Positioning method, apparatus, computer readable medium, and electronic device

Abstract

The present disclosure relates to a positioning method, device, computer readable medium and electronic device. The method comprises: in response to receiving a user positioning request, determining at least one candidate point of interest corresponding to the user positioning request, wherein the user positioning request comprises first WiFi fingerprint information; for each candidate point of interest, extracting a similarity feature of the first WiFi fingerprint information and second WiFi fingerprint information of the candidate point of interest by an image feature extraction model; and determining a target point of interest where the user is located from the at least one candidate point of interest according to each similarity feature. By using the image feature extraction model in the image field to depict the fingerprint similarity, the complex work of manually designing features can be avoided, and the fingerprint similarity measurement has good generalization ability.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of indoor positioning, and in particular, to a positioning method, device, computer readable medium and electronic device. BACKGROUND

[0002] As a commonly used method of Point of Interest (POI) positioning, WiFi fingerprint positioning technology is widely used to serve users due to its advantages of no need for manual deployment of devices and good spatial distribution characteristics. In common WiFi fingerprint positioning technology, the POI is effectively positioned according to the similarity between the fingerprint matrix in the positioning request and the historical fingerprint matrix to meet the needs of users. The similarity of fingerprints, as an important feature information, directly affects the credibility of the final positioning result. SUMMARY

[0003] This summary is provided to introduce a selection of concepts that are further described below in the detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

[0004] In a first aspect, the present disclosure provides a positioning method, comprising:

[0005] determining at least one candidate POI corresponding to a user positioning request in response to receiving the user positioning request, wherein the user positioning request comprises first WiFi fingerprint information;

[0006] extracting, for each candidate POI, a similarity feature of the first WiFi fingerprint information and second WiFi fingerprint information of the candidate POI through an image feature extraction model;

[0007] determining a target POI where the user is located from the at least one candidate POI according to each similarity feature.

[0008] In a second aspect, the present disclosure provides a positioning device, comprising:

[0009] a first determining module configured to determine at least one candidate POI corresponding to a user positioning request in response to receiving the user positioning request, wherein the user positioning request comprises first WiFi fingerprint information;

[0010] a feature extraction module configured to extract, for each candidate POI, a similarity feature of the first WiFi fingerprint information and second WiFi fingerprint information of the candidate POI through an image feature extraction model;

[0011] The second determining module is used to determine the user's target interest point from the at least one candidate interest point based on each of the similarity features.

[0012] Thirdly, this disclosure provides a computer-readable medium having a computer program stored thereon, which, when executed by a processing device, implements the steps of the positioning method provided in the first aspect of this disclosure.

[0013] Fourthly, this disclosure provides an electronic device, comprising:

[0014] A storage device on which computer programs are stored;

[0015] A processing device is configured to execute the computer program in the storage device to implement the steps of the positioning method provided in the first aspect of this disclosure.

[0016] In the above technical solution, upon receiving a user location request, at least one candidate point of interest (POI) corresponding to the user location request is first determined. Then, for each candidate POI, an image feature extraction model is used to extract similarity features between the first WiFi fingerprint information carried in the user location request and the second WiFi fingerprint information of the candidate POI. Finally, based on each similarity feature, the user's target POI is determined from the at least one candidate POI. Utilizing an image feature extraction model from the image domain to characterize fingerprint similarity avoids the complex work of manually designing features, resulting in better generalization ability for fingerprint similarity measurement.

[0017] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0018] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale. In the drawings:

[0019] Figure 1 This is a schematic diagram of the fingerprint similarity calculation process in related technologies.

[0020] Figure 2 This is a flowchart illustrating a positioning method according to an exemplary embodiment.

[0021] Figure 3 This is a schematic diagram illustrating a cross-merging of a first fingerprint matrix and a second fingerprint matrix according to an exemplary embodiment.

[0022] Figure 4This is a schematic diagram illustrating a process for extracting similarity features between a first fingerprint matrix and a second fingerprint matrix according to an exemplary embodiment.

[0023] Figure 5 This is a schematic diagram illustrating a process of extracting similarity features of a first similarity metric matrix using an image feature extraction model, according to an exemplary embodiment.

[0024] Figure 6 This is a block diagram illustrating a positioning device according to an exemplary embodiment.

[0025] Figure 7 This is a schematic diagram of the structure of an electronic device according to an exemplary embodiment. Detailed Implementation

[0026] As discussed in the background section, fingerprint similarity, as a crucial feature, directly impacts the reliability of the final localization result due to the accuracy of its calculation.

[0027] Current fingerprint similarity calculation methods mostly employ manually designed features. For example, they calculate fingerprint similarity based on the WiFi list information scanned by the user in real time (i.e., the fingerprint matrix in the user's location request, referred to as the first fingerprint matrix below) and the WiFi fingerprint list information already constructed based on historical information (i.e., the second fingerprint matrix below), typically using a joint probability approach. Specifically, such as... Figure 1 As shown, for each WiFi in the real-time scanned WiFi list (i.e., W1, W2, W3, ..., Wn), the similarity Pi (i.e., P1, P2, P3, ..., Pn) between its scanned signal strength distribution and its historical signal strength distribution is calculated. Finally, the fingerprint similarity P is obtained based on the similarity results of multiple WiFis. It is evident that current methods focus on designing more reasonable methods for calculating P values. However, this approach relies excessively on human experience, resulting in a lack of generalization ability in fingerprint similarity measurement schemes.

