Delivery data processing method, device, equipment and storage medium

Abstract

The present specification provides a delivery data processing method, apparatus, device and storage medium, wherein a historical sequence set is obtained, wherein each historical sequence includes: a plurality of data points collected when the delivery capacity executes the delivery waybill of a merchant located within a set geographical range, each data point carrying wireless signal information and one or more tags indicating the delivery capacity or the delivery waybill related information; a plurality of clusters are obtained according to the similarity of the wireless signal information between each data point of each historical sequence; a cluster tag of each cluster is obtained, wherein the cluster tag of each cluster is obtained according to the tags carried by each data point belonging to the cluster; after determining a cluster matching each merchant within the set geographical range according to the cluster tag of each cluster, the wireless signal characteristics of each merchant are determined according to the wireless signal information of each data point in the cluster matching each merchant.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of Internet technology, and in particular to distribution data processing methods, devices, equipment and storage media. Background Art

[0002] At present, delivery services are widely used in scenarios such as food delivery and errand shopping. In this scenario, the delivery capacity needs to go to the location of the physical merchant to pick up the items and then deliver them to the user's designated location. In actual business, it is often necessary to locate the location of the delivery capacity, especially to locate whether the delivery capacity has reached the location of the physical merchant. Some stores or warehouses are indoors, and the satellite signals indoors will have a large drift, making it difficult to use satellite signals to accurately locate the location of the delivery capacity. Wireless signals can be used to solve the positioning problem indoors, but how to achieve a low-cost solution is a technical problem that needs to be solved urgently. Summary of the invention

[0003] In order to overcome the problems existing in the related art, this specification provides a distribution data processing method, device, equipment and storage medium.

[0004] According to a first aspect of an embodiment of this specification, a delivery data processing method is provided, comprising:

[0005] Acquire a historical sequence set, each historical sequence in the historical sequence set comprising: a plurality of data points collected when a delivery transport capacity executes a delivery waybill of a merchant located within a set geographical range, each data point carrying wireless signal information and one or more tags indicating information related to the delivery transport capacity or the delivery waybill;

[0006] According to the similarity of wireless signal information between each data point of each historical sequence, multiple clusters are obtained;

[0007] Obtaining a cluster label of each of the clusters, wherein the cluster label of each of the clusters is obtained according to a label carried by each data point belonging to the cluster;

[0008] After determining a cluster matching each merchant within the set geographical range according to the cluster label of each cluster, the wireless signal characteristics of each merchant are determined according to the wireless signal information of each data point in the cluster matching each merchant.

[0009] In some examples, the labels carried by the data points include any of the following:

[0010] A static tag indicating that the delivery capacity was in a relatively static state when the data point was collected; or

[0011] A waybill information label representing each first waybill of the delivery capacity when the data point is collected; the first waybill includes: a delivery waybill that is not completed when the data point is collected and the merchant location is within the set geographical range.

[0012] In some examples, the method further includes: for each data point of each of the historical sequences, if the similarity of the wireless signal information of the data point and a plurality of data points adjacent in time satisfies a similarity condition, configuring a label for the data point indicating that the delivery capacity was in a relatively static state when the data point was collected;

[0013] and / or,

[0014] The waybill information includes any one of the following: a first waybill identifier, a merchant identifier corresponding to the first waybill, or a shipping time of the first waybill.

[0015] In some examples, obtaining a cluster label of each of the clusters includes:

[0016] According to a ratio of the number of data points in the cluster carrying the static label to the total number of data points in the cluster, obtaining a ratio label indicating the ratio;

[0017] Determine the order quantity of each merchant included in the cluster according to the waybill information tag of the data point in the cluster, and obtain a quantity tag indicating the order quantity of each merchant; and / or,

[0018] According to the waybill information tags of the data points in the cluster, the average shipping time of the waybills of each merchant included in the cluster is determined, and a tag indicating the average shipping time of the waybills of each merchant is obtained.

[0019] In some examples, determining a cluster matching each of the merchants within the set geographical range according to the cluster label of each cluster includes:

[0020] For a first merchant among the multiple merchants within the set geographical range, selecting one or more clusters including a first waybill information label of the first merchant from the multiple clusters according to the waybill information label;

[0021] Determine the degree of match between each selected cluster and the first merchant; wherein the degree of match is positively correlated with the proportion label, positively correlated with the quantity label indicating the order quantity of the first merchant, and positively correlated with the similarity between the average shipping time label indicating the first merchant's waybill and the timestamp of the data point carrying the stationary state label.

[0022] In some examples, there are multiple clusters matching the merchant, and determining the wireless signal characteristics of the merchant includes:

[0023] The wireless signal characteristics of each cluster in the multiple clusters matching the merchant are obtained to obtain multiple wireless signal characteristics of the merchant.

[0024] In some examples, obtaining the plurality of clusters includes:

[0025] Take each data point in the historical sequence as the clustering object and use the clustering algorithm to obtain multiple clusters; or,

[0026] A network is established with each data point in each historical sequence as a node, wherein two nodes connected by an edge represent that the similarity of two data points respectively corresponding to the two nodes meets a preset data point similarity condition; the network is detected using a community detection algorithm, and multiple clusters are determined based on the multiple communities detected.

[0027] In some examples, the method further comprises:

[0028] After determining that the delivery capacity is within the set geographical range, in response to the wireless signal information collected at the current moment of the delivery capacity, the wireless signal information collected at the current moment is matched with the wireless signal characteristics of each merchant within the set geographical range, and the location of the delivery capacity is determined based on the matching results.

[0029] According to a second aspect of an embodiment of this specification, a distribution data processing device is provided, the device comprising:

[0030] A sequence acquisition module is used to: acquire a historical sequence set, each historical sequence in the historical sequence set includes: a plurality of data points collected when the delivery capacity executes the delivery waybill of a merchant located within a set geographical range, each data point carries wireless signal information and one or more tags indicating the delivery capacity or the delivery waybill related information;

[0031] A cluster acquisition module, used to: acquire multiple clusters according to the similarity of wireless signal information between each data point of each historical sequence;

[0032] A label acquisition module, used to: acquire a cluster label of each cluster, wherein the cluster label of each cluster is obtained according to a label carried by each data point belonging to the cluster;

[0033] The matching module is used to: determine the cluster matching each merchant within the set geographical range according to the cluster label of each cluster, and then determine the wireless signal characteristics of each merchant according to the wireless signal information of each data point in the cluster matching each merchant.

