Arrival event determination method and device, electronic device, and storage medium

Abstract

The present application provides a method and device for determining an arrival event, an electronic device, and a storage medium; the method includes: obtaining a signal feature set of a wireless signal detected by a delivery party during the execution of at least one delivery service, wherein the delivery items corresponding to the at least one delivery service are from the same pick-up location; identifying a target feature subset corresponding to the item pick-up stage in the signal feature set, and determining the signal feature of the wireless signal corresponding to the pick-up location based on the target feature subset, wherein the item pick-up stage is the stage from the time when the delivery party arrives at the pick-up location to the time when the delivery party leaves the pick-up location during the execution process; obtaining the signal feature of the wireless signal currently detected by the user's client, and determining that an arrival event has occurred for the user at the pick-up location when the signal feature currently detected by the client matches the signal feature of the wireless signal corresponding to the pick-up location.

Description

Technical Field

[0001] One or more embodiments of the present application relate to the field of communication technology, and in particular, to a method and device for determining an arrival event, an electronic device, and a storage medium. Background Art

[0002] WiFi technology is widely used in various large or small buildings such as homes, hotels, cafes, airports, shopping malls, etc. For this application scenario, WiFi fingerprint data can be used to automatically detect the user's arrival and departure behaviors at a certain building. Taking the POI (Point of Interest) in a business district as an example, the WiFi fingerprint data of a physical store in the business district can be used to determine whether the user has arrived at the store or left the store.

[0003] In the related technologies, the WiFi fingerprint mounting of the business district POI mainly relies on manual collection, which leads to high cost, low coverage and low accuracy. Summary of the invention

[0004] In view of this, one or more embodiments of the present application provide a method and device for determining an arrival event, an electronic device, and a storage medium.

[0005] To achieve the above objectives, one or more embodiments of the present application provide the following technical solutions:

[0006] According to a first aspect of one or more embodiments of the present application, a method for acquiring characteristics of a wireless signal is proposed, which is applied to a server; the method includes:

[0007] Acquire a signal feature set of wireless signals detected by the delivery party during the execution of at least one delivery service, wherein the delivery items corresponding to the at least one delivery service are from the same pickup location;

[0008] Identifying a target feature subset corresponding to an item pickup phase in the signal feature set, wherein the item pickup phase is a phase from after the delivery party arrives at the pickup location to before the delivery party leaves the pickup location during the execution process;

[0009] Signal characteristics of the wireless signal corresponding to the pick-up location are determined based on the target characteristic subset.

[0010] Optionally, the signal feature set includes a plurality of feature sequences, and the plurality of feature sequences are obtained by detecting feature values ​​of each wireless signal on a preset feature dimension according to a preset detection period; and identifying a target feature subset corresponding to an item collection stage in the signal feature set includes:

[0011] Determine the similarity between the feature values ​​contained in each feature sequence, and distribute the feature sequences according to the similarity to obtain the distribution of the signal feature set; wherein the density of the distributed feature sequences is positively correlated with the corresponding similarity;

[0012] A feature subset with the highest density of feature sequences contained in the signal feature set is determined according to the distribution to serve as the target feature subset.

[0013] Optional,

[0014] The determining of the similarity between the eigenvalues ​​included in each feature sequence and distributing the feature sequences according to the similarity to obtain the distribution of the signal feature set includes: forming a corresponding feature matrix according to the eigenvalues ​​included in each feature sequence, and calculating the distance between each feature matrix to establish an association relationship between feature sequences whose distances between the corresponding feature matrices are within a distance threshold;

[0015] The method of determining the most densely populated feature subset of feature sequences contained in the signal feature set according to the distribution as the target feature subset includes: composing a network diagram according to the established association relationship and determining communities of the network diagram, wherein the feature sequences contained in the communities constitute the target feature subset.

[0016] Optionally, the signal feature set includes multiple feature sequences, and the multiple feature sequences are obtained by detecting feature values ​​of each wireless signal on a preset feature dimension according to a preset detection period; and determining the signal feature of the wireless signal corresponding to the pickup location based on the target feature subset includes:

[0017] Selecting a target feature sequence from the feature sequences included in the target feature subset;

[0018] The signal characteristics of the wireless signal corresponding to the pickup location are characterized based on the characteristic value of the wireless signal included in the target characteristic sequence.

[0019] Optionally, the feature sequence records a mapping relationship between a signal identifier of each detected wireless signal and a corresponding feature value; the feature value of the wireless signal contained in the target feature sequence characterizes the signal characteristics of the wireless signal corresponding to the pickup location, including:

[0020] determining a target signal identifier of the wireless signal corresponding to the pickup location;

[0021] Determining a target feature value corresponding to the target signal identifier according to a mapping relationship recorded in the target feature sequence;

[0022] The signal characteristics of the wireless signal corresponding to the pick-up location are characterized based on the target characteristic value.

[0023] Optional,

[0024] It also includes: obtaining time information corresponding to the item collection stage reported by the delivery party;

[0025] The signal characteristics of the wireless signal corresponding to the pick-up location based on the characteristic value characterization of the wireless signal contained in the target characteristic sequence include: when the detection period corresponding to the target characteristic sequence matches the time information, the signal characteristics of the wireless signal corresponding to the pick-up location based on the characteristic value characterization of the wireless signal contained in the target characteristic sequence.

[0026] Optionally, the wireless signal includes a WiFi signal, and the characteristic dimension used by the distributor to detect the wireless signal includes a WiFi fingerprint, and the WiFi fingerprint includes a multipath structure of the WiFi signal and / or a signal strength of the WiFi signal.

[0027] According to a second aspect of one or more embodiments of the present application, a method for determining an arrival event is provided, including:

[0028] Obtain the signal characteristics of the wireless signal currently detected by the user's client;

[0029] Acquire a signal characteristic of a wireless signal corresponding to a pickup location obtained by the method described in any one of the first aspects;

[0030] In the case where the signal characteristics currently detected by the client match the signal characteristics of the wireless signal corresponding to the pick-up location, it is determined that an arrival event of the user to the pick-up location occurs.

[0031] Optionally, also include:

[0032] After determining that the user has the arrival event, if the signal characteristics currently detected by the client do not match the signal characteristics of the wireless signal corresponding to the pick-up location, it is determined that the user has the departure event for the pick-up location.

[0033] According to a third aspect of one or more embodiments of the present application, a method for uploading characteristics of a wireless signal is proposed, which is applied to a delivery party; the method includes:

[0034] During the execution of the delivery service, the wireless signal is detected to obtain corresponding signal characteristics;

[0035] A signal feature set consisting of signal features obtained by detecting wireless signals during the execution of at least one delivery service is sent to a server, wherein the delivery items corresponding to the at least one delivery service come from the same pickup location, and the signal feature set is used by the server to identify a target feature subset corresponding to a pickup stage of the item, and determine the signal features of the wireless signal corresponding to the pickup location based on the target feature subset, wherein the pickup stage of the item is the stage from the time when the delivery party arrives at the pickup location to the time when the delivery party leaves the pickup location during the execution process.