[0028] In view of this, the present disclosure provides a positioning method, apparatus, computer-readable medium, and electronic device.

[0029] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0030] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0031] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0032] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0033] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0034] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0035] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0036] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0037] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0038] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0039] Meanwhile, it is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0040] Figure 2 This is a flowchart illustrating a positioning method according to an exemplary embodiment. For example... Figure 2 As shown, the positioning method may include the following steps S201 to S203.

[0041] In S201, in response to receiving a user location request, at least one candidate point of interest corresponding to the user location request is determined, wherein the user location request includes first WiFi fingerprint information.

[0042] In this disclosure, upon receiving a user's location request, a prompt message can be sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosure, based on the prompt message.

[0043] The first WiFi fingerprint information may include: a list of WiFi networks scanned by the terminal that initiated the user location request (e.g., ...). Figure 3 The first fingerprint matrix (as shown in the diagram, W1, W2, W3, ..., Wn) is formed by the distribution of scanned signal strengths of each WiFi in the WiFi list. Figure 3 (As shown).

[0044] When a user needs to know their location of a Point of Interest (POI), they can trigger a location request through a device (such as a smartphone, smart bracelet, etc.) to obtain the target POI.

[0045] For example, if a user initiates navigation from a store in a shopping mall (the store being a Point of Interest, or POI), the GPS signal may be lost or obstructed due to the indoor environment, preventing accurate location of the user's actual POI. In this case, the navigation start point may not be the store itself, but rather the entire shopping mall. The user can then request a location request to obtain their target POI.

[0046] Among them, there may be one or more candidate points of interest corresponding to the user's location request.

[0047] In S202, for each candidate point of interest, the similarity features between the first WiFi fingerprint information and the second WiFi fingerprint information of the candidate point of interest are extracted using an image feature extraction model.

[0048] In this disclosure, the second WiFi fingerprint information may include: a second fingerprint matrix consisting of the WiFi networks associated with the candidate point of interest and the historical signal strength distributions of each WiFi network associated with the candidate point of interest. A WiFi fingerprint database can be pre-established, which includes the second WiFi fingerprint information of different reference points of interest, i.e., WiFi fingerprint information of different reference POIs. The candidate points of interest are a subset of the reference points of interest in the WiFi fingerprint database. The WiFi fingerprint database is constructed based on historical POI visit data from multiple dimensions.

[0049] Image feature extraction models can be, for example, convolutional neural networks or attention-based convolutional neural networks.

[0050] In S203, based on each similarity feature, the user's target interest point is determined from at least one candidate interest point.

[0051] In the above technical solution, upon receiving a user location request, at least one candidate point of interest (POI) corresponding to the user location request is first determined. Then, for each candidate POI, an image feature extraction model is used to extract similarity features between the first WiFi fingerprint information carried in the user location request and the second WiFi fingerprint information of the candidate POI. Finally, based on each similarity feature, the user's target POI is determined from the at least one candidate POI. Utilizing an image feature extraction model from the image domain to characterize fingerprint similarity avoids the complex work of manually designing features, resulting in better generalization ability for fingerprint similarity measurement.

[0052] The i-th row of the first fingerprint matrix represents the signal strength distribution of the i-th WiFi in the WiFi list scanned by the terminal that initiated the user location request. The j-th column of the first fingerprint matrix corresponds to the j-th signal strength interval. If the signal strength value of the i-th WiFi falls within the j-th signal strength interval, then the element value of the i-th row and j-th column of the first fingerprint matrix is ​​1, and the element values ​​of the remaining columns of the i-th row of the first fingerprint matrix are 0.

[0053] For example, such as Figure 3As shown, the first fingerprint matrix is ​​an n*6 matrix. The first row of the first fingerprint matrix represents the scanning signal strength distribution of Wi-Fi "W1", the second row represents the scanning signal strength distribution of Wi-Fi "W2", the third row represents the scanning signal strength distribution of Wi-Fi "W3", and so on, with the nth row representing the scanning signal strength distribution of Wi-Fi "Wn". The first column of the first fingerprint matrix corresponds to the first signal strength interval [-50dBm, -40dBm], and the second column corresponds to the second signal strength interval [-60dBm, -50dBm]. The first fingerprint matrix has a 0dBm signal strength range. The third column of the first fingerprint matrix corresponds to the third signal strength range [-70dBm, -60dBm). The fourth column of the first fingerprint matrix corresponds to the fourth signal strength range [-80dBm, -70dBm). The fifth column of the first fingerprint matrix corresponds to the fifth signal strength range [-90dBm, -80dBm). The sixth column of the first fingerprint matrix corresponds to the sixth signal strength range [-100dBm, -90dBm]. The scanning signal strength values ​​of W1, W2, W3, ..., Wn are -46dBm, -68dBm, -81dBm, ..., -80dBm, respectively.