[0034] According to a third aspect of an embodiment of this specification, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method embodiment described in the first aspect are implemented.

[0035] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method embodiment described in the first aspect are implemented.

[0036] The technical solutions provided by the embodiments of this specification may have the following beneficial effects:

[0037] In the embodiment of this specification, it is designed to use the historical sequence of distribution capacity to analyze and mine the wireless signal characteristics of each merchant in multiple merchants within a geographical range; wherein the historical sequence includes: multiple data points collected when the distribution capacity executes the distribution waybill of the merchant located within the set geographical range, each data point carries wireless signal information and one or more tags indicating the distribution capacity or the distribution waybill related information. Through clustering, if multiple distribution capacity stops at the merchant to pick up the goods, the data points collected when staying at the merchant in the historical distribution data of these distribution capacity have a high degree of similarity, that is, they can be clustered into a cluster. The cluster label of a cluster can be obtained according to the labels carried by each data point belonging to the cluster, so in one execution process of this embodiment, the cluster matching each merchant within the set geographical range can be determined, and then the wireless signal characteristics of each merchant can be determined, so the calculation efficiency is fast. This embodiment can achieve an unsupervised processing method through clustering, and combined with the labels carried by the data points, which reduces the cost of data processing and improves the efficiency of data processing.

[0038] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the specification and, together with the description, serve to explain the principles of the specification.

[0040] Figure 1 It is a schematic diagram of a delivery scenario shown in this specification according to an exemplary embodiment.

[0041] Figure 2 It is a flow chart of a delivery data processing method shown in this specification according to an exemplary embodiment.

[0042] Figure 3It is a structural block diagram of a computer device where a distribution data processing device is located according to an exemplary embodiment of this specification.

[0043] Figure 4 It is a block diagram of a distribution data processing device shown in this specification according to an exemplary embodiment. DETAILED DESCRIPTION

[0044] 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 implementations described in the following exemplary embodiments do not represent all implementations consistent with this specification. Instead, they are merely examples of devices and methods consistent with some aspects of this specification as detailed in the appended claims.

[0045] The terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit this specification. The singular forms "a", "the" and "the" used in this specification and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. 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.

[0046] It should be understood that although the terms first, second, third, etc. may be used in this specification to describe various information, this 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 this specification, 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 determining".

[0047] like Figure 1 As shown, it is a schematic diagram of a delivery scenario according to an exemplary embodiment of the present specification, wherein the service provider has built a service end 111, and provides a client 122 to a user 121, and the user 121 can use the service provided by the service provider through the client 122; the service provider also provides a client 132 for the merchant 131 to use, and the merchant 131 can use the service provided by the service provider through the client 132. Among them, each user can trade with the merchant through the client, and the service provider can generate a transaction order and a delivery waybill based on the transaction, and allocate delivery capacity for the delivery waybill. The delivery capacity of this embodiment refers to a party with delivery capabilities, including but not limited to delivery personnel, such as the so-called riders; for example, Figure 1The delivery capacity 141 and its client 142 are shown in the figure; in other examples, the delivery capacity can also include unmanned delivery electronic devices, such as drones, unmanned vehicles, etc. These devices can run clients that communicate with the server.

[0048] For example, after a user places an order, the delivery transport capacity needs to go to the physical store to pick up the items and then deliver them to the user's designated location. Therefore, the service end (such as an e-commerce platform or other delivery platform that cooperates with it) needs to generate a corresponding delivery waybill for the delivery items and allocate the delivery waybill to the delivery transport capacity. After receiving the delivery waybill, the delivery transport capacity goes to the delivery item pick-up location (such as the above-mentioned physical store or warehouse) to pick up the delivery items, and delivers the delivery items to the user's designated location after successful pickup.

[0049] For example, in a food delivery scenario, a user places an order through a client to a physical store on the food delivery platform. The food delivery platform generates the corresponding food delivery order and then allocates the food delivery order to the delivery capacity (such as the client device used by the rider). The rider then goes to the physical store (i.e., the pick-up location for the delivered items) to pick up the food and deliver it to the location specified by the user.

[0050] It can be seen that the execution process of the delivery order includes the stage of going to the pick-up location for the delivery items, the stage of picking up the delivery items after arriving at the pick-up location (i.e. the item pickup stage), and the stage of delivering the delivery items after leaving the pick-up location.

[0051] In actual business, it is often necessary to locate the location of the delivery capacity. For example, to determine whether the delivery capacity has actually arrived at the merchant's location, or to accurately determine the time when the delivery capacity arrives at the merchant. However, many merchants are located indoors, and indoor satellite signals will drift greatly, making it difficult to use satellite signals for accurate indoor positioning. Therefore, indoor positioning solutions using wireless signals can be considered.

[0052] There is a corresponding wireless signal at the pickup location. For example, if the pickup location is equipped with an AP (Wireless Access Point), and the mobile terminal held by the delivery transport capacity is equipped with a Wi-Fi module, then the client running on the mobile terminal can obtain the Wi-Fi module to detect the Wi-Fi signal emitted from the pickup location within a certain range. Therefore, the delivery transport capacity detects the signal characteristics of the wireless signal in the process of executing the delivery order, and the location of the delivery transport capacity can be determined by combining the characteristics of the wireless signal's limitation on the signal range (it cannot be detected beyond a certain range). For example, in the stage when the delivery transport capacity goes to the pickup location and after leaving the pickup location, the delivery transport capacity is not within the signal coverage of the pickup location, and its mobile terminal cannot detect the wireless signal or detects the wireless signal of other locations. The delivery transport capacity is at the pickup location during the item pickup stage and can detect the wireless signal corresponding to the pickup location. Therefore, the characteristics of the wireless signal detected by the delivery party during the item pickup stage can be used as a basis for determining the signal characteristics of the wireless signal corresponding to the pickup location.

[0053] Of course, in addition to the above example of Wi-Fi signals, any other short-range communication technology can be used as long as it has the characteristic of "range limitation". For example, communication technologies such as IrDA (Infrared Data Association) infrared data transmission, ZigBee, NFC (Near Field Communication), UWB (UltraWideBand), DECT (Digital Enhanced Cordless Telecommunications) and the like can also be used.

[0054] Therefore, in the delivery scenario, how to accurately determine the signal characteristics of the wireless signal at the pickup location is of great business significance. Some solutions are to manually collect wireless signal data at various locations indoors and then analyze the wireless signal characteristics of each location, but this method is costly and has low coverage.