[0036] According to a fourth aspect of one or more embodiments of the present application, a device for acquiring characteristics of a wireless signal is provided, which is applied to a server; the device includes:

[0037] A feature acquisition unit, which acquires a signal feature set of wireless signals detected by the delivery party during the execution of at least one delivery service, wherein the delivery items corresponding to the at least one delivery service are from the same pickup location;

[0038] an identification unit, identifying a target feature subset corresponding to an item pickup stage in the signal feature set, wherein the item pickup stage is a stage from when the delivery party arrives at the pickup location to when the delivery party leaves the pickup location during the execution process;

[0039] A determination unit determines a signal characteristic of the wireless signal corresponding to the pickup location based on the target characteristic subset.

[0040] Optionally, the signal feature set includes a plurality of feature sequences, and the plurality of feature sequences are obtained by detecting feature values ​​of each wireless signal in a preset feature dimension according to a preset detection period; and the identification unit is specifically configured to:

[0041] Determine the similarity between the feature values ​​contained in each feature sequence, and distribute the feature sequences according to the similarity to obtain the distribution of the signal feature set; wherein the density of the distributed feature sequences is positively correlated with the corresponding similarity;

[0042] A feature subset with the highest density of feature sequences contained in the signal feature set is determined according to the distribution to serve as the target feature subset.

[0043] Optional,

[0044] The identification unit is further used to: form a corresponding feature matrix according to the feature values ​​contained in each feature sequence, and calculate the distance between each feature matrix, so as to establish an association relationship between feature sequences whose distances between the corresponding feature matrices are within a distance threshold;

[0045] A network diagram is obtained by constructing the established association relationship and a community of the network diagram is determined. The feature sequences contained in the community constitute the target feature subset.

[0046] Optionally, the signal feature set includes multiple feature sequences, and the multiple feature sequences are obtained by detecting feature values ​​of each wireless signal in a preset feature dimension according to a preset detection period; and the determining unit is specifically used to:

[0047] Selecting a target feature sequence from the feature sequences included in the target feature subset;

[0048] The signal characteristics of the wireless signal corresponding to the pickup location are characterized based on the characteristic value of the wireless signal included in the target characteristic sequence.

[0049] Optionally, the feature sequence records a mapping relationship between a signal identifier of each detected wireless signal and a corresponding feature value; and the determining unit is further configured to:

[0050] determining a target signal identifier of the wireless signal corresponding to the pickup location;

[0051] Determining a target feature value corresponding to the target signal identifier according to a mapping relationship recorded in the target feature sequence;

[0052] The signal characteristics of the wireless signal corresponding to the pick-up location are characterized based on the target characteristic value.

[0053] Optional,

[0054] It also includes: an information acquisition unit, which acquires time information corresponding to the item collection stage reported by the delivery party;

[0055] The determination unit is further used to: when the detection period corresponding to the target feature sequence matches the time information, characterize the signal characteristics of the wireless signal corresponding to the collection location based on the characteristic value of the wireless signal contained in the target feature sequence.

[0056] Optionally, the wireless signal includes a WiFi signal, and the characteristic dimension used by the distributor to detect the wireless signal includes a WiFi fingerprint, and the WiFi fingerprint includes a multipath structure of the WiFi signal and / or a signal strength of the WiFi signal.

[0057] According to a fifth aspect of one or more embodiments of the present application, a device for determining an arrival event is provided, including:

[0058] A first acquisition unit is configured to acquire a signal characteristic of a wireless signal currently detected by a client of a user;

[0059] A second acquisition unit, which acquires a signal characteristic of a wireless signal corresponding to a pickup location obtained by the method described in any one of the first aspects;

[0060] The determining unit determines that the user has an arrival event at the pick-up location when the signal characteristics currently detected by the client match the signal characteristics of the wireless signal at the pick-up location.

[0061] Optionally, the determining unit is further configured to:

[0062] After determining that the user has the arrival event, if the signal characteristics currently detected by the client do not match the signal characteristics of the wireless signal corresponding to the pick-up location, it is determined that the user has the departure event for the pick-up location.

[0063] According to a sixth aspect of one or more embodiments of the present application, a device for uploading characteristics of a wireless signal is provided, which is applied to a delivery party; the device includes:

[0064] A detection unit, which detects wireless signals during the execution of the delivery service to obtain corresponding signal characteristics;

[0065] A sending unit sends to a server a signal feature set consisting of signal features obtained by detecting wireless signals during the execution of at least one delivery service, wherein the delivery items corresponding to the at least one delivery service come from the same pickup location, and the signal feature set is used by the server to identify a target feature subset corresponding to a pickup stage of the item, and determine the signal features of the wireless signal corresponding to the pickup location based on the target feature subset, wherein the pickup stage of the item is the stage from the time when the delivery party arrives at the pickup location to the time when the delivery party leaves the pickup location during the execution process.

[0066] According to a seventh aspect of one or more embodiments of the present application, an electronic device is provided, including:

[0067] processor;

[0068] a memory for storing processor-executable instructions;

[0069] The processor implements the method described in any of the above embodiments by running the executable instructions.

[0070] According to an eighth aspect of one or more embodiments of the present application, a computer-readable storage medium is provided, on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method described in any of the above embodiments are implemented.

[0071] In the technical solution of the present application, the signal characteristics of the wireless signal are detected by the distributor during the execution of the distribution service, and the execution process includes the stage of going to the pick-up location of the distribution items, the stage of picking up the distribution items after arriving at the pick-up location, and the stage of delivering the distribution items after leaving the pick-up location. Based on the limitation of the signal range of the wireless signal (it cannot be detected if it exceeds a certain range), for the stages of going to the pick-up location and leaving the pick-up location, the wireless signal detected by the distributor is not the wireless signal corresponding to the pick-up location, while for the above-mentioned item pick-up stage, the distributor is at the pick-up location and can detect the wireless signal corresponding to the pick-up location. Then, the characteristics of the wireless signal detected by the distributor during the item pick-up stage can be used as the basis for determining the signal characteristics of the wireless signal corresponding to the pick-up location. Therefore, the signal characteristics set of the wireless signal detected by the distributor during the execution of at least one distribution service (the corresponding distribution items come from the same pick-up location) can be obtained, and the target feature subset in the item pick-up stage can be identified, and then the signal characteristics of the wireless signal corresponding to the pick-up location can be determined based on the target feature subset.

[0072] On the one hand, the above process of obtaining wireless signal characteristics does not require the delivery personnel to add additional operations during the delivery process using the delivery party. The delivery party can upload the detected signal characteristics, so it will not affect the normal delivery process of the delivery personnel. Under the premise of ensuring that the delivery business is not affected, it can avoid manual special detection of signal characteristics, thereby reducing costs and improving detection efficiency.

[0073] On the other hand, as long as there is a delivery service performed by the delivery party at the pick-up location, the feature acquisition scheme of the present application can be used to obtain the signal characteristics of the pick-up location. That is, the feature acquisition scheme of the present application can cover all pick-up locations where there is a delivery service, thereby improving the coverage rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 It is a schematic diagram of the architecture of a wireless signal feature acquisition system provided by an exemplary embodiment.

[0075] Figure 2 It is a flowchart of a method for acquiring characteristics of a wireless signal provided by an exemplary embodiment.

[0076] Figure 3 It is a flowchart of a method for determining an arrival event provided by an exemplary embodiment.

[0077] Figure 4 It is a flowchart of a method for uploading characteristics of a wireless signal provided by an exemplary embodiment.

