This causes the two Gaussian distributions to be unable to accurately distinguish indoor and outdoor terminals. At this time, the fitting of the two Gaussian distributions fails. Location partitioning cannot differentiate between indoor and outdoor terminals.

Take the above fitting as an example: when α ₁ <t ₇ or α ₂ <t ₇ , the two Gaussian distributions fail to fit at this time, and the indoor and outdoor distinction cannot be made in this location partition, where t ₇ is a parameter (that is, the preset weight threshold), determined according to the actual situation, for example, the default value is t ₇ =0.05.

Alternatively, the abnormal situation includes that the covariance of any one of the two Gaussian distributions obtained by fitting is less than a preset covariance threshold.

The covariance of any one of the two Gaussian distributions is less than the preset covariance threshold, which can also indicate that the fourth measurement data used to fit the two Gaussian distributions is unbalanced. The number of first terminals located indoors is different from the number of first terminals located outdoors. The difference in the number of first terminals is too large, which causes the two Gaussian distributions to be unable to accurately distinguish indoor and outdoor terminals. At this time, the fitting of the two Gaussian distributions fails, and the distinction between indoor and outdoor terminals cannot be made in this location partition.

Take the above fitting as an example: when |Σ ₁ |<t ₈ or |Σ ₂ |<t ₈ , the two Gaussian distributions fail to fit at this time, and indoor and outdoor terminals cannot be distinguished in this location partition. Where |·| represents determinant calculation, t ₈ is a parameter (that is, the preset covariance threshold), which is determined according to the actual situation, for example, the default value t ₈ =1.

Alternatively, the abnormal situation includes that the distance between the corresponding means of the two Gaussian distributions obtained by fitting is less than a preset distance threshold.

The distance between the means corresponding to the two Gaussian distributions is less than the preset distance threshold, that is, the means corresponding to the two Gaussian distributions are close, which will result in the inability to accurately distinguish indoor and outdoor terminals.

Take the above fitting as _an example: |(μ ₁ -μ ₂ ) ^T (μ ₁ -μ ₂ )| t ₉ is a parameter, which is determined according to the actual situation. For example, the default value is t ₉ =5.

Alternatively, the abnormal situation includes that the mean relationships of the two two-dimensional Gaussian distributions are conflicting with each other.

The mean relationship between the two two-dimensional Gaussian distributions is contradictory, that is to say, the mean relationship between the two normal distributions is unreasonable. When the second element of the mean vector of the determined outdoor Gaussian distribution (that is, the RSRQ corresponding to the determined outdoor Gaussian distribution When the mean value) is not greater than the second element of the determined mean vector of the indoor Gaussian distribution (that is, the mean value corresponding to the RSRQ of the determined indoor Gaussian distribution), the relationship between the means of the two fitted normal distributions is unreasonable. At this time, the two The two-dimensional Gaussian distribution fitting failed, and indoor and outdoor terminals cannot be distinguished in this location partition.

For the terminal to be distinguished, the distance between the second measurement data and the centers of the two Gaussian distributions can be calculated. If it is close to the center of the indoor Gaussian distribution, it is determined that the terminal to be distinguished is an indoor terminal. If it is close to the center of the outdoor Gaussian distribution, it is determined that it needs to be distinguished. The terminal is an outdoor terminal. The center of the Gaussian distribution can be the center of the Gaussian distribution obtained by fitting one-dimensional RSRP, or it can be the center of the Gaussian distribution obtained by fitting two-dimensional RSRP or RSRQ.

For example, for the terminal to be differentiated, first determine the location partition to which the location of the terminal to be differentiated belongs, and calculate the signal characteristics of the second measurement data s = (RSRP, RSRQ) ^T and the mean vector μ in corresponding to the indoor Gaussian distribution of the location partition to which it belongs _. The distance ^d _in =| ₍ s-μ _in ) ^T (s-μ _in )|, and the distance d _out = |(s-μ _out ) ^T (s-μ _out )|.

If d _in < d _out , it means that the signal characteristics of the second measurement data are closer to the mean vector μ _in corresponding to the indoor Gaussian distribution, so it can be determined that the terminal to be distinguished is located indoors. If d _in ≥ d _out , it means that the signal of the second measurement data The feature is closer to the mean vector μ _out corresponding to the outdoor Gaussian distribution, so it can be determined that the terminal to be distinguished is located outdoors.

Referring to Figure 3, Figure 3 is a schematic structural diagram of an embodiment of a device for distinguishing indoor and outdoor terminals of the present disclosure. The device of the embodiment of the present disclosure can be applied in a base station. It should be noted that the device of this embodiment can implement the above method for distinguishing indoor and outdoor terminals. For detailed description of the relevant content, please refer to the above method section, which will not be described again here.