[0055] Based on this, the embodiment of this specification provides a solution with low implementation cost. This embodiment is designed to use the historical sequence of distribution capacity to analyze and mine the wireless signal characteristics of each merchant in multiple merchants within a geographical range; wherein the historical sequence includes: multiple data points collected when the distribution capacity executes the distribution waybill of the merchant located within the set geographical range, each data point carries wireless signal information and one or more tags indicating the distribution capacity or the distribution waybill related information. Through clustering, if multiple distribution capacity stops at the merchant to pick up the goods, the data points collected when staying at the merchant in the historical distribution data of these distribution capacity have a high degree of similarity, that is, they can be clustered into a cluster. The cluster label of a cluster can be obtained according to the labels carried by each data point belonging to the cluster. Therefore, in one execution process of this embodiment, the cluster matching each merchant within the set geographical range can be determined, and then the wireless signal characteristics of each merchant can be determined, so the calculation efficiency is fast. This embodiment can realize unsupervised processing through clustering, and combined with the labels carried by the data points, which reduces the cost of data processing and improves data processing efficiency. Next, this embodiment is described in detail.

[0056] like Figure 2 As shown, Figure 2 This is a flow chart of a delivery data processing method according to an exemplary embodiment of the present specification. The solution of this embodiment can be applied to the server, and includes the following steps:

[0057] In step 202, a historical sequence set is obtained.

[0058] Among them, each historical sequence in the historical sequence set includes: multiple data points collected when the delivery capacity executes the delivery waybill of merchants located within the set geographical range, each data point carries wireless signal information and one or more tags indicating the delivery capacity or the delivery waybill related information.

[0059] In step 204, multiple clusters are obtained according to the similarity of the wireless signal information between the data points of the historical sequences.

[0060] In step 206, a cluster label of each cluster is obtained, where the cluster label of each cluster is obtained according to labels carried by each data point belonging to the cluster.

[0061] In step 208, after determining a cluster matching each merchant within the set geographical range according to the cluster label of each cluster, the wireless signal characteristics of each merchant are determined according to the wireless signal information of each data point in the cluster matching each merchant.

[0062] In order to achieve a low-cost solution, this embodiment is designed to use the historical delivery data of the delivery capacity to analyze and mine the wireless signal characteristics of the merchant. Among them, the delivery capacity can continuously collect information during the delivery process; any information involved in this embodiment is collected with the authorization and consent of the user, and the client can perform information desensitization and information protection locally through privacy computing and other methods.

[0063] Exemplarily, the client may start collecting delivery data after determining that the delivery capacity has accepted the order until the delivery capacity stops accepting orders; the client may send the collected delivery data to the server in a set manner. Among them, the delivery data continuously collected by the client is a time-ordered sequence of data points, and the information carried by each of the data points includes: time information, and at least one of geographic location information or wireless signal information. In actual applications, some data points may carry both geographic location information and wireless signal information, the geographic location information in some data points is empty (perhaps because the delivery capacity is indoors and the geographic location information cannot be determined), and the wireless signal information of some data points (indicating that no wireless signal is detected at the current location of the delivery capacity) is empty.

[0064] As mentioned above, the positioning information will drift when the delivery capacity is indoors, and a delivery order will last for a certain period of time from the beginning to the end of delivery. During this period, it is unknown at which time the delivery capacity will pick up the items at the merchant. In this embodiment, it is considered that the delivery capacity is in a moving state at some stages during the entire delivery process, such as the process of going to the merchant and the process of leaving the merchant after picking up the items; but the delivery capacity needs to stay at the merchant to pick up the items to be delivered. When the delivery capacity is within the wireless signal range of the merchant, the delivery capacity is in a relatively static state.

[0065] In actual applications, the server can obtain a large amount of historical distribution data collected from the client of the distribution capacity. In this embodiment, when determining the wireless signal characteristics of merchants, the merchants to be analyzed need to be limited to the set geographical range, and the number of merchants analyzed at a time can be one or more. In actual applications, the set geographical range can be flexibly configured as needed, and this embodiment does not limit this. For example, setting a larger geographical range can include a larger number of merchants, and the wireless signal characteristics of multiple merchants can be determined more efficiently; setting a smaller business district geographical range, the number of merchants included in the business district is smaller, and the wireless signal characteristics of each merchant can be determined more accurately. Exemplarily, the set geographical range can be the geographical range of a shopping mall, which includes a certain number of indoor merchants.

[0066] After the set geographical range is determined, the merchants within the range can be determined. These merchants are the merchants for which the wireless signal characteristics need to be determined in this embodiment. Exemplarily, in a distribution scenario, the server has merchant information of multiple merchants, such as the name and geographic location information of the merchant, etc., and combined with the existing map data, the merchants within the set geographical range can be determined. Exemplarily, each historical distribution waybill of the distribution capacity distribution corresponds to merchant information, and the server can obtain the historical distribution data of the merchants within the set geographical range from the existing large amount of historical distribution data. Exemplarily, each merchant can correspond to multiple historical distribution data.

[0067] In some examples, one or more historical sequences can be obtained from each piece of the historical delivery data. For example, based on the geographic location information carried by the data point and the distance of the set geographic range, multiple data points collected when the delivery capacity is within the set geographic range can be determined from the historical delivery data as the historical sequence.

[0068] In some examples, the labels carried by the data points include any of the following:

[0069] A static tag indicating that the delivery capacity was in a relatively static state when the data point was collected; or

[0070] A waybill information label representing each first waybill of the delivery capacity when the data point is collected; the first waybill includes: a delivery waybill that is not completed when the data point is collected and the merchant location is within the set geographical range.

[0071] Among them, the relative static state of this embodiment refers to the fact that the delivery capacity is relatively static in certain time periods relative to other time periods during the entire delivery process, and is not limited to an absolutely static state. Based on this, this embodiment determines the data points of the delivery capacity in a relatively static state from the historical delivery data, and some of these data points must be collected when the delivery capacity is within the wireless signal range of the merchant. However, the historical delivery data also includes noise points, and other data points that also meet the characteristics of the relatively static state, but these data points are not collected by the delivery capacity at the merchant, for example, the delivery capacity is collected when waiting for the elevator. Therefore, this embodiment is designed to solve the problem by clustering. If there are multiple delivery capacities that stay at the merchant to pick up the items to be delivered, the data points collected when staying at the merchant in the historical delivery data of these delivery capacities have a high degree of similarity, and can be clustered into one category using clustering processing. The information of the wireless signals in the data points clustered into one category can be used to analyze the wireless signal characteristics of the merchant.