[0054] As can be seen, the Wi-Fi “W1” scanning signal strength value of -46dBm falls within the first signal strength interval [-50dBm, -40dBm]. Therefore, the element value of the first row and first column of the first fingerprint matrix is ​​1, and the element values ​​of the other columns in the first row are 0, that is, the Wi-Fi “W1” scanning signal strength distribution is “1 0 0 0 0 0”. The Wi-Fi “W2” scanning signal strength value of -68dBm falls within the third signal strength interval [-70dBm, -60dBm]. Therefore, the element value of the second row and third column of the first fingerprint matrix is ​​1, and the element values ​​of the other columns in the second row are 0, that is, the Wi-Fi “W2” scanning signal strength distribution is “0 0 1 0 0”. 0”; The scan signal strength value of Wifi “W3”, “-81dBm”, falls within the 5th signal strength interval [-90dBm, -80dBm). Therefore, the element value of the 3rd row and 5th column of the first fingerprint matrix is ​​1, and the element value of the other columns in the 3rd row is 0. That is, the scan signal strength distribution of Wifi “W3” is “0 0 00 1 0”; ...; The scan signal strength value of Wifi “Wn”, “-80dBm”, falls within the 4th signal strength interval [-80dBm, -70dBm]. Therefore, the element value of the nth row and 4th column of the first fingerprint matrix is ​​1, and the element value of the other columns in the nth row is 0. That is, the scan signal strength distribution of Wifi “Wn” is “0 0 0 1 0 0”.

[0055] Furthermore, the m-th row of the second fingerprint matrix represents the historical signal strength distribution of the m-th WiFi associated with the candidate point of interest, the k-th column of the second fingerprint matrix corresponds to the k-th signal strength interval, and the element value of the m-th row and k-th column of the second fingerprint matrix represents the number of historical signal strength values ​​among the multiple historical signal strength values ​​corresponding to the m-th WiFi associated with the candidate point of interest that fall within the k-th signal strength interval. These multiple historical signal strength values ​​include the signal strength values ​​of the m-th WiFi scanned by users who visited the candidate point of interest during the historical time period. It is worth noting that the WiFi list scanned by the terminal initiating the user location request may be completely identical to the WiFi associated with the candidate point of interest (e.g., ...). Figure 3 As shown, all are W1, W2, W3, ..., Wn), and may be partially the same. Correspondingly, the number of rows in the second fingerprint matrix may be equal to or different from the number of rows in the first fingerprint matrix; and the number of columns in the second fingerprint matrix is ​​equal to the number of columns in the first fingerprint matrix.

[0056] For example, such as Figure 3 As shown, the second fingerprint matrix, composed of the historical signal strength distributions of each WiFi network associated with a candidate point of interest A, is an n*6 matrix. The first row of the second fingerprint matrix represents the historical signal strength distribution of WiFi "W1", the second row represents the historical signal strength distribution of WiFi "W2", the third row represents the historical signal strength distribution of WiFi "W3", and so on, with the nth row representing the historical signal strength distribution of WiFi "Wn". The first column of the second fingerprint matrix corresponds to the first signal strength interval [-50d]. The second column of the second fingerprint matrix corresponds to the second signal strength range [-60dBm, -40dBm], the third column of the second fingerprint matrix corresponds to the third signal strength range [-70dBm, -60dBm), the fourth column of the second fingerprint matrix corresponds to the fourth signal strength range [-80dBm, -70dBm), the fifth column of the second fingerprint matrix corresponds to the fifth signal strength range [-90dBm, -80dBm), and the sixth column of the second fingerprint matrix corresponds to the sixth signal strength range [-100dBm, -90dBm].

[0057] Furthermore, the Wi-Fi "W1" associated with candidate point of interest A has 23 historical signal strength values. Of these, 5 historical signal strength values ​​fall within the first signal strength interval [-50dBm, -40dBm], 7 fall within the second signal strength interval [-60dBm, -50dBm), 9 fall within the third signal strength interval [-70dBm, -60dBm], and 4 fall within the fourth signal strength interval [-50dBm, -40dBm]. The number of historical signal strength values ​​within the range of -80dBm to -70dBm is 1. The number of historical signal strength values ​​within the fifth signal strength range of -90dBm to -80dBm is 1. The number of historical signal strength values ​​within the sixth signal strength range of -100dBm to -90dBm is 0. Therefore, the element values ​​of the first row of the second fingerprint matrix are 5, 7, 9, 1, 1, and 0, respectively. That is, the historical signal strength distribution of the Wifi “W1” associated with candidate point of interest A is “5 7 9 11 0”.