The device 100 includes a communication circuit 3, a memory 1 and a processor 2. The communication circuit 3 is used for communication; the memory 1 is used to store a computer program; the processor 2 is used to execute the computer program and execute the computer program. The computer program implements the method for distinguishing indoor and outdoor terminals as described above.

Among them, the processor 2 can be a micro control unit, a central processing unit or a digital signal processor, etc. The memory 1 can be a Flash chip, a read-only memory, a magnetic disk, an optical disk, a U disk or a mobile hard disk, etc.

The present disclosure also provides a computer-readable storage medium that stores a computer program. When the computer program is executed by a processor, the processor enables the processor to realize the distinction between indoor and outdoor terminals as described above. method.

Wherein, the computer-readable storage medium may be an internal storage unit of the above-mentioned device, such as a hard disk or a memory. The computer-readable storage medium can also be an external storage device of the above-mentioned device, such as a plug-in hard disk, a smart memory card, a secure digital card, a flash memory card, etc.

Embodiments of the present disclosure provide a method, device and storage medium for distinguishing indoor and outdoor terminals. The serving cell is divided into multiple location partitions. Each location partition corresponds to an indoor and outdoor differentiation threshold. The terminal to be differentiated is determined based on the first measurement data. The location partition to which the location belongs, and then the second measurement data can be compared with the indoor and outdoor differentiation threshold corresponding to the location partition to which the location of the terminal to be differentiated belongs to determine whether the terminal to be differentiated is an indoor terminal or an outdoor terminal. Due to the fine division of the serving cell For multiple location partitions, each location partition uses different indoor and outdoor distinction thresholds instead of a unified fixed threshold. This makes the indoor and outdoor distinction thresholds corresponding to each location partition more in line with the actual situation of the location partition, thus making it more accurate. The indoor and outdoor terminals that distinguish the location zone.

Those of ordinary skill in the art can understand that all or some steps, systems, and functional modules/units in the devices disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof.

In hardware implementations, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may consist of several physical components. Components execute cooperatively. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit . Such software may be distributed on computer-readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). As is known to those of ordinary skill in the art, the term computer storage media includes volatile and nonvolatile media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. removable, removable and non-removable media. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disk (DVD) or other optical disk storage, magnetic cassettes, tapes, disk storage or other magnetic storage devices, or may Any other medium used to store the desired information and that can be accessed by a computer. Additionally, it is known to those of ordinary skill in the art that communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media .

The optional embodiments of the present disclosure have been described above with reference to the accompanying drawings, but the scope of rights of the present disclosure is not thereby limited. Any modifications, equivalent substitutions and improvements made by those skilled in the art without departing from the scope and essence of the present disclosure shall be within the scope of rights of the present disclosure.

Claims

A method for distinguishing indoor and outdoor terminals, including:

Obtain first measurement data and second measurement data. The first measurement data includes data related to the location of the terminal to be distinguished. The second measurement data includes the reference signal received power RSRP measured by the terminal to be distinguished, or includes the reference signal received power RSRP measured by the terminal to be distinguished. RSRP and reference signal reception quality RSRQ measured by the terminal;

Determine the location partition to which the location of the terminal to be distinguished belongs based on the first measurement data and the multiple location partitions into which the serving cell has been divided; and

The terminal to be differentiated is determined to be an indoor terminal or an outdoor terminal according to the indoor and outdoor differentiation threshold corresponding to the location partition to which the terminal to be differentiated belongs and the second measurement data, wherein each location partition of the serving cell corresponds to an indoor terminal. The outdoor and indoor differentiation threshold is obtained based on a plurality of fourth measurement data of each location partition under the serving cell. The fourth measurement data includes the RSRP measured by the first terminal, or includes the first RSRP and RSRQ measured by the terminal.
The method according to claim 1, wherein the first measurement data includes a first timing advance and a first horizontal azimuth angle; or includes a first timing advance and a first beam with the strongest RSRP of the serving cell; or Including the first time advance and the first neighbor with the strongest RSRP.
The method according to claim 1, wherein the plurality of location partitions of the serving cell are divided according to a plurality of third measurement data under the serving cell, and the third measurement data includes information related to the first terminal Data related to your location.
The method according to claim 3, wherein the third measurement data includes a third time advance and a third horizontal azimuth angle; or includes a third time advance and a third beam with the strongest RSRP of the serving cell; or Including the third time advance and the third neighbor with the strongest RSRP.
The method according to claim 4, wherein before determining the location partition to which the location of the terminal to be distinguished belongs based on the first measurement data and the multiple location partitions into which the serving cell has been divided, the method further includes:

Discretize the third time advance and the third horizontal azimuth angle in each third measurement data under the serving cell, respectively, to obtain multiple sets of discretized time advance and horizontal azimuth angles;