[0072] In some examples, when delivery capacity is outdoors, it can use methods such as satellite positioning or base station positioning to determine highly reliable geographic location information. That is, the data points collected outdoors carry geographic location information, and the geographic location information carried by the data points in the historical delivery data can be matched with the set geographic range to determine whether the delivery capacity is approaching or entering the set geographic range.

[0073] Each historical sequence of this embodiment may include multiple data points collected within a set time period. The set time period can be flexibly determined as needed, for example, it can be determined by analyzing the length of time that the delivery capacity usually stays at the merchant based on historical delivery data, or it can be customized according to business needs. For example, the value of the set time period can be a value between 5 minutes and 10 minutes, etc., which can be determined as needed in actual applications, and this embodiment does not limit this.

[0074] Optionally, a static state label can be configured for the data point in the historical sequence indicating that the delivery capacity is in a relatively static state, and the data table that is not in a static state in the historical sequence does not correspond to a static state label. The static state in this embodiment is a relative concept, that is, the relative static state of the delivery capacity in the entire delivery process of the delivery order, and does not simply refer to the delivery capacity being in an absolutely static state.

[0075] There are many ways to determine the data points that indicate that the delivery capacity is in a relatively static state. As an example, it can also be determined by obtaining other information. For example, if the delivery capacity is in a static state, the delivery capacity will not move. Most electronic devices are equipped with an inertial measurement unit (IMU). The electronic device can use the data collected by the IMU to determine the posture information of the delivery capacity and the number of steps of the delivery capacity when walking, etc. The electronic device also provides an interface for the step information to be called by the client. Therefore, if the electronic device supports it and the client has the authority to obtain the step information, the client can obtain the step information of the delivery capacity collected by the electronic device, and identify whether the delivery capacity is in a static state based on the step information. For example, if the step information changes very little or does not change within a certain period of time, it can be determined that the delivery capacity is in a static state during this time period.

[0076] In other examples, the label of the data point also includes a waybill information label, and the first waybill includes: a delivery waybill that is not completed when the data point is collected and the merchant location is within the set geographical range. The waybill information may include any of the following: a first waybill identifier, a merchant identifier corresponding to the first waybill, or a shipping time of the first waybill. In actual applications, other waybill information may also be included as needed, and this embodiment does not limit this.

[0077] In some examples, for each data point in each of the historical sequences, if the similarity between the wireless signal information of the data point and multiple data points adjacent in time meets the similarity condition, a label representing that the distribution capacity was in a relatively static state when the data point was collected is configured for the data point. For example, when the distribution capacity is in a static state, the similarity between the data point and the surrounding data points is high, so the similarity between multiple data points can be calculated to determine the data point indicating that the distribution capacity is in a relatively static state. For example, in a relatively static state, the distribution capacity is within the wireless signal range of the merchant, and the wireless signal information of multiple data points collected in this process are highly similar and have not changed much. Therefore, the distance between each data point can be calculated to determine the similarity. For example, the wireless signal information collected by each data point may include the name and strength of one or more wireless signals, and the similarity of each data point can be calculated based on the name of the wireless signal of the data point and the strength of the wireless signal.

[0078] In step 204, each cluster includes multiple data points, and the similarity of wireless signal information between the data points in a cluster satisfies a set similarity condition. Exemplarily, a clustering algorithm or a community detection algorithm may be used to obtain multiple clusters.

[0079] Taking the clustering algorithm as an example, the data points in each historical sequence can be used as clustering objects, and multiple clusters can be obtained by using the clustering algorithm; multiple clusters can be obtained by clustering all historical sequences; a variety of clustering algorithms can be used in practical applications, such as the k-means algorithm. Clustering processing can obtain multiple clusters, and then the clusters that match the merchant can be determined. The historical sequences that are clustered into one category are more likely to be sequences composed of data points collected when the rider is at a merchant location.

[0080] Taking the community detection algorithm as an example, a network can be established with each data point in each historical sequence as a node, wherein two nodes connected by an edge indicate that the similarity of the two data points corresponding to the two nodes respectively meets the preset data point similarity condition; the network is detected using the community detection algorithm, and multiple clusters are determined based on the multiple communities detected.

[0081] A cluster represents that multiple delivery waybills all come from one merchant. Since multiple data points under the cluster carry labels, this embodiment obtains the cluster label of each cluster according to the labels carried by each data point belonging to the cluster. Therefore, according to the cluster label of each cluster, a cluster matching each merchant within the set geographical range can be determined.

[0082] In actual applications, when the client collects information to generate data points, the delivery capacity may correspond to multiple unfinished delivery waybills, that is, the delivery capacity has multiple back orders, and multiple unfinished delivery waybills may involve multiple merchants, that is, when a data point is generated, due to multiple unfinished delivery waybills of multiple merchants, it is necessary to accurately determine which merchant this data point corresponds to. In the above embodiments, the problem can be solved to a certain extent by using geographic location information. For example, in some embodiments, wireless signal characteristics can be obtained for merchants within a set geographic location range. For a data point, the geographic location information of merchants in multiple waybills carried by the delivery capacity can be used to determine which merchants the data point may correspond to. For example, when collecting data points, multiple back orders of the delivery capacity involve merchant 1, merchant 2, and merchant 3. In this embodiment, for merchants within a set geographic location range, it can be determined whether the locations of merchant 1, merchant 2, and merchant 3 are within the set geographic location range. If merchant 3 is not within the set geographic location range, it can be determined that the data point may be collected when the delivery capacity is located at merchant 1 or merchant 2.

[0083] Of course, it is also possible that when data points are collected, multiple merchants with multiple orders for delivery capacity are all within the set geographical location range. Therefore, when matching merchants with each cluster, this embodiment uses the label information carried by the data points in the cluster to improve the accuracy of the merchant and cluster matching results.

[0084] In some examples, obtaining a cluster label for each of the clusters may include:

[0085] According to the ratio of the number of data points carrying the static tags in the cluster to the total number of data points in the cluster, a proportional label indicating the ratio is obtained; for example, in a cluster, the more data points carrying the static tags are, the higher the probability that the distribution capacity is in a static state (i.e., waiting for goods) near the merchant, and the reliability of the data points collected by the distribution capacity for characterizing the wireless signal characteristics of the merchant is higher. Exemplarily, if there are N data points in a cluster and M data points carrying static tags are present, the ratio indicated by the proportional label is M / N, where N and M are positive integers and N is greater than or equal to M.