[0058] Candidate point of interest A is associated with Wi-Fi "W2" and has 59 historical signal strength values. Of these, 2 historical signal strength values ​​fall within the first signal strength range [-50dBm, -40dBm], 3 fall within the second range [-60dBm, -50dBm], 44 fall within the third range [-70dBm, -60dBm], and [the remaining values ​​fall within the fourth range [-80dBm, -50dBm]]. The number of historical signal strength values ​​within the range of -70dBm is 5, the number of historical signal strength values ​​within the range of -90dBm to -80dBm is 4, and the number of historical signal strength values ​​within the range of -100dBm to -90dBm is 1. Therefore, the element values ​​of the second row of the second fingerprint matrix are 2, 3, 44, 5, 4, and 1, respectively. That is, the historical signal strength distribution of the Wifi “W2” associated with candidate point of interest A is “2344 5 4 1”.

[0059] Similarly, the historical signal strength distribution of Wifi “W3” associated with candidate point of interest A is “2 610 1 11”; ...; the historical signal strength distribution of Wifi “Wn” associated with candidate point of interest A is “1 2 9 3 1 4”.

[0060] The following is a detailed description of a specific implementation method for determining at least one candidate point of interest corresponding to the user location request in step S201 above. Specifically, this can be implemented in various ways. In one implementation, the user location request may further include first-type location information (e.g., latitude and longitude information) of the terminal initiating the user location request. In this case, reference points of interest located within a preset distance range of the terminal in the WiFi fingerprint database can be determined as candidate points of interest based on the first-type location information. The candidate points of interest are second-type location information, and the first-type location information and the second-type location information are used to describe the terminal's location information from different perspectives.

[0061] In another implementation, candidate points of interest (POIs) can be determined from the list of WiFi networks scanned by the terminal initiating the user location request, and the points of interest associated with each WiFi network. Here, a pre-established association between WiFi networks and POIs can be used; for example, if a WiFi network is associated with store B as a POI, the POIs associated with each WiFi network in the aforementioned list can be determined based on this association.

[0062] The following is a detailed description of the specific implementation method for extracting the similarity features between the first WiFi fingerprint information and the second WiFi fingerprint information of the candidate interest point using the image feature extraction model in step S202 above. Specifically, it can be achieved through the following steps (1) and (2):

[0063] Step (1): Cross-merge the first fingerprint matrix and the second fingerprint matrix to obtain the similarity measurement matrix.

[0064] In this disclosure, the first fingerprint matrix and the second fingerprint matrix are cross-merged in order to convert the first fingerprint matrix and the second fingerprint matrix into a format that the image feature extraction model can process, that is, to perform data conversion.

[0065] Step (2): Input the similarity metric matrix into the image feature extraction model to obtain similarity features.

[0066] In the above implementation, the similarity measurement matrix obtained by cross-merging the first fingerprint matrix and the second fingerprint matrix is ​​used as the input of the image feature extraction model. The first fingerprint matrix consists of the WiFi list scanned by the terminal and the scanning signal intensity distribution of each WiFi. The second fingerprint matrix consists of the historical signal intensity distribution of each WiFi associated with the candidate point of interest. Since the signal intensity distribution is the original information, the input information of the image feature extraction model is relatively original. In this way, the image feature extraction model can learn more and more comprehensive similarity features from the original information, thereby improving the accuracy of fingerprint similarity measurement.

[0067] The following is a detailed description of the specific implementation method for cross-merging the first fingerprint matrix and the second fingerprint matrix in step (1) above. Specifically, it can be implemented through various methods. In one implementation method, the first fingerprint matrix and the second fingerprint matrix can be alternately merged row by row to obtain a similarity measurement matrix.

[0068] Specifically, if the number of rows in the second fingerprint matrix is ​​equal to the number of rows in the first fingerprint matrix, that is, the second fingerprint matrix and the first fingerprint matrix have the same dimension, then the i-th row of the first fingerprint matrix can be used as the 2i-1-th row of the similarity measurement matrix, and the m-th row of the second fingerprint matrix can be used as the 2m-th row of the similarity measurement matrix. Alternatively, the m-th row of the second fingerprint matrix can be used as the (2m-1)-th row of the similarity measurement matrix, and the i-th row of the first fingerprint matrix can be used as the 2i-th row of the similarity measurement matrix.

[0069] If the number of rows in the second fingerprint matrix is ​​greater than the number of rows in the first fingerprint matrix, then the m-th row of the second fingerprint matrix can be used as the (2m-1)-th row of the similarity measurement matrix, where m is less than or equal to the number of rows in the first fingerprint matrix. The i-th row of the first fingerprint matrix can be used as the 2i-th row of the similarity measurement matrix. After that, the remaining rows of the second fingerprint matrix can be used as the last few rows of the similarity measurement matrix. Alternatively, the i-th row of the first fingerprint matrix can be used as the (2i-1)-th row of the similarity measurement matrix, and the m-th row of the second fingerprint matrix can be used as the 2m-th row of the similarity measurement matrix, where m is less than or equal to the number of rows in the first fingerprint matrix. After that, the remaining rows of the second fingerprint matrix can be used as the last few rows of the similarity measurement matrix.