[0078] Figure 5It is a flowchart of a method for mounting a store WiFi fingerprint provided by an exemplary embodiment.

[0079] Figure 6 It is a schematic diagram of a network graph constructed based on a feature sequence provided by an exemplary embodiment.

[0080] Figure 7 It is a flowchart of a method for determining a store arrival event provided by an exemplary embodiment.

[0081] Figure 8 It is a schematic structural diagram of an electronic device provided by an exemplary embodiment.

[0082] Fig. 9 It is a block diagram of a device for acquiring characteristics of a wireless signal provided by an exemplary embodiment.

[0083] Fig.10 It is a schematic structural diagram of another electronic device provided by an exemplary embodiment.

[0084] Fig.11 It is a block diagram of a device for determining an arrival event provided by an exemplary embodiment.

[0085] Fig.12 It is a schematic structural diagram of another electronic device provided by an exemplary embodiment.

[0086] Fig.13 It is a block diagram of a device for uploading characteristics of a wireless signal provided by an exemplary embodiment. DETAILED DESCRIPTION

[0087] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of the present application. Instead, they are merely examples of devices and methods consistent with some aspects of one or more embodiments of the present application as detailed in the appended claims.

[0088] It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this application. In some other embodiments, the steps included in the method may be more or less than those described in this application. In addition, a single step described in this application may be decomposed into multiple steps for description in other embodiments; and multiple steps described in this application may also be combined into a single step for description in other embodiments.

[0089] See also Figure 1 , Figure 1FIG. 1 is a schematic diagram of the architecture of a wireless signal feature acquisition system provided by an exemplary embodiment. Figure 1 As shown, the system may include a server 11 , at least one delivery party (such as mobile phones 12 - 14 , etc.) and a network 15 .

[0090] The server 11 may be a physical server including an independent host, or the server 11 may be a virtual server carried by a host cluster. During operation, the server 11 may run a server-side program of a certain application to implement the relevant business functions of the application as a corresponding server. For example, the server 11 may run a server-side program of a distribution service platform to implement the service end of the distribution service platform.

[0091] Mobile phones 12-14 represent a type of electronic device that can be used by users. In fact, users can obviously also use electronic devices such as the following types: tablet devices, laptops, PDAs (Personal Digital Assistants), wearable devices (such as smart glasses, smart watches, etc.), etc., and one or more embodiments of the present application do not limit this. During operation, the electronic device can run a program on the client side of an application to implement the relevant business functions of the application. For example, mobile phones 12-14 can run a delivery side program of a delivery service platform to realize the delivery party of the delivery service platform.

[0092] The network 15 for interaction between the mobile phones 12-14 and the server 11 may include various types of wired or wireless networks. For example, the network 15 may include a public switched telephone network (PSTN) and the Internet. A long connection may be established between the server 11 and the mobile phones 12-14 through the network 15, so that data is transmitted between the server 11 and the mobile phones 12-14 through the long connection.

[0093] See also Figure 2 , Figure 2 FIG. 1 is a flow chart of a method for acquiring characteristics of a wireless signal provided by an exemplary embodiment. Figure 2 As shown, the method is applied to the server and may include the following steps:

[0094] Step 202: obtaining a signal feature set of wireless signals detected by the delivery party during the execution of at least one delivery service, wherein the delivery items corresponding to the at least one delivery service are from the same pick-up location.

[0095] In this embodiment, users can place orders for any goods on the e-commerce platform. In some cases, the goods ordered by the user need to be delivered from a physical store or warehouse to the user's location. Therefore, a delivery service platform (such as an e-commerce platform or other delivery platform that cooperates with it) is required to generate corresponding delivery services for the delivery items and allocate the delivery services to the delivery party (the client device used by the delivery person). After accepting the delivery service, the delivery person goes to the pick-up location of the delivery item (such as the above-mentioned physical store or warehouse) to pick up the delivery item, and delivers the delivery item to the user's location after successful collection.

[0096] For example, in a takeaway scenario, a user places an order to a physical store on the takeaway platform through a user client (i.e., the delivery object). The takeaway platform generates the corresponding takeaway order and then assigns the takeaway order to the delivery party (in this case, the client device used by the rider), so that the rider goes to the physical store (i.e., the pickup location for the delivery items) to pick up the takeaway and delivers it to the location specified by the user. For another example, in a courier scenario, for the delivery items stored in the warehouse, the courier platform generates the corresponding courier order and then assigns the courier order to the delivery party (in this case, the client device used by the courier), so that the courier goes to the warehouse (i.e., the pickup location for the delivery items) to pick up the goods and delivers them to the location of the recipient (in this case, the client used by the recipient is the delivery object).

[0097] It can be seen that the execution process of the distribution service includes the stage of going to the pick-up location of the delivered items, the stage of picking up the delivered items after arriving at the pick-up location (i.e., the item pick-up stage), and the stage of delivering the delivered items after leaving the pick-up location. At the same time, there is a corresponding wireless signal at the pick-up location. For example, an AP (Wireless Access Point) is configured at the pick-up location, and the distributor is configured with a WiFi module, so the distributor can detect the WiFi signal emitted from the pick-up location within a certain range. Then, the distributor can detect the signal characteristics of the wireless signal in the process of executing the distribution service. Based on the limitation of the wireless signal on the signal range (it cannot be detected beyond a certain range), for the stages of going to the pick-up location and leaving the pick-up location, the wireless signal detected by the distributor is not the wireless signal corresponding to the pick-up location, while for the above-mentioned item pick-up stage, the distributor is at the pick-up location and can detect the wireless signal corresponding to the pick-up location. Therefore, the characteristics of the wireless signal detected by the distributor during the item pick-up stage can be used as a basis for determining the signal characteristics of the wireless signal corresponding to the pick-up location.

[0098] Of course, any other short-range communication technology can be used as long as it has the characteristic of "range limitation". For example, IrDA (Infrared Data Association) infrared data transmission, ZigBee, NFC (Near Field Communication), UWB (Ultra WideBand), DECT (Digital Enhanced Cordless Telecommunications) and other communication technologies can be used.

[0099] It should be noted that when constructing a signal feature set, it is not necessary to be limited to one delivery business, but can cover multiple delivery businesses, as long as the delivery items corresponding to the delivery business are guaranteed to come from the same pickup location, thereby expanding the data volume of the signal feature set and improving the accuracy of the signal features for the pickup location obtained subsequently. Similarly, it is not necessary to be limited to the same delivery party, but can cover multiple delivery parties, as long as the delivery items corresponding to the delivery business performed by the multiple delivery parties are guaranteed to come from the same pickup location, so that the signal feature set covers a variety of different types of delivery parties (there are differences in the hardware performance of the delivery parties), and improves the accuracy of the obtained signal features. For example, in the takeaway scenario, multiple takeaway orders for the same physical store (which can be received by different riders) can be selected to construct a signal feature set. Similarly, in the express delivery scenario, multiple express delivery orders for the same warehouse (which can be received by different couriers) can be selected to construct a signal feature set.

[0100] Step 204, identifying a target feature subset in the signal feature set corresponding to the item pickup stage, wherein the item pickup stage is the stage from when the delivery party arrives at the pickup location to when the delivery party leaves the pickup location during the execution process.