[0086] According to the waybill information label of the data point in the cluster, the number of orders of each merchant included in the cluster is determined, and a quantity label indicating the number of orders of each merchant is obtained; for example, there are N data points in the cluster, where data point A carries a label representing an order identifier, wherein the back order of the delivery capacity (i.e., the waybill in the pickup stage) when collecting data point A includes order number 1, order number 2, and order number 3, and the three order identifiers can be used to determine that the three waybills correspond to merchant 1, merchant 2, and merchant 3 respectively; it can be seen from the above embodiment that these three merchants are all located within the set geographical range. Similarly, according to other data points in the cluster that carry labels representing order identifiers, the merchants appearing in the cluster are counted, for example, if a total of K merchants appear in the cluster, the number of waybills corresponding to each of the K merchants is counted, for example, the number of waybills for merchant 1 in the cluster is 3, the number of waybills for merchant 2 is 8, and so on. It can be seen that in a cluster, the more waybills a merchant has, the higher the matching degree between the cluster and the merchant.

[0087] According to the waybill information label of the data point in the cluster, the average shipping time of the waybill of each merchant included in the cluster is determined, and the label indicating the average shipping time of the waybill of each merchant is obtained. For example, there are N data points in the cluster, wherein data point A carries a label indicating an order identifier, wherein the back order of the delivery capacity (i.e., the waybill in the pickup stage) when collecting data point A includes order number 1, order number 2, and order number 3, and the three order identifiers can be used to determine that the three waybill correspond to the shipping time 1 of merchant 1, the shipping time 2 of merchant 2, and the shipping time 3 of merchant 3 respectively; it can be known from the above embodiment that these three merchants are all located within the set geographical range. Among them, the shipping time can be determined by obtaining the business information corresponding to the order through the order number, for example, some merchants will send the actual shipping time to the service end after shipping; if the merchant does not provide the shipping time, the shipping time of the order can be estimated using a machine learning model, and the machine learning model can be pre-trained using historical delivery order data, and the historical delivery order data includes data of multiple delivery orders carrying real shipping times. The shipping time of a waybill is determined, and the timestamp of the data point collected when the delivery transport capacity picks up the goods from the merchant has a large similarity with the shipping time of the waybill, that is, the similarity between the average shipping time label of the waybill indicating the merchant and the timestamp of the data point is positively correlated; considering that the delivery transport capacity is in a relatively static state when picking up the goods, the matching degree is also positively correlated with the similarity between the average shipping time label of the waybill indicating the first merchant and the timestamp of the data point carrying the static state label.

[0088] Each data point in the cluster carries a label indicating the order identification. As mentioned above, the merchants appearing in the cluster can be counted. For example, it is counted that there are K merchants in the cluster, and each of the K merchants has multiple waybills. Assuming that the number of waybills of merchant 1 in the cluster is 3, the shipping time label of each waybill of the merchant can be obtained, such as the shipping time label of waybill A1, the shipping time label of waybill A2, and the shipping time label of waybill A3. The timestamps of the data points carrying the shipping time label of waybill A1 are counted. The similarity with the shipping time tag of waybill A1, the timestamp of the data point carrying the shipping time tag of waybill A2, the similarity with the shipping time tag of waybill A2, the timestamp of the data point carrying the shipping time tag of waybill A3, and the similarity with the shipping time tag of waybill A3. Based on the three statistical similarities, the matching degree of the cluster and merchant 1 can be determined; similarly, the same method is used for other merchants in the cluster to determine the matching degree of the cluster and the K merchants that appear.

[0089] Exemplarily, the merchant may be matched with each cluster respectively to determine the cluster with the highest matching degree with the merchant. For example, it is assumed that there are n merchants from merchant 1 to merchant n within the geographical location range, and m clusters are obtained. Merchants 1 to merchant n may be traversed. For example, for merchant 1, merchant 1 is matched with m clusters one by one to determine the matching degree between merchant 1 and each cluster. Similarly, other merchants may obtain their matching degree with each cluster. As an example, a matching degree condition may be preset, and if the matching degree condition is met, it means that the cluster matches the merchant. Based on this, one or more clusters matching the merchant may be determined. In actual applications, there may be a situation where the merchant's store is large and there are two or more pickup locations. Therefore, there may be more than one cluster matching the merchant.

[0090] Exemplarily, the matching degree between the merchant and each cluster can be based on at least the information indicated by the labels of all the data points in the cluster. Optionally, the delivery service information can be flexibly selected as needed, for example, it can include order information or merchant information of one or more uncompleted orders of the delivery capacity when the data points are collected, etc. When determining whether the merchant matches the cluster, the matching degree can be determined by combining the information of the merchant to be matched with the information of the labels of all the data points in the cluster.

[0091] Exemplarily, determining a cluster matching each of the merchants within the set geographical range according to the cluster label of each cluster may include:

[0092] For a first merchant among the multiple merchants within the set geographical range, according to the waybill information label, one or more clusters including the first waybill information label of the first merchant from among the clusters;

[0093] Determine the degree of match between each selected cluster and the first merchant; wherein the degree of match is positively correlated with the proportion label, positively correlated with the quantity label indicating the order quantity of the first merchant, and positively correlated with the similarity between the average shipping time label indicating the first merchant's waybill and the timestamp of the data point carrying the stationary state label.

[0094] In practical applications, other methods can also be used to determine the degree of matching. For example, based on one or more unfinished waybills of the delivery capacity when each data point is collected, the merchant of each unfinished waybill and one of the merchant shipping time of each unfinished waybill or the pickup time submitted by the delivery capacity can be obtained; for each data point, the probability that the data point matches the merchant of each unfinished waybill can be determined based on the difference between the collection time of the data point and the meal delivery time of each unfinished order, and / or the difference between the collection time of the data point and the pickup time submitted by the delivery capacity; for the merchant and each cluster, the degree of matching between the merchant and the cluster can be determined based on the number of data points in the cluster and the probability that the data point matches the merchant of each unfinished waybill.