[0070] If the number of rows in the second fingerprint matrix is ​​less than the number of rows in the first fingerprint matrix, then the m-th row of the second fingerprint matrix can be used as the 2m-1-th row of the similarity measurement matrix, and the i-th row of the first fingerprint matrix can be used as the 2i-th row of the similarity measurement matrix, where i is less than or equal to the number of rows in the second fingerprint matrix. Then, the remaining rows of the first fingerprint matrix can be used as the last few rows of the similarity measurement matrix. Alternatively, the i-th row of the first fingerprint matrix can be used as the (2i-1)-th row of the similarity measurement matrix, where i is less than or equal to the number of rows in the second fingerprint matrix, and the m-th row of the second fingerprint matrix can be used as the m-th row of the similarity measurement matrix. Then, the remaining rows of the first fingerprint matrix can be used as the last few rows of the similarity measurement matrix.

[0071] In another implementation, when merging the first fingerprint matrix and the second fingerprint matrix, the scanning signal intensity distribution and historical signal intensity distribution of the same WiFi can be arranged adjacently to form the original feature sub-matrix of similarity for this WiFi. That is, the scanning signal intensity distribution and historical signal intensity distribution of the same WiFi are arranged adjacently in the similarity measurement matrix. In this way, the similarity relationship can be better reflected in the input data of the image feature extraction module, improving the accuracy of fingerprint similarity measurement.

[0072] Specifically, if the WiFi associated with the candidate point of interest includes all WiFi networks in the WiFi list scanned by the terminal initiating the user location request, that is, if there are no WiFi networks in the WiFi list scanned by the terminal initiating the user location request that are different from the WiFi networks associated with the candidate point of interest, a similarity measurement matrix can be obtained by arranging the scan signal strength distribution and historical signal strength distribution of the same WiFi networks adjacent to each other.

[0073] If the terminal initiating the user location request scans a WiFi list containing WiFi networks that are not associated with the candidate point of interest, after arranging the scanned signal strength distribution and historical signal strength distribution of the same WiFi networks adjacently, it is also necessary to arrange the historical signal strength distribution of the remaining WiFi networks in the second fingerprint matrix (excluding the aforementioned same WiFi networks) into the last odd-numbered rows of the similarity metric matrix. In this case, the next adjacent even-numbered row of each odd-numbered row in the last odd-numbered row is filled with zero element values, and each row of the second fingerprint matrix is ​​arranged into the odd-numbered rows of the similarity metric matrix. Alternatively, it is also necessary to arrange the historical signal strength distribution of the remaining WiFi networks in the second fingerprint matrix (excluding the aforementioned same WiFi networks) into the last even-numbered rows of the similarity metric matrix. In this case, the previous adjacent odd-numbered row of each even-numbered row in the last even-numbered row is filled with zero element values, and each row of the second fingerprint matrix is ​​arranged into the even-numbered rows of the similarity metric matrix.

[0074] For example, such as Figure 3 As shown, the WiFi list scanned by the terminal initiating the user location request is exactly the same as the WiFi associated with candidate point of interest A. That is, the WiFi associated with candidate point of interest A includes all the WiFi in the WiFi list scanned by the terminal initiating the user location request. In this case, by arranging the scanned signal strength distribution and historical signal strength distribution of the same WiFi adjacently, we can obtain the following... Figure 3 The similarity measurement matrix is ​​shown.

[0075] In addition, the image feature extraction model described above may include convolutional layers, pooling layers, and flattening layers connected in sequence.

[0076] The convolutional layer is used to perform a convolution operation with a stride of 2 on the similarity metric matrix to extract the similarity of the signal intensity distributions of adjacent arrays and obtain the first feature matrix; the pooling layer is used to extract features from the first feature matrix to obtain the second feature matrix; and the flattening layer is used to flatten the second feature matrix into a one-dimensional vector as a similarity feature.

[0077] For example, such as Figure 4 and Figure 5 As shown, the convolutional layer uses 16 convolutional kernels of size 2*N with a stride of 2 to convolve the similarity metric matrix to extract the similarity of signal intensity distributions in adjacent arrays, resulting in the first feature matrix. Then, the pooling layer uses a pooling layer of size 1*2 with a stride of 1 to extract features from the features extracted by different convolutional kernels (specifically, extracting the MAX value from the feature values ​​of corresponding rows in the similarity features extracted by adjacent convolutional kernels), suppressing noise and reducing information redundancy, ultimately obtaining an M*M second feature matrix. Finally, the second feature matrix is ​​flattened into an L*1 one-dimensional vector as the similarity feature. Here, N is the number of columns in the first fingerprint matrix, M is equal to half the number of rows in the similarity metric matrix, and L = M... 2 .

[0078] In the above implementation, by using an image feature extraction model to perform convolution and pooling operations on the similarity measurement matrix, the relationships between different WiFi networks can be learned, thereby enabling better utilization of information from different WiFi networks and improving the accuracy of fingerprint similarity measurement.