[0101] In this embodiment, the signal feature set covers the stage of the delivery person going to the pickup location (hereinafter referred to as the going stage), the stage of picking up the delivered items after arriving at the pickup location (hereinafter referred to as the item picking stage), and the stage of delivering the delivered items after leaving the pickup location (hereinafter referred to as the item delivery stage) in time sequence. In other words, the signal feature set includes the signal features of all wireless signals detected by the delivery party in the going stage, the item picking stage, and the item delivery stage.

[0102] Among them, the delivery party can detect the characteristic value of the wireless signal on the preset characteristic dimension according to the preset detection cycle. Since multiple different wireless signals may be detected at the same time (that is, there are multiple different wireless signals at the location), the detected signal feature is a feature sequence, which contains the characteristic values ​​of all wireless signals detected at the same time on the feature dimension. Accordingly, since the signal feature set covers the entire execution process of the delivery business, the signal feature set can be divided into feature subsets corresponding to the going stage, the item collection stage and the item delivery stage according to the stage, and each feature subset contains the feature sequence detected by the delivery party in the corresponding stage.

[0103] Furthermore, for the going stage and the item delivery stage, since the delivery party is constantly moving and has a large range of movement in both stages, the characteristic values ​​of the wireless signal detected by the delivery party also change frequently. For the item pickup stage, since the delivery party is at the pickup location, there is no need to move constantly and the range of movement is small, the characteristic values ​​of the wireless signal detected by the delivery party are also relatively stable. Therefore, compared with the going stage and the item delivery stage, the similarity between the feature sequences detected in each detection cycle in the item pickup stage is greater. Based on the above characteristics, the target feature subset corresponding to the item pickup stage in the signal feature set can be identified based on the similarity between the feature sequences contained in each feature subset.

[0104] As an exemplary embodiment, the similarity between the feature values ​​contained in each feature sequence can be determined, and the feature sequences are distributed according to the similarity to obtain the distribution of the signal feature set. The rule for distributing the feature sequences is that the density of the distributed feature sequences is positively correlated with the corresponding similarity; in other words, the higher the similarity between any two feature sequences, the denser they are distributed. Then, according to the distribution of the signal feature set (i.e., the distribution of the feature sequences), the feature subset with the highest density of the feature sequences contained in the signal feature set is determined as the target feature subset.

[0105] For example, the similarity between feature sequences can be measured by distance. Specifically, when determining the distribution of the signal feature set, a corresponding feature matrix can be formed according to the eigenvalues ​​contained in each feature sequence, and the distance between each feature matrix can be calculated to establish an association relationship between the feature sequences whose distances between the corresponding feature matrices are within the distance threshold. Among them, the distance between each feature matrix can be Euclidean distance, Jacobi distance, cosine distance, etc.; of course, this application is not limited to this. Accordingly, when determining the target feature subset in the signal feature set, a network diagram can be obtained by first constructing a graph based on the established association relationship (using the feature sequence as a node), and then determining the community of the network diagram. Then, the feature sequence contained in the community constitutes the target feature subset.

[0106] Step 206: Determine the signal characteristics of the wireless signal corresponding to the pick-up location based on the target characteristic subset.

[0107] In this embodiment, after obtaining the target feature subset, the target feature sequence can be selected from the feature sequence included in the target feature subset, and then the signal characteristics of the wireless signal corresponding to the pick-up location can be characterized based on the characteristic values ​​of the wireless signal included in the target feature sequence. Among them, the target feature sequence can be selected in combination with the most central node. Specifically, the most central node of the community of the above-mentioned network diagram can be determined, and then N nodes can be expanded outward according to a preset distance with the most central node as the center, and the feature sequence corresponding to the N nodes is the target feature sequence. Furthermore, the average characteristic value can be calculated for the characteristic values ​​recorded in the feature sequence corresponding to the N nodes, and then the average characteristic value is used to characterize the signal characteristics of the wireless signal corresponding to the pick-up location. Alternatively, the feature sequence with the highest frequency of occurrence in the feature sequence corresponding to the N nodes can be selected, and then the characteristic value contained in the feature sequence is used to characterize the signal characteristics of the wireless signal corresponding to the pick-up location.

[0108] It should be noted that the target feature sequence can also be selected by other methods, and the present application does not limit this. For example, a preset number of feature sequences can be arbitrarily selected from the target feature subset as the target feature sequence. Alternatively, the feature values ​​of the feature sequence records included in the target feature subset can be calculated by averaging, weighted averaging, median, etc. to obtain the target feature sequence.

[0109] In this embodiment, in view of the situation where the delivery party detects multiple different wireless signals, when creating a feature sequence, the mapping relationship between the signal identifier of each wireless signal detected by the delivery party and the corresponding feature value is recorded in the feature sequence. Based on the above data format of the feature sequence, when characterizing the signal characteristics of the wireless signal corresponding to the pickup location, the target signal identifier of the wireless signal corresponding to the pickup location can be determined first, and then the target feature value corresponding to the target signal identifier can be determined according to the mapping relationship recorded in the target feature sequence, so as to characterize the signal characteristics of the wireless signal corresponding to the pickup location based on the target feature value. Through the above characterization method, interference from wireless signals corresponding to other locations near the pickup location can be avoided, thereby improving the accuracy of the obtained signal characteristics.

[0110] In this embodiment, since the time information corresponding to the target feature sequence should theoretically match the time information of the item collection stage, in order to further improve the accuracy of characterizing the signal characteristics, the time information corresponding to the item collection stage reported by the delivery party can be used as a verification standard to verify the target feature sequence from the time dimension. Specifically, the time information corresponding to the item collection stage reported by the delivery party can be obtained, so that when the detection period corresponding to the target feature sequence matches the time information, the signal characteristics of the wireless signal corresponding to the collection location are characterized based on the characteristic values ​​of the wireless signal contained in the target feature sequence.

[0111] For example, the time information corresponding to the item collection stage reported by the delivery party may include the time of arrival at the collection location and the time of departure from the collection location uploaded by the delivery party. Taking the takeaway scenario as an example, the rider can manually click the arrival trigger control and the departure trigger control on the rider client. The arrival trigger control is used to trigger the rider client to report the arrival event (with the arrival time recorded), and the departure trigger control is used to trigger the rider client to report the departure event (with the departure time recorded). Since the time when the rider manually clicks the arrival trigger control and the departure trigger control may deviate from the actual time of the arrival event and the departure event (such as early or delayed), a threshold value can be set to reduce the impact of the above deviation. For example, following the above example of obtaining N nodes, the above deviation relationship is: the time when the rider clicks the arrival store < the actual time period in the store < the time when the rider clicks to leave the store. For this relationship, if the detection times (which can be obtained through the detection cycle) corresponding to the nodes among the N nodes that exceed the threshold (such as 90%, 80%, etc.) are all within the above-mentioned time period of "the moment the rider clicks to arrive at the store ~ ​​the moment he clicks to leave the store", then it is determined that the target feature sequence verification has passed.

[0112] In this embodiment, the wireless signal targeted by the present application includes a WiFi signal. In this case, the characteristic dimension used by the distributor to detect the wireless signal includes a WiFi fingerprint, and the WiFi fingerprint includes a multipath structure of the WiFi signal and / or a signal strength (RSS) of the WiFi signal.