[0095] Exemplarily, this embodiment considers the matching degree between merchants and clusters from multiple dimensions. The cluster includes multiple historical sequences, each of which includes multiple data points. The information carried by each data point includes the time information when the data point was collected. Through the time when each data point was collected, the server can obtain one or more unfinished waybills of the distribution capacity when the data point was collected, and then obtain the merchant of each unfinished waybill, the shipping time of each merchant of the unfinished waybill, or the pickup time submitted by the distribution capacity.

[0096] In some examples, the merchant shipping time of each uncompleted waybill is submitted by the merchant through the client. Through the study of actual business scenarios, the time when the delivery capacity executes a waybill and is at the merchant's location to pick up the goods will not be too far away from the shipping time of the delivery waybill submitted by the merchant. For example, the collection time of data point A is T. When collecting, the delivery capacity has waybill 1 and waybill 2, which correspond to merchant 1 and merchant 2 respectively. The shipping time submitted by merchant 1 for waybill 1 is t1, and the shipping time submitted by merchant 2 for waybill 2 is t2. Based on this, the difference between T and t1, and the difference between T and t2, can determine the probability that the data point matches merchant 1, and the probability that the data point matches merchant 2. Exemplarily, the method of determining the probability can be configured as needed, for example, by comparing the interval between T and t1 and the interval between T and t2, the probability of the data point matching merchant 1 and merchant 2 can be determined based on the two interval values, or it can also be determined in combination with the interval threshold, for example, if it is greater than the interval threshold, the probability is lower. Alternatively, the corresponding relationship between the interval value and the probability value may be set.

[0097] In other examples, the pickup time submitted by the delivery transport for each uncompleted waybill is submitted through the client when the delivery transport arrives at the merchant. Through the study of actual business scenarios, the pickup time submitted by the delivery transport is usually close to the time when the delivery transport is at the merchant's location. For example, the delivery transport usually submits the pickup time when it is about to approach the merchant's location, arrives at the merchant's location, or leaves the merchant's location after picking up the goods. Therefore, the data points collected when the delivery transport is at a certain merchant's location will not be too far away from the pickup time submitted by the delivery transport. For example, the collection time of data point A is T. At the time of collection, the delivery transport has waybill 1 and waybill 2, corresponding to merchant 1 and merchant 2 respectively. The pickup time submitted by the delivery transport for waybill 1 is t1, and the pickup time submitted by the delivery transport for waybill 2 is t2. Based on this, the difference between T and t1, and the difference between T and t2, can determine the probability that the data point matches merchant 1, and the probability that the data point matches merchant 2. Exemplarily, the method of determining the probability can be configured as needed, for example, by comparing the interval between T and t1 and the interval between T and t2, the probability of the data point matching merchant 1 and merchant 2 can be determined based on the two interval values, or it can be determined in combination with the interval threshold, for example, if it is greater than the interval threshold, the probability is low. Alternatively, the corresponding relationship between the interval value and the probability value can be set, etc.

[0098] In actual applications, one of the above methods can be selected for implementation, or a combination of multiple methods can be used. For example, when two methods are combined for implementation, the probability can be determined based on the difference between the collection time of the data point and the merchant shipping time of each uncompleted order, and the difference between the collection time of the data point and the delivery capacity pickup time. The weight of the difference between the collection time of the data point and the merchant shipping time, and the weight of the difference between the collection time of the data point and the delivery capacity pickup time can be determined according to actual needs.

[0099] For example, through the study of actual business scenarios, the pickup time submitted by the delivery capacity is relatively subjective. Since the delivery capacity may not strictly submit the pickup time according to the time when it picks up the goods at the merchant's location, it may be earlier or later, etc. Therefore, its reliability is lower than the merchant's delivery time. Therefore, when the two methods are combined, the weight of the difference between the data point collection time and the merchant's delivery time can be greater than the weight of the difference between the data point collection time and the delivery capacity pickup time.

[0100] Alternatively, when the two methods are combined, matching can be first performed based on the probability determined by the merchant's shipping time. When it is found that the merchant has multiple clusters with the same matching degree, the matching degree can be adjusted again based on the probability based on the delivery capacity pickup time.

[0101] Exemplarily, when determining the degree of matching between the merchant and each cluster, it can also be determined comprehensively in combination with the number of data points in each cluster and the probability that the data point matches the merchant of each uncompleted waybill. Exemplarily, the degree of matching between merchant 1 and cluster 1 is positively correlated with the probability that the data point in cluster 1 matches merchant 1 and the number of data points. For example, a probability threshold can be set to determine the number of data points in the cluster whose probability of matching merchant 1 is higher than the probability threshold, the number of data points whose probability of matching merchant 1 is lower than the probability threshold, and the probability value of each data point matching merchant 1, and comprehensively determine the degree of matching between merchant 1 and cluster 1.

[0102] After obtaining the matching degree between each merchant and each cluster within the set geographic location range, for each merchant, the corresponding cluster of the merchant can be determined according to the matching degree between the merchant and each cluster. There are many ways to determine the cluster corresponding to the merchant, for example, select the cluster with the highest matching degree; or determine in combination with a preset matching degree threshold, select the cluster with a matching degree greater than the preset matching degree threshold and the highest matching degree; if the matching degree between a merchant and all clusters is lower than the preset matching degree threshold, further determination can be made as needed, for example, considering reusing other historical delivery data for clustering again, or determining that the merchant has not matched a suitable cluster, etc.

[0103] Exemplarily, for each cluster, the merchant with the highest matching degree can be determined, or it can be determined in combination with the calculated matching score between the cluster and the merchant. If the matching score is greater than a set threshold, it means that the cluster matches the merchant. The wireless signal information of all data points in all historical sequences in the cluster can be used to extract wireless signal features.

[0104] If a merchant is not matched to any cluster using the above method, the cluster with the highest matching degree may be selected to further determine the wireless signal characteristics of the merchant.

[0105] Using the above method, the wireless signal characteristics of multiple merchants in the business district can be determined, based on which it can be used to locate whether the delivery capacity has arrived at the merchant. In some examples, the method may also include: after determining that the delivery capacity is within the set geographical range, obtaining the wireless signal information collected at the current moment; matching the wireless signal information collected at the current moment with the wireless signal characteristics of one or more merchants within the set geographical range, and determining the merchant location where the delivery capacity is located based on the matching results. For example, if the wireless signal characteristics of the current location of the delivery capacity match the wireless signal characteristics of a predetermined merchant, it can be determined that the delivery capacity is located at the merchant.