[0079] In addition, the historical signal strength distribution of each WiFi associated with the candidate point of interest in the second fingerprint matrix is ​​arranged according to the popularity of the corresponding WiFi. In this way, the sequence relationship between the WiFi associated with the candidate point of interest can be reflected, and the sequence relationship can be used as the original information to input into the image feature extraction model, thereby further improving the accuracy of fingerprint similarity measurement.

[0080] The following is a detailed description of the specific implementation method for determining the user's target interest point from at least one candidate interest point based on each similarity feature in S203 above. Specifically, it can be achieved through the following steps (a) and (b):

[0081] Step (a): For each candidate point of interest, determine the probability that the user is at that candidate point of interest based on the similarity features corresponding to that candidate point of interest.

[0082] Specifically, for each candidate point of interest, the similarity features corresponding to that candidate point of interest can be input into a pre-trained probability prediction model (e.g., a neural network model) to obtain the probability that the user is at that candidate point of interest.

[0083] Step (b): Determine the user's target interest point from at least one candidate interest point based on each probability.

[0084] Specifically, the candidate interest point corresponding to the maximum value among all probabilities can be determined as the user's target interest point.

[0085] In addition, to improve the accuracy of the above probability prediction and thus improve the positioning accuracy, in addition to the similarity features corresponding to the candidate points of interest, information such as scanning coverage, the distance between the terminal and the point of interest, and the popularity of each WiFi in the WiFi list can also be considered. The scanning coverage is the ratio of the number of targets to the total number of WiFi associated with the candidate point of interest, and the number of targets is the number of identical WiFi in the WiFi list associated with the candidate point of interest.

[0086] Figure 6 This is a block diagram illustrating a positioning device according to an exemplary embodiment. Figure 6 As shown, the device 300 includes:

[0087] The first determining module 301 is configured to determine at least one candidate point of interest corresponding to the user location request in response to receiving the user location request, wherein the user location request includes first WiFi fingerprint information.

[0088] Feature extraction module 302 is used to extract similarity features between the first WiFi fingerprint information and the second WiFi fingerprint information of the candidate interest point for each candidate interest point through an image feature extraction model;

[0089] The second determining module 303 is used to determine the user's target interest point from the at least one candidate interest point based on each of the similarity features.

[0090] In the above technical solution, upon receiving a user location request, at least one candidate point of interest (POI) corresponding to the user location request is first determined. Then, for each candidate POI, an image feature extraction model is used to extract similarity features between the first WiFi fingerprint information carried in the user location request and the second WiFi fingerprint information of the candidate POI. Finally, based on each similarity feature, the user's target POI is determined from the at least one candidate POI. Utilizing an image feature extraction model from the image domain to characterize fingerprint similarity avoids the complex work of manually designing features, resulting in better generalization ability for fingerprint similarity measurement.

[0091] Optionally, the first WiFi fingerprint information includes a first fingerprint matrix composed of the scan signal strength distributions of multiple WiFi networks, and the second WiFi fingerprint information includes a second fingerprint matrix composed of the historical signal strength distributions of each WiFi network associated with the candidate point of interest.

[0092] The feature extraction module 302 includes:

[0093] The merging submodule is used to cross-merge the first fingerprint matrix and the second fingerprint matrix to obtain a similarity measurement matrix;

[0094] The extraction submodule is used to input the similarity metric matrix into the image feature extraction model to obtain the similarity features.

[0095] Optionally, the scan signal strength distribution and historical signal strength distribution of the same WiFi in the similarity metric matrix are arranged adjacently.

[0096] Optionally, the image feature extraction model includes a convolutional layer, a pooling layer, and a flattening layer connected in sequence;

[0097] The convolutional layer is used to perform a convolution operation with a stride of 2 on the similarity metric matrix to extract the similarity of the signal intensity distributions of adjacent arrays and obtain the first feature matrix.

[0098] The pooling layer is used to extract features from the first feature matrix to obtain a second feature matrix.

[0099] The flattening layer is used to flatten the second feature matrix into a one-dimensional vector, which serves as the similarity feature.

[0100] Optionally, the historical signal strength distribution of each WiFi associated with the candidate point of interest in the second fingerprint matrix is ​​arranged according to the popularity of the corresponding WiFi.

[0101] Optionally, the user location request may further include a first type of location information of the terminal that initiated the user location request, and the candidate point of interest may be a second type of location information;

[0102] The first determining module 301 is used to determine the reference points of interest located within a preset distance range of the terminal in the WiFi fingerprint database as the candidate points of interest based on the first type of location information, wherein the WiFi fingerprint database includes second WiFi fingerprint information of different reference points of interest.

[0103] Optionally, the first WiFi fingerprint information includes a list of WiFi networks scanned by the terminal that initiated the user location request;

[0104] The first determining module 301 is used to determine the points of interest associated with each WiFi in the WiFi list as the candidate points of interest.