[0113] It can be seen from the above embodiments that, on the one hand, the above process of acquiring wireless signal characteristics does not require the delivery personnel to add additional operations in the process of delivery by the delivery party. The delivery party can upload the detected signal characteristics, so it will not affect the normal delivery process of the delivery personnel. It can avoid manual special detection of signal characteristics while ensuring that the delivery service is not affected, thereby reducing costs and improving detection efficiency. On the other hand, as long as there is a delivery service performed by the delivery party at the pick-up location, the feature acquisition scheme of the present application can be used to acquire the signal characteristics of the pick-up location, that is, the feature acquisition scheme of the present application can cover all pick-up locations with delivery services, thereby improving coverage; and it is convenient to update the signal characteristics of the pick-up location.

[0114] For the application scenarios involving distribution in the above embodiments, there is a need to obtain the progress of the distribution business execution, so that the execution of the distribution business can be monitored, the distribution business can be ensured to proceed smoothly, and it is also convenient for users to understand the logistics of the ordered items. Specifically, in the process of the distribution party executing the distribution business, there is a need to understand whether the delivery person has arrived at the pickup location and whether he has left the pickup location subsequently. For example, for the above-mentioned takeaway scenario, it is necessary to understand whether the rider has arrived at the store and whether he has left the store to start delivery. For the above-mentioned express delivery scenario, it is necessary to understand whether the courier has arrived at the warehouse and whether he has left the warehouse to start delivery. In addition, based on the signal characteristics of the wireless signal corresponding to the pickup location obtained in the above embodiments, it is possible to judge whether the user has arrived at the pickup location by the signal characteristics. For example, in addition to providing takeaway services, physical stores also provide in-store consumption services. Users can pre-book the in-store consumption service, so the signal characteristics of the wireless signal corresponding to the physical store can be used to judge whether the user has arrived at the store.

[0115] In summary, the signal features obtained in the above embodiments can be used to perform indoor positioning of users who need to go to the pick-up location, thereby determining whether the user has arrived at the pick-up location and whether he has subsequently left the pick-up location. Figure 3 Provide explanation.

[0116] See also Figure 3 , Figure 3 FIG. 1 is a flow chart of a method for determining an arrival event provided by an exemplary embodiment. Figure 3 As shown, the method is applied to the server and may include the following steps:

[0117] Step 302: Acquire the signal characteristics of the wireless signal currently detected by the user's client.

[0118] In this embodiment, the above-mentioned user may be a food delivery rider, a courier, a customer who goes to a physical store for in-store consumption, etc. Based on the signal characteristics of the wireless signal corresponding to the pickup location obtained in the above embodiment, the signal characteristics of the wireless signal currently detected by the above-mentioned user may be obtained for comparison, thereby determining whether the above-mentioned user has arrived at the pickup location.

[0119] Step 304, obtaining the signal characteristics of the wireless signal corresponding to the pick-up location.

[0120] In this embodiment, after obtaining the signal characteristics of the wireless signal corresponding to the pick-up location through the above embodiment, the fingerprint library can be maintained by the signal characteristics as a judgment standard; that is, the fingerprint library records the signal characteristics of the wireless signal corresponding to each pick-up location. Then, after obtaining the signal characteristics of the wireless signal currently detected by the user, a match can be performed in the fingerprint library. If the match hits a certain pick-up location, it is determined that the user has arrived at the pick-up location. Among them, the matching process is similar to the above embodiment. For example, the similarity between the signal characteristics of the wireless signal currently detected by the user and the signal characteristics recorded in the fingerprint library can be calculated, and then compared with the preset threshold. If the similarity exceeds the preset threshold, it is determined that the two match.

[0121] Step 306, when the signal characteristics currently detected by the client match the signal characteristics of the wireless signal corresponding to the pick-up location, it is determined that the user has arrived at the pick-up location.

[0122] In this embodiment, after determining that the user has the arrival event, it is further possible to determine whether the user has left the pickup location based on the signal characteristics of the wireless signal corresponding to the pickup location. Specifically, if the signal characteristics currently detected by the user's client do not match the signal characteristics of the wireless signal corresponding to the pickup location, it is determined that the user has left the pickup location.

[0123] Corresponding to the above-mentioned embodiments on the service side, the present application also provides embodiments on the delivery side. The description involved in the embodiments on the service side can also be applied to the embodiments on the delivery side, which will not be repeated below.

[0124] See also Figure 4 , Figure 4 FIG. 1 is a flow chart of a method for uploading characteristics of a wireless signal provided by an exemplary embodiment. Figure 4 As shown, the method is applied to the delivery party and may include the following steps:

[0125] Step 402: Detect wireless signals during the delivery service to obtain corresponding signal characteristics.

[0126] Step 404, sending to the server a signal feature set consisting of signal features obtained by detecting wireless signals during the execution of at least one delivery service, wherein the delivery items corresponding to the at least one delivery service come from the same pick-up location, and the signal feature set is used by the server to identify a target feature subset corresponding to the item pick-up stage, and determine the signal features of the wireless signal corresponding to the pick-up location based on the target feature subset, wherein the item pick-up stage is the stage from the time when the delivery party arrives at the pick-up location to the time when the delivery party leaves the pick-up location during the execution process.

[0127] For ease of understanding, the technical solution of the present application is described in detail below in conjunction with application scenarios.

[0128] See also Figure 5 , Figure 5 This is a flow chart of a method for mounting a store WiFi fingerprint provided by an exemplary embodiment. Figure 5 As shown, the method is applied to the server and may include the following steps:

[0129] Step 502, obtaining multiple feature sequences collected by the rider in the process of delivering the takeaway order.

[0130] In this embodiment, the takeaway scenario is used as an example. For multiple takeaway orders of a physical store to be detected, the characteristic sequence of the WiFi signal collected by the rider client during the delivery process of the rider who accepts each takeaway order can be obtained respectively. For example, the rider client can collect the signal strength of the detected WiFi signal every 10 seconds to generate a characteristic sequence. Among them, the data format of the characteristic sequence is: WiFi_id:rssi. WiFi_id is the signal identifier of the WiFi signal, for example, the mac address of the hardware device that transmits the WiFi signal can be used as the signal identifier; rssi is the signal strength.

[0131] Step 504: convert the feature sequence into a corresponding feature matrix.

[0132] Step 506, calculating the distance between each feature matrix.

[0133] Step 508: Establish association relationships between feature sequences based on the calculated distances, and construct a network graph based on the association relationships.

[0134] Step 510, determine the communities of the network graph.

[0135] Step 512, selecting a target feature sequence.

[0136] For example, feature sequence A is: WiFi_1:-80, WiFi_2:-90, WiFi_3:-80, WiFi_4:-60; feature sequence B is: WiFi_1:-70, WiFi_2:-60, WiFi_3:-30, WiFi_4:-40. Then, the feature matrix a of feature sequence A can be constructed: [-80,-90,-80,-60], and the feature matrix b of feature sequence B can be constructed: [-70,-60,-30,-40], and then the distance between feature matrix a and feature matrix b can be calculated: [-80,-90,-80,-60]-[-70,-60,-30,-40].