[0106] This embodiment is designed to use the historical delivery data of the delivery capacity to analyze and mine the wireless signal characteristics of the merchant; wherein, the delivery data continuously collected by the client of the delivery capacity is a time-ordered sequence of data points, and the information carried by each of the data points includes: time information, and at least one of geographic location information or wireless signal information. By obtaining a historical sequence from the historical delivery data, the historical sequence is a plurality of data points collected when the delivery capacity is in the business district and is continuously in a stationary state for a set time period, therefore, it includes data points collected when the delivery capacity is within the wireless signal range of the merchant. Furthermore, a clustering process is designed. If multiple delivery capacities all stay at a merchant to pick up items to be delivered, the data points collected when staying at the merchant in the historical delivery data of these delivery capacities have a high degree of similarity, and can be clustered into one category using clustering processing. The wireless signal information in the data points clustered into one category can be used to analyze the wireless signal characteristics of the merchant. This embodiment does not require special manual marking, and can be implemented using data collected by existing distribution capacity, so the implementation cost is low; and in one execution of this embodiment, the wireless signal characteristics of multiple merchants within a set geographical range can be determined, so the calculation efficiency is fast. In addition, it is unknown at what time the distribution capacity in the historical distribution data arrives at the merchant location. This embodiment is implemented through clustering, that is, in an unsupervised manner, which also reduces the cost of data processing and improves data processing efficiency.

[0107] Corresponding to the above-mentioned embodiments of the delivery data processing method, this specification also provides embodiments of a delivery data processing apparatus and a computer device used therein.

[0108] The embodiments of the data processing device distributed in this specification can be applied to computer devices, such as servers or terminal devices. The device embodiments can be implemented by software, hardware, or a combination of software and hardware. Taking software implementation as an example, as a device in a logical sense, it is formed by the processor of the file processing in which it is located reading the corresponding computer program instructions in the non-volatile memory into the memory and running them. From the hardware level, if Figure 3 The figure is a hardware structure diagram of the computer equipment where the data processing device of this manual is distributed, except Figure 3 In addition to the processor 310, memory 330, network interface 320, and non-volatile memory 340 shown, the computer device where the distribution data processing device 331 is located in the embodiment may also include other hardware according to the actual function of the computer device, which will not be described in detail.

[0109] like Figure 4 As shown, Figure 4 is a block diagram of a distribution data processing device according to an exemplary embodiment of the present specification, the device comprising:

[0110] The sequence acquisition module 41 is used to: acquire a historical sequence set, each historical sequence in the historical sequence set includes: a plurality of data points collected when the delivery capacity executes the delivery waybill of the merchant located within the set geographical range, each data point carries wireless signal information and one or more tags indicating the delivery capacity or the delivery waybill related information;

[0111] The cluster acquisition module 42 is used to: acquire multiple clusters according to the similarity of wireless signal information between each data point of each historical sequence;

[0112] The label acquisition module 43 is used to: acquire a cluster label of each cluster, wherein the cluster label of each cluster is obtained according to the label carried by each data point belonging to the cluster;

[0113] The matching module 44 is used to: determine the cluster matching each merchant within the set geographical range according to the cluster label of each cluster, and then determine the wireless signal characteristics of each merchant according to the wireless signal information of each data point in the cluster matching each merchant.

[0114] In some examples, the labels carried by the data points include any of the following:

[0115] A static tag indicating that the delivery capacity was in a relatively static state when the data point was collected; or

[0116] A waybill information label representing each first waybill of the delivery capacity when the data point is collected; the first waybill includes: a delivery waybill that is not completed when the data point is collected and the merchant location is within the set geographical range.

[0117] In some examples, the label acquisition module is further used to: for each data point of each historical sequence, if the similarity of the wireless signal information of the data point and multiple data points adjacent in time meets the similarity condition, configure a label for the data point indicating that the distribution capacity is in a relatively static state when the data point is collected;

[0118] and / or,

[0119] The waybill information includes any one of the following: a first waybill identifier, a merchant identifier corresponding to the first waybill, or a shipping time of the first waybill.

[0120] In some examples, the tag acquisition module is further used to:

[0121] According to a ratio of the number of data points in the cluster carrying the static label to the total number of data points in the cluster, obtaining a ratio label indicating the ratio;

[0122] Determine the order quantity of each merchant included in the cluster according to the waybill information tag of the data point in the cluster, and obtain a quantity tag indicating the order quantity of each merchant; and / or,

[0123] According to the waybill information tags of the data points in the cluster, the average shipping time of the waybills of each merchant included in the cluster is determined, and a tag indicating the average shipping time of the waybills of each merchant is obtained.

[0124] In some examples, the matching module is further used to:

[0125] For a first merchant among the multiple merchants within the set geographical range, selecting one or more clusters including a first waybill information label of the first merchant from the multiple clusters according to the waybill information label;

[0126] Determine the degree of match between each selected cluster and the first merchant; wherein the degree of match is positively correlated with the proportion label, positively correlated with the quantity label indicating the order quantity of the first merchant, and positively correlated with the similarity between the average shipping time label indicating the first merchant's waybill and the timestamp of the data point carrying the stationary state label.

[0127] In some examples, the matching module is further used to: obtain a wireless signal feature of each of a plurality of clusters matching the merchant, to obtain a plurality of wireless signal features of the merchant.

[0128] In some examples, the cluster acquisition module is further used to:

[0129] Take each data point in the historical sequence as the clustering object and use the clustering algorithm to obtain multiple clusters; or,

[0130] A network is established with each data point in each historical sequence as a node, wherein two nodes connected by an edge represent that the similarity of two data points respectively corresponding to the two nodes meets a preset data point similarity condition; the network is detected using a community detection algorithm, and multiple clusters are determined based on the multiple communities detected.

[0131] In some examples, the device location determination module is used to:

[0132] After determining that the delivery capacity is within the set geographical range, in response to the wireless signal information collected at the current moment of the delivery capacity, the wireless signal information collected at the current moment is matched with the wireless signal characteristics of each merchant within the set geographical range, and the location of the delivery capacity is determined based on the matching results.

[0133] Correspondingly, an embodiment of the present specification also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the aforementioned distribution data processing method embodiment when executing the computer program.

[0134] Correspondingly, the embodiment of the present specification also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the aforementioned distribution data processing method embodiment are implemented.

[0135] The implementation process of the functions and effects of each module in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned distribution data processing method, and will not be repeated here.