[0105] Optionally, the second determining module 303 includes:

[0106] The first determining submodule is used to determine the probability that a user is at each candidate point of interest based on the similarity features corresponding to that candidate point of interest.

[0107] The second determining submodule is used to determine the user's target interest point from the at least one candidate interest point according to each of the probabilities.

[0108] This disclosure also provides a computer-readable medium having a computer program stored thereon, which, when executed by a processing device, implements the steps of the positioning method described above.

[0109] The following is for reference. Figure 7 The diagram illustrates a structural schematic of an electronic device (e.g., a terminal device) 600 suitable for implementing embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0110] like Figure 7 As shown, electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 601, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 602 or a program loaded from storage device 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of electronic device 600. Processing device 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0111] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic device 600 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 7 An electronic device 600 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0112] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a storage device 608, or installed from a ROM 602. When the computer program is executed by the processing device 601, it performs the functions defined in the methods of embodiments of this disclosure.

[0113] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0114] In some implementations, the client can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0115] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0116] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: in response to receiving a user location request, determine at least one candidate point of interest corresponding to the user location request, wherein the user location request includes first WiFi fingerprint information; for each candidate point of interest, extract similarity features between the first WiFi fingerprint information and second WiFi fingerprint information of the candidate point of interest using an image feature extraction model; and determine the user's target point of interest from the at least one candidate point of interest based on each similarity feature.

[0117] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0118] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0119] The modules described in the embodiments of this disclosure can be implemented in software or in hardware. The names of the modules are not necessarily limiting in certain circumstances; for example, the first determining module can also be described as "a module that, in response to receiving a user location request, determines at least one candidate point of interest corresponding to the user location request."

[0120] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0121] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0122] According to one or more embodiments of this disclosure, Example 1 provides a positioning method, comprising: in response to receiving a user positioning request, determining at least one candidate point of interest corresponding to the user positioning request, wherein the user positioning request includes first WiFi fingerprint information; for each candidate point of interest, extracting similarity features between the first WiFi fingerprint information and second WiFi fingerprint information of the candidate point of interest using an image feature extraction model; and determining a target point of interest where the user is located from the at least one candidate point of interest based on each similarity feature.

[0123] According to one or more embodiments of this disclosure, Example 2 provides the method of Example 1, wherein the first WiFi fingerprint information includes a first fingerprint matrix composed of the scanning signal strength distributions of multiple WiFi networks, and the second WiFi fingerprint information includes a second fingerprint matrix composed of the historical signal strength distributions of each WiFi network associated with the candidate point of interest; the step of extracting similarity features between the first WiFi fingerprint information and the second WiFi fingerprint information of the candidate point of interest through an image feature extraction model includes: cross-merging the first fingerprint matrix and the second fingerprint matrix to obtain a similarity measurement matrix; and inputting the similarity measurement matrix into the image feature extraction model to obtain the similarity features.

[0124] According to one or more embodiments of this disclosure, Example 3 provides the method of Example 2, wherein the scan signal strength distribution and historical signal strength distribution of the same WiFi in the similarity metric matrix are arranged adjacently.

[0125] According to one or more embodiments of this disclosure, Example 4 provides the method of Example 3, wherein the image feature extraction model includes a convolutional layer, a pooling layer, and a flattening layer connected in sequence; wherein the convolutional layer is used to perform a convolution operation with a stride of 2 on the similarity metric matrix to extract the similarity of adjacent signal intensity distributions to obtain a first feature matrix; the pooling layer is used to extract features from the first feature matrix to obtain a second feature matrix; and the flattening layer is used to flatten the second feature matrix into a one-dimensional vector as the similarity feature.

[0126] According to one or more embodiments of this disclosure, Example 5 provides a method of any one of Examples 2-4, wherein the historical signal strength distribution of each WiFi associated with the candidate point of interest in the second fingerprint matrix is ​​arranged according to the popularity of the corresponding WiFi.

[0127] According to one or more embodiments of this disclosure, Example 6 provides the method of Example 1, wherein the user location request further includes a first type of location information of the terminal initiating the user location request, and the candidate point of interest is a second type of location information; determining at least one candidate point of interest corresponding to the user location request includes: determining reference points of interest in a WiFi fingerprint database located within a preset distance range of the terminal as the candidate point of interest based on the first type of location information, wherein the WiFi fingerprint database includes second WiFi fingerprint information of different reference points of interest.

[0128] According to one or more embodiments of this disclosure, Example 7 provides the method of Example 1, wherein determining the target interest point of a user from the at least one candidate interest point based on each of the similarity features includes: for each of the candidate interest points, determining the probability that the user is at the candidate interest point based on the similarity feature corresponding to the candidate interest point; and determining the target interest point of the user from the at least one candidate interest point based on each of the probabilities.