Divide the serving cell according to the multiple sets of discretized time advances and horizontal azimuth angles to obtain multiple location partitions;

or

Discretize the third time advance in each third measurement data under the serving cell to obtain multiple discretized time advances;

Divide the serving cell according to the plurality of discretized time advances and the plurality of third beams to obtain a plurality of location partitions;

or

Discretize each third time advance under the serving cell to obtain multiple discretized time advances; and

According to the plurality of discretized time advances and the plurality of third neighboring cells, the serving cell is divided to obtain a plurality of location partitions.
The method according to claim 1, wherein the terminal to be distinguished is determined to be an indoor terminal or an outdoor terminal according to the indoor and outdoor differentiation threshold corresponding to the location partition to which the terminal to be distinguished is located and the second measurement data. ,Also includes:

Using a plurality of fourth measurement data and a Gaussian mixture model of each location partition under the service cell, the outdoor Gaussian distribution and the indoor Gaussian distribution of each location partition are obtained;

According to the outdoor Gaussian distribution and indoor Gaussian distribution of each location partition, the indoor and outdoor distinction threshold of each location partition is determined.
The method according to claim 6, wherein the plurality of fourth measurement data of each location partition under the serving cell do not have indoor and outdoor tags;

The fourth measurement data includes the RSRP and RSRQ of the serving cell measured by the first terminal;

The use of multiple fourth measurement data and Gaussian mixture models of each location partition under the service cell to obtain the outdoor Gaussian distribution and indoor Gaussian distribution of each location partition includes:

Discretize the RSRP and RSRQ in each fourth measurement data in each location partition separately to obtain multiple pairs of discretized RSRP and RSRQ value pairs;

Count the frequency of occurrence of each pair of discretized RSRP and RSRQ values in each location partition; and

The frequency of occurrence of each pair of discretized RSRP and RSRQ value pairs in each location partition and multiple pairs of discretized RSRP and RSRQ value pairs are used as input, and the Gaussian mixture model is fitted using an unsupervised learning method to obtain each Two-dimensional outdoor Gaussian distribution and two-dimensional indoor Gaussian distribution of location partitions;

or

The fourth measurement data includes the first RSRP and the first RSRQ of the serving cell measured by the first terminal and the second RSRP and the second RSRQ of the neighbor cell with the strongest RSRP;

The use of multiple fourth measurement data and Gaussian mixture models of each location partition under the service cell to obtain the outdoor Gaussian distribution and indoor Gaussian distribution of each location partition includes:

Obtain the mean RSRP of the first RSRP and the second RSRP in each fourth measurement data within each location partition, and the mean RSRQ of the first RSRQ and the second RSRQ;

Each mean RSRP and mean RSRQ in each location partition are discretized separately to obtain multiple pairs of discretized RSRP and RSRQ value pairs;

Count the frequency of occurrence of each pair of discretized RSRP and RSRQ values in each location partition; and

The frequency of occurrence of each pair of discretized RSRP and RSRQ value pairs in each location partition and multiple pairs of discretized RSRP and RSRQ value pairs are used as input, and the Gaussian mixture model is fitted using an unsupervised learning method to obtain each Two-dimensional outdoor Gaussian distribution and two-dimensional indoor Gaussian distribution of location partitions.
The method of claim 7, further comprising:

If there is an abnormality in the fitting of the Gaussian mixture model corresponding to the location partition, it is determined that indoor terminals and outdoor terminals cannot be distinguished in the location partition;

The abnormal situation includes that the frequency of occurrence of each pair of discretized RSRP and RSRQ value pairs in the location partition is less than the first preset quantity threshold, or the number of discretized pairs of RSRP and RSRQ value pairs is less than the second preset quantity threshold. ;

Alternatively, the abnormal situation includes that the weight of any one of the two Gaussian distributions obtained by fitting is less than the preset weight threshold;

Alternatively, the abnormal situation includes that the covariance of any one of the two Gaussian distributions obtained by fitting is less than the preset covariance threshold;

Alternatively, the abnormal situation includes that the distance between the corresponding means of the two Gaussian distributions obtained by fitting is less than a preset distance threshold;

Alternatively, the abnormal situation includes that the mean relationships of the two two-dimensional Gaussian distributions are conflicting with each other.
A device for distinguishing indoor and outdoor terminals, the device includes a communication circuit, a memory and a processor, the communication circuit is used for communication; the memory is used to store a computer program; the processor is used to execute the computer program and When the computer program is executed, the method for distinguishing indoor and outdoor terminals according to any one of claims 1 to 8 is implemented.
A computer-readable storage medium that stores a computer program. When executed by a processor, the computer program causes the processor to implement the indoor and outdoor terminal as claimed in any one of claims 1-8. method of differentiation.