[0136] Correspondingly, an embodiment of the present specification also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the distribution data processing method embodiment when executing the program.

[0137] Accordingly, the embodiments of the present specification also provide a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the embodiment of the distribution data processing method are implemented.

[0138] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this specification. A person of ordinary skill in the art can understand and implement it without paying creative labor.

[0139] The above is a description of a specific embodiment of the specification. 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 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.

[0140] The step division of the above methods is only for clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the protection scope of this patent; adding insignificant modifications to the algorithm or process or introducing insignificant designs without changing the core design of the algorithm and process are all within the protection scope of this application.

[0141] The description of "specific examples" or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of this specification. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0142] Those skilled in the art will readily appreciate other embodiments of the specification after considering the specification and practicing the invention claimed herein. The specification is intended to cover any variations, uses or adaptations of the specification that follow the general principles of the specification and include common knowledge or customary techniques in the art that are not claimed in the specification. The specification and examples are to be considered exemplary only, and the true scope and spirit of the specification are indicated by the following claims.

[0143] It should be understood that the present description is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present description is limited only by the appended claims.

[0144] The above description is only a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this specification should be included in the scope of protection of this specification.

Claims

1. A distribution data processing method, comprising: A historical sequence set is obtained, wherein each historical sequence in the historical sequence set includes: a plurality of data points collected when the delivery transport capacity executes a delivery waybill of a merchant located within a set geographical range, each data point carrying wireless signal information and a label; the label includes a stationary label representing that the delivery transport capacity is in a relatively stationary state when the data point is collected; and a waybill information label representing each first waybill of the delivery transport capacity when the data point is collected; the first waybill includes: a delivery waybill that is not completed when the data point is collected and the merchant location is within the set geographical range; According to the similarity of wireless signal information between each data point of each historical sequence, multiple clusters are obtained; Obtaining a cluster label of each of the clusters, wherein the cluster label of each of the clusters is obtained according to a label carried by each data point belonging to the cluster; After determining a cluster matching each merchant within the set geographical range according to the cluster label of each cluster, determine the wireless signal characteristics of each merchant according to the wireless signal information of each data point in the cluster matching each merchant; The matching degree between each merchant and the cluster is positively correlated with the ratio of the number of data points carrying the static tags in the cluster to the total number of data points in the cluster, and is positively correlated with the number of orders belonging to the merchant corresponding to the cluster; The number of orders belonging to the merchant corresponding to the cluster is determined by the waybill information tags carried by the data points in the cluster.

2. The method according to claim 1, further comprising: For each data point of each of the historical sequences, if the similarity between the wireless signal information of the data point and multiple data points adjacent in time satisfies a similarity condition, a label is configured for the data point indicating that the distribution capacity is in a relatively static state when the data point is collected; and / or, The waybill information includes any one of the following: a first waybill identifier, a merchant identifier corresponding to the first waybill, or a shipping time of the first waybill.

3. According to the method of claim 2, the obtaining of the cluster label of each cluster comprises: According to a ratio of the number of data points in the cluster carrying the static label to the total number of data points in the cluster, obtaining a ratio label indicating the ratio; Determine the order quantity of each merchant included in the cluster according to the waybill information tag of the data point in the cluster, and obtain a quantity tag indicating the order quantity of each merchant; and / or, According to the waybill information tags of the data points in the cluster, the average shipping time of the waybills of each merchant included in the cluster is determined, and a tag indicating the average shipping time of the waybills of each merchant is obtained.

4. The method according to claim 3, wherein determining a cluster matching each of the merchants within the set geographical range according to the cluster label of each cluster comprises: For a first merchant among the multiple merchants within the set geographical range, selecting one or more clusters including a first waybill information label of the first merchant from the multiple clusters according to the waybill information label; Determine the degree of match between each selected cluster and the first merchant; wherein the degree of match is positively correlated with the proportion label, positively correlated with the quantity label indicating the order quantity of the first merchant, and positively correlated with the similarity between the average shipping time label indicating the first merchant's waybill and the timestamp of the data point carrying the stationary state label.

5. The method according to claim 3, wherein the merchant has multiple matching clusters, and the determining of the wireless signal characteristics of the merchant comprises: The wireless signal characteristics of each cluster in the multiple clusters matching the merchant are obtained to obtain multiple wireless signal characteristics of the merchant.

6. The method according to claim 1, wherein obtaining a plurality of clusters comprises: Taking the data points in each historical sequence as clustering objects, multiple clusters are obtained using clustering algorithms; or, A network is established with each data point in each historical sequence as a node, wherein two nodes connected by an edge represent that the similarity of two data points respectively corresponding to the two nodes meets a preset data point similarity condition; the network is detected using a community detection algorithm, and multiple clusters are determined based on the multiple communities detected.

7. The method according to claim 1, further comprising: After determining that the delivery capacity is within the set geographical range, in response to the wireless signal information collected at the current moment of the delivery capacity, the wireless signal information collected at the current moment is matched with the wireless signal characteristics of each merchant within the set geographical range, and the location of the delivery capacity is determined based on the matching results.

8. A distribution data processing device, comprising: A sequence acquisition module is used to: acquire a historical sequence set, each historical sequence in the historical sequence set includes: a plurality of data points collected when the delivery transport capacity executes the delivery waybill of a merchant located within a set geographical range, each data point carries wireless signal information and a label; the label includes a stationary label representing that the delivery transport capacity is in a relatively static state when the data point is collected; and a waybill information label representing each first waybill of the delivery transport capacity when the data point is collected; the first waybill includes: a delivery waybill that is not completed when the data point is collected and the merchant location is within the set geographical range; A cluster acquisition module, used to: acquire multiple clusters according to the similarity of wireless signal information between each data point of each historical sequence; A label acquisition module, used to: acquire a cluster label of each cluster, wherein the cluster label of each cluster is obtained according to a label carried by each data point belonging to the cluster; A matching module, configured to: determine a cluster matching each merchant within the set geographical range according to the cluster label of each cluster, and then determine a wireless signal feature of each merchant according to wireless signal information of each data point in the cluster matching each merchant; The matching degree between each merchant and the cluster is positively correlated with the ratio of the number of data points carrying the static tags in the cluster to the total number of data points in the cluster, and is positively correlated with the number of orders belonging to the merchant corresponding to the cluster; The number of orders belonging to the merchant corresponding to the cluster is determined by the waybill information tags carried by the data points in the cluster.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method according to any one of claims 1 to 7.

Images