[0129] According to one or more embodiments of this disclosure, Example 8 provides a positioning device, comprising: a first determining module, configured to determine at least one candidate point of interest corresponding to the user positioning request in response to receiving a user positioning request, wherein the user positioning request includes first WiFi fingerprint information; a feature extraction module, configured to extract, for each candidate point of interest, similarity features between the first WiFi fingerprint information and second WiFi fingerprint information of the candidate point of interest using an image feature extraction model; and a second determining module, configured to determine the target point of interest where the user is located from the at least one candidate point of interest based on each of the similarity features.

[0130] According to one or more embodiments of the present disclosure, Example 9 provides a computer-readable medium having a computer program stored thereon that, when executed by a processing device, implements the steps of the method described in any one of Examples 1-7.

[0131] According to one or more embodiments of this disclosure, Example 10 provides an electronic device including: a storage device having a computer program stored thereon; and a processing device for executing the computer program in the storage device to implement the steps of any one of Examples 1-7.

[0132] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0133] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0134] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative forms of implementing the claims. Regarding the apparatus in the above embodiments, the specific manner in which the various modules perform their operations has been described in detail in the embodiments relating to the method, and will not be elaborated upon here.

Claims

1. A positioning method, characterized in that, include: In response to receiving a user location request, at least one candidate point of interest corresponding to the user location request is determined, wherein the user location request includes first WiFi fingerprint information; For each candidate point of interest, the similarity features between the first WiFi fingerprint information and the second WiFi fingerprint information of the candidate point of interest are extracted using an image feature extraction model; Based on each of the aforementioned similarity features, determine the user's target interest point from the at least one candidate interest point; The first WiFi fingerprint information includes a first fingerprint matrix composed of the scan signal strength distributions of multiple WiFi networks, and the second WiFi fingerprint information includes a second fingerprint matrix composed of the historical signal strength distributions of at least one WiFi network associated with the candidate point of interest. The step of extracting similarity features between the first WiFi fingerprint information and the second WiFi fingerprint information of the candidate point of interest using an image feature extraction model includes: The first fingerprint matrix and the second fingerprint matrix are cross-merged to obtain a similarity measurement matrix; The similarity metric matrix is ​​input into the image feature extraction model to obtain the similarity features.

2. The method according to claim 1, characterized in that, In the similarity metric matrix, the scanning signal strength distribution and historical signal strength distribution of the same WiFi are arranged adjacently.

3. The method according to claim 2, characterized in that, The image feature extraction model includes a convolutional layer, a pooling layer, and a flattening layer connected in sequence. The convolutional layer is used to perform a convolution operation with a stride of 2 on the similarity metric matrix to extract the similarity of the signal intensity distributions of adjacent arrays and obtain the first feature matrix. The pooling layer is used to extract features from the first feature matrix to obtain a second feature matrix. The flattening layer is used to flatten the second feature matrix into a one-dimensional vector, which serves as the similarity feature.

4. The method according to any one of claims 1-3, characterized in that, In the second fingerprint matrix, the historical signal strength distribution of each WiFi associated with the candidate point of interest is arranged according to the popularity of the corresponding WiFi.

5. The method according to claim 1, characterized in that, The user location request also includes a first type of location information of the terminal that initiated the user location request, and the candidate point of interest is a second type of location information. Determining at least one candidate point of interest corresponding to the user's location request includes: Based on the first type of location information, reference points of interest located within a preset distance range of the terminal in the WiFi fingerprint database are determined as candidate points of interest, wherein the WiFi fingerprint database includes second WiFi fingerprint information of different reference points of interest.

6. The method according to claim 1, characterized in that, Determining the user's target interest point from the at least one candidate interest point based on each of the similarity features includes: For each candidate point of interest, the probability that a user is at that candidate point of interest is determined based on the similarity features corresponding to that candidate point of interest. Based on each of the probabilities, the user's target interest point is determined from the at least one candidate interest point.

7. A positioning device, characterized in that, include: The first determining module is configured to, in response to receiving a user location request, determine at least one candidate point of interest corresponding to the user location request, wherein the user location request includes first WiFi fingerprint information; The feature extraction module is used to extract similarity features between the first WiFi fingerprint information and the second WiFi fingerprint information of the candidate interest point for each candidate interest point using an image feature extraction model. The second determining module is used to determine the user's target interest point from the at least one candidate interest point based on each of the similarity features. The first WiFi fingerprint information includes a first fingerprint matrix composed of the scan signal strength distributions of multiple WiFi networks, and the second WiFi fingerprint information includes a second fingerprint matrix composed of the historical signal strength distributions of at least one WiFi network associated with the candidate point of interest. The feature extraction module includes: The merging submodule is used to cross-merge the first fingerprint matrix and the second fingerprint matrix to obtain a similarity measurement matrix; The extraction submodule is used to input the similarity metric matrix into the image feature extraction model to obtain the similarity features.

8. A computer-readable medium having a computer program stored thereon, characterized in that, When executed by the processing device, the program implements the steps of the method according to any one of claims 1-6.

9. An electronic device, characterized in that, include: A storage device on which computer programs are stored; A processing device for executing the computer program in the storage device to implement the steps of the method according to any one of claims 1-6.

Images