[0137] A distance threshold can be set to determine whether there is an association relationship between two feature sequences. For any two feature sequences, if the distance between the corresponding feature matrices is within the distance threshold, an association relationship is established between the two feature sequences. When composing according to the association relationship, the nodes of the network diagram are used to represent the feature sequence, and the edge of the network diagram is used to represent the association relationship (if there is an association relationship between the two feature sequences, the corresponding nodes are connected by the edge). Of course, the specific value of the distance threshold can be flexibly set according to the actual situation, and this application does not limit this.

[0138] Assuming that a total of 10 feature sequences are obtained, the above composition method is used to obtain Figure 6 The network diagram shown. Figure 6 As shown, each node represents a feature sequence, and each node is connected to its adjacent nodes. The number of edges connecting the nodes in the graph is less than or equal to k (k=4).

[0139] Furthermore, the network graph can be decomposed and iterated to obtain the communities of the network graph. There are some tightly connected areas in various networks such as information networks, social networks, and biological networks. These areas (node ​​sets) often correspond to certain functions and are called communities. Detecting communities in a network is equivalent to grouping node sets. Modularity is a commonly used standard for measuring the quality of node grouping. The higher the modularity, the more the detected community conforms to the characteristics of "tight inside and loose outside", and the better the grouping quality. Based on the concept of modularity, the modularity maximization method can be used to detect communities. The goal of this method is to find the grouping with the largest modularity from all possible groupings.

[0140] The communities of the network graph can also be determined by using the k-core algorithm and clustering algorithms in machine learning algorithms.

[0141] The k-Core algorithm is a subgraph mining algorithm used to find a set of nodes in a graph that meet the specified coreness, that is, each node is required to be associated with at least k other nodes in the subgraph. Taking graph G with coreness k as an example, the k-Core algorithm includes the following steps:

[0142] Step 1: Remove all vertices with degree less than k from graph G to obtain subgraph G'.

[0143] Step 2: Remove all vertices with degree less than k in graph G' to obtain a new subgraph G"; this subgraph G" is the subgraph resulting from the final k-Core partitioning.

[0144] As for the clustering algorithm, K-means algorithm, DBSCAN algorithm, Gaussian mixture clustering, etc. can be used; of course, this application does not limit this.

[0145] like Figure 6 As shown, the community P can be obtained by the above method, and the community P includes nodes 61-64. Further, the most central node of the community P can be determined (the node with the highest centrality, the measurement indicator of centrality is degree, that is, the number of edges), and then the most central node is taken as the center, and N nodes are obtained by expanding outward according to a preset distance. The feature sequence corresponding to the N nodes is the target feature sequence.

[0146] Step 514: if it matches the reference time period, proceed to step 516; otherwise, return to step 502.

[0147] In this embodiment, the rider can manually click the store arrival trigger control and the store departure trigger control on the rider client. The store arrival trigger control is used to trigger the rider client to report the store arrival event (with the store arrival time recorded), and the store departure trigger control is used to trigger the rider client to report the store departure event (with the store departure time recorded). Since the time when the rider manually clicks the store arrival trigger control and the store departure trigger control may deviate from the actual time of the store arrival event and the store departure event (such as early or delayed), a threshold value can be set to reduce the impact of the above deviation.

[0148] For example, following the example of obtaining N nodes above, the reference time period is the time when the rider clicks to arrive at the store ~ ​​the time when the rider clicks to leave the store. In this case, the above deviation relationship is: the time when the rider clicks to arrive at the store < the actual time period in the store < the time when the rider clicks to leave the store. With respect to this relationship, if the detection times (which can be obtained through the detection cycle) corresponding to the nodes among the N nodes that exceed the threshold (such as 90%, 80%, etc.) are all within the above reference time period, it is determined that the target feature sequence verification has passed.

[0149] Step 516, characterize the store WiFi fingerprint.

[0150] Based on the above example, the average feature value can be calculated for the feature values ​​recorded in the feature sequences corresponding to the N nodes, and then the average feature value is used to represent the store WiFi fingerprint. Alternatively, the feature sequence with the highest frequency in the feature sequences corresponding to the N nodes can be selected, and then the feature value contained in the feature sequence can be used to represent the store WiFi fingerprint.

[0151] Based on the above data format of the feature sequence, when characterizing the store WiFi fingerprint, the target signal identifier of the physical store's WiFi signal can be determined first, and then the target feature value (signal strength) corresponding to the target signal identifier in the target feature sequence can be determined, so as to characterize the store WiFi fingerprint based on the target feature value. For example, the target feature sequence is: WiFi_1: -80, WiFi_2: -90, WiFi_3: -80, WiFi_4: -60; the WiFi_id of the physical store's WiFi signal is WiFi_3, then the signal strength -80 recorded in WiFi_3: -80 is used to characterize the store WiFi fingerprint.

[0152] See also Figure 7 , Figure 7 FIG. 1 is a flow chart of a method for determining a store arrival event provided by an exemplary embodiment. Figure 7 As shown, the method is applied to the server and may include the following steps:

[0153] Step 702, obtaining the signal characteristics currently detected by the rider client.

[0154] Step 704, obtaining the store WiFi fingerprint.

[0155] Step 706, if the signal feature matches the store WiFi fingerprint, proceed to step 708; otherwise, proceed to step 710.

[0156] In this embodiment, based on the store WiFi fingerprint obtained in the above embodiment, the signal characteristics of the wireless signal currently detected by the rider client can be obtained (such as signal strength representation) for comparison, so as to determine whether the rider has arrived at the physical store.

[0157] Step 708, determine whether the rider has arrived at the store.

[0158] Step 710, determine that the rider has not arrived at the store.

[0159] In this embodiment, after obtaining the store WiFi fingerprint through the above embodiment, the store WiFi fingerprint of each physical store can be used as a judgment standard to maintain a fingerprint library, that is, the fingerprint library records the signal characteristics of the WiFi signal of each physical store. Then, after obtaining the signal strength of the WiFi signal currently detected by the rider client, a match can be made in the fingerprint library. If the match hits a certain physical store, it is determined that the rider has arrived at the physical store. Among them, the matching process is similar to the above embodiment. For example, the similarity between the signal strength of the WiFi signal currently detected by the rider client and the signal strength recorded in the fingerprint library can be calculated, and then compared with the preset threshold. If the similarity exceeds the preset threshold, it is determined that the two match.

[0160] Step 712, obtaining the signal characteristics currently detected by the rider client.

[0161] Step 714, if the signal characteristics match the store WiFi fingerprint, proceed to step 716; otherwise, proceed to step 718.

[0162] Step 716, determine that the rider has not left the store.

[0163] Step 718, determine whether the rider has left the store.

[0164] In this embodiment, after the rider arrives at the store (it takes a certain amount of time to pick up the takeaway, or there may be a situation where the takeaway is waiting to be made), it can be further determined whether the rider has left the store based on the store WiFi fingerprint. Specifically, if the signal strength of the WiFi signal currently detected by the rider's client does not match the store WiFi fingerprint of the corresponding physical store, it is determined that the rider has left the store.

[0165] Figure 8 This is a schematic diagram of the structure of an electronic device provided by an exemplary embodiment. Figure 8 At the hardware level, the device includes a processor 802, an internal bus 804, a network interface 806, a memory 808, and a non-volatile memory 810, and may also include hardware required for other services. The processor 802 reads the corresponding computer program from the non-volatile memory 810 into the memory 808 and then runs it, forming a feature acquisition device for wireless signals at the logical level. Of course, in addition to software implementations, one or more embodiments of the present application do not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0166] Please refer to Fig. 9 In a software implementation, the wireless signal feature acquisition device is applied to the server and may include:

[0167] A feature acquisition unit 91 is configured to acquire a signal feature set of wireless signals detected by the delivery party during the execution of at least one delivery service, wherein the delivery items corresponding to the at least one delivery service are from the same pickup location;

[0168] An identification unit 92 identifies a target feature subset corresponding to an item pickup phase in the signal feature set, wherein the item pickup phase is a phase from after the delivery party arrives at the pickup location to before the delivery party leaves the pickup location during the execution process;

[0169] The determination unit 93 determines the signal characteristics of the wireless signal corresponding to the pickup location based on the target characteristic subset.

[0170] Optionally, the signal feature set includes a plurality of feature sequences, and the plurality of feature sequences are obtained by detecting feature values ​​of each wireless signal in a preset feature dimension according to a preset detection period; the identification unit 92 is specifically configured to:

[0171] Determine the similarity between the feature values ​​contained in each feature sequence, and distribute the feature sequences according to the similarity to obtain the distribution of the signal feature set; wherein the density of the distributed feature sequences is positively correlated with the corresponding similarity;

[0172] A feature subset with the highest density of feature sequences contained in the signal feature set is determined according to the distribution to serve as the target feature subset.

[0173] Optional,

[0174] The identification unit 92 is further used to: form a corresponding feature matrix according to the feature values ​​contained in each feature sequence, and calculate the distance between each feature matrix, so as to establish an association relationship between the feature sequences whose distances between the corresponding feature matrices are within a distance threshold;

[0175] A network diagram is obtained by constructing the established association relationship and a community of the network diagram is determined. The feature sequences contained in the community constitute the target feature subset.

[0176] Optionally, the signal feature set includes multiple feature sequences, and the multiple feature sequences are obtained by detecting feature values ​​of each wireless signal in a preset feature dimension according to a preset detection period; the determining unit 93 is specifically used to:

[0177] Selecting a target feature sequence from the feature sequences included in the target feature subset;

[0178] The signal characteristics of the wireless signal corresponding to the pickup location are characterized based on the characteristic value of the wireless signal included in the target characteristic sequence.

[0179] Optionally, the feature sequence records a mapping relationship between a signal identifier of each detected wireless signal and a corresponding feature value; the determining unit 93 is further configured to:

[0180] determining a target signal identifier of the wireless signal corresponding to the pickup location;

[0181] Determining a target feature value corresponding to the target signal identifier according to a mapping relationship recorded in the target feature sequence;

[0182] The signal characteristics of the wireless signal corresponding to the pick-up location are characterized based on the target characteristic value.

[0183] Optional,

[0184] It also includes: an information acquisition unit 94, which acquires time information corresponding to the item collection stage reported by the delivery party;

[0185] The determination unit 93 is further used to: when the detection period corresponding to the target feature sequence matches the time information, characterize the signal characteristics of the wireless signal corresponding to the collection location based on the characteristic value of the wireless signal contained in the target feature sequence.

[0186] Optionally, the wireless signal includes a WiFi signal, and the characteristic dimension used by the distributor to detect the wireless signal includes a WiFi fingerprint, and the WiFi fingerprint includes a multipath structure of the WiFi signal and / or a signal strength of the WiFi signal.

[0187] Fig.10 This is a schematic diagram of the structure of an electronic device provided by an exemplary embodiment. Fig.10 At the hardware level, the device includes a processor 1002, an internal bus 1004, a network interface 1006, a memory 1008, and a non-volatile memory 1010, and may also include hardware required for other services. The processor 1002 reads the corresponding computer program from the non-volatile memory 1010 into the memory 1008 and then runs it, forming a device for determining the arrival event at the logical level. Of course, in addition to the software implementation, one or more embodiments of the present application do not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0188] Please refer to Fig.11 In a software implementation, the arrival event determination device may include:

[0189] A first acquisition unit 1101 is configured to acquire a signal characteristic of a wireless signal currently detected by a client of a user;

[0190] A second acquisition unit 1102 acquires a signal characteristic of a wireless signal corresponding to a pickup location obtained by the method described in any one of the first aspects;

[0191] The determination unit 1103 determines that the user has an arrival event at the pick-up location when the signal characteristics currently detected by the client match the signal characteristics of the wireless signal at the pick-up location.

[0192] Optionally, the determining unit 1103 is further configured to:

[0193] After determining that the user has the arrival event, if the signal characteristics currently detected by the client do not match the signal characteristics of the wireless signal corresponding to the pick-up location, it is determined that the user has the departure event for the pick-up location.

[0194] Fig.12 This is a schematic diagram of the structure of an electronic device provided by an exemplary embodiment. Fig.12 At the hardware level, the device includes a processor 1202, an internal bus 1204, a network interface 1206, a memory 1208, and a non-volatile memory 1210, and may also include hardware required for other services. The processor 1202 reads the corresponding computer program from the non-volatile memory 1210 into the memory 1208 and then runs it, forming a feature upload device for wireless signals at the logical level. Of course, in addition to software implementations, one or more embodiments of the present application do not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0195] Please refer to Fig.13 In the software implementation, the characteristic uploading device of the wireless signal is applied to the delivery party and may include:

[0196] The detection unit 1301 detects the wireless signal during the execution of the delivery service to obtain the corresponding signal characteristics;

[0197] The sending unit 1302 sends to the server a signal feature set consisting of signal features obtained by detecting wireless signals during the execution of at least one delivery service, wherein the delivery items corresponding to the at least one delivery service come from the same pickup location, and the signal feature set is used by the server to identify a target feature subset corresponding to the item pickup stage, and determine the signal features of the wireless signal corresponding to the pickup location based on the target feature subset, wherein the item pickup stage is the stage from the time when the delivery party arrives at the pickup location to the time when the delivery party leaves the pickup location during the execution process.

[0198] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer, which may be in the form of a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email transceiver, a game console, a tablet computer, a wearable device or a combination of any of these devices.

[0199] In a typical configuration, a computer includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0200] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0201] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0202] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0203] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0204] The terms used in one or more embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of the present application. The singular forms of "a", "said" and "the" used in one or more embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0205] It should be understood that, although the terms first, second, third, etc. may be used to describe various information in one or more embodiments of the present application, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determination".

[0206] The above description is merely a preferred embodiment of one or more embodiments of the present application and is not intended to limit one or more embodiments of the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of the present application shall be included in the scope of protection of one or more embodiments of the present application.

Claims

1. A method for determining an arrival event, characterized in that: include: Acquire a signal feature set of wireless signals detected by the delivery party during the execution of at least one delivery service, wherein the delivery items corresponding to the at least one delivery service are from the same pickup location, and the signal feature set includes a plurality of feature sequences, and the plurality of feature sequences are obtained by detecting feature values ​​of each wireless signal according to a preset detection period; According to the similarity between the feature sequences included in the signal feature set, a target feature subset corresponding to the item pickup stage in the signal feature set is identified, and based on the target feature subset, a signal feature of the wireless signal corresponding to the pickup location is determined, wherein the item pickup stage is the stage from the time when the delivery party arrives at the pickup location to the time when the delivery party leaves the pickup location during the execution process; Acquire a signal feature of a wireless signal currently detected by a client of the user, and determine that an arrival event of the user at the pickup location occurs when the signal feature currently detected by the client matches a signal feature of a wireless signal corresponding to the pickup location; The target feature subset includes a target feature sequence, and the detection period corresponding to the target feature sequence matches the time information corresponding to the item collection stage reported by the delivery party. The time information includes the time of arrival at the collection location and the time of departure from the collection location uploaded by the delivery party. The signal characteristics of the wireless signal corresponding to the collection location are characterized based on the characteristic values ​​of the wireless signal contained in the target feature sequence.

2. The method according to claim 1, characterized in that The step of identifying a target feature subset corresponding to an item collection stage in the signal feature set according to the similarity between feature sequences included in the signal feature set includes: Determine the similarity between the feature values ​​contained in each feature sequence, and distribute the feature sequences according to the similarity to obtain the distribution of the signal feature set; wherein the density of the distributed feature sequences is positively correlated with the corresponding similarity; A feature subset with the highest density of feature sequences contained in the signal feature set is determined according to the distribution to serve as the target feature subset.

3. The method according to claim 2, characterized in that The determining of the similarity between the eigenvalues ​​included in each feature sequence and distributing the feature sequences according to the similarity to obtain the distribution of the signal feature set includes: forming a corresponding feature matrix according to the eigenvalues ​​included in each feature sequence, and calculating the distance between each feature matrix to establish an association relationship between feature sequences whose distances between the corresponding feature matrices are within a distance threshold; The method of determining the most densely populated feature subset of feature sequences contained in the signal feature set according to the distribution as the target feature subset includes: composing a network diagram according to the established association relationship and determining communities of the network diagram, wherein the feature sequences contained in the communities constitute the target feature subset.

4. The method according to claim 1, characterized in that: The feature sequence records the mapping relationship between the signal identification of each detected wireless signal and the corresponding feature value; the signal feature of the wireless signal corresponding to the collection location is characterized based on the feature value of the wireless signal contained in the target feature sequence, including: determining a target signal identifier of the wireless signal corresponding to the pickup location; Determining a target feature value corresponding to the target signal identifier according to a mapping relationship recorded in the target feature sequence; The signal characteristics of the wireless signal corresponding to the pick-up location are characterized based on the target characteristic value.

5. The method according to claim 1, characterized in that The wireless signal includes a WiFi signal, and the characteristic dimension used by the distributor to detect the wireless signal includes a WiFi fingerprint, and the WiFi fingerprint includes a multipath structure of the WiFi signal and / or a signal strength of the WiFi signal.

6. The method according to claim 1, characterized in that Also includes: After determining that the user has the arrival event, if the signal characteristics currently detected by the client do not match the signal characteristics of the wireless signal corresponding to the pick-up location, it is determined that the user has the departure event for the pick-up location.

7. A method for determining an arrival event, characterized in that: include: The user's client detects the signal characteristics of the wireless signal and sends the detected signal characteristics to the server, so that the server determines that the user has an arrival event at the pickup location when the signal characteristics detected by the client match the signal characteristics of the wireless signal corresponding to the pickup location; Among them, the signal characteristics of the wireless signal corresponding to the pick-up location are obtained based on the target feature subset corresponding to the item pick-up stage in the signal feature set, the signal feature set includes the signal characteristics of the wireless signal detected by the delivery party during the execution of at least one delivery service, and the delivery items corresponding to the at least one delivery service come from the same pick-up location, the signal feature set includes multiple feature sequences, and the multiple feature sequences are obtained by detecting the feature values ​​of each wireless signal according to a preset detection period, and the target feature subset is identified according to the similarity between the feature sequences included in the signal feature set, and the item pick-up stage is the stage from the delivery party arriving at the pick-up location to the delivery party leaving the pick-up location during the execution process; the target feature subset includes a target feature sequence, and the detection period corresponding to the target feature sequence matches the time information corresponding to the item pick-up stage reported by the delivery party, and the time information includes the time of arrival at the pick-up location and the time of leaving the pick-up location uploaded by the delivery party, and the signal characteristics of the wireless signal corresponding to the pick-up location are characterized based on the feature value of the wireless signal included in the target feature sequence.

8. A device for determining an arrival event, characterized in that: include: A first acquisition unit is configured to acquire a signal feature set of a wireless signal detected by a delivery party during the execution of at least one delivery service, wherein the delivery items corresponding to the at least one delivery service are from the same pick-up location, and the signal feature set includes a plurality of feature sequences, and the plurality of feature sequences are obtained by detecting feature values ​​of each wireless signal according to a preset detection period; a target feature subset corresponding to an item pick-up stage in the signal feature set is identified according to the similarity between the feature sequences included in the signal feature set, and a signal feature of the wireless signal corresponding to the pick-up location is determined based on the target feature subset, wherein the item pick-up stage is a stage from the time when the delivery party arrives at the pick-up location to the time when the delivery party leaves the pick-up location during the execution; the target feature subset includes a target feature sequence, and the detection period corresponding to the target feature sequence matches the time information corresponding to the item pick-up stage reported by the delivery party, wherein the time information includes the time of arrival at the pick-up location and the time of leaving the pick-up location uploaded by the delivery party, and the signal feature of the wireless signal corresponding to the pick-up location is characterized based on the feature value of the wireless signal included in the target feature sequence; A second acquisition unit is configured to acquire a signal characteristic of a wireless signal currently detected by a client of the user; The determination unit determines that the user has an arrival event at the pick-up location when the signal characteristics currently detected by the client match the signal characteristics of the wireless signal corresponding to the pick-up location.

9. A device for determining an arrival event, characterized in that: include: A detection unit, which enables the user's client to detect the signal characteristics of the wireless signal; A sending unit, causing the client to send the detected signal characteristics to the server, so that the server determines that the user has an arrival event at the pickup location when the signal characteristics detected by the client match the signal characteristics of the wireless signal corresponding to the pickup location; wherein the signal characteristics of the wireless signal corresponding to the pickup location are obtained based on a target feature subset corresponding to the item pickup stage in a signal characteristic set, the signal characteristic set includes signal characteristics of the wireless signal detected by the delivery party during the execution of at least one delivery service, the delivery items corresponding to the at least one delivery service are from the same pickup location, and the signal characteristic set includes multiple feature sequences, and the multiple feature sequences are detected according to preset detection The target feature subset is identified according to the similarity between the feature sequences included in the signal feature set, and the item collection stage is the stage from the time when the delivery party arrives at the collection location to the time when the delivery party leaves the collection location during the execution process; the target feature subset includes a target feature sequence, and the detection period corresponding to the target feature sequence matches the time information corresponding to the item collection stage reported by the delivery party, and the time information includes the time of arrival at the collection location and the time of leaving the collection location uploaded by the delivery party, and the signal characteristics of the wireless signal corresponding to the collection location are characterized based on the feature values ​​of the wireless signal included in the target feature sequence.

10. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor implements the method according to any one of claims 1 to 7 by running the executable instructions.

11. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images