Merchant positioning method, device and equipment and computer readable storage medium
By analyzing merchant spatiotemporal trajectory fragments and grid division, the problem that existing technologies cannot simultaneously guarantee comprehensiveness and efficiency in merchant positioning has been solved, achieving efficient and accurate merchant positioning.
Patent Information
- Application Number
- CN202411097433.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2024-11-22
AI Technical Summary
Existing merchant location methods cannot simultaneously guarantee the comprehensiveness and efficiency of obtaining merchant location information.
By acquiring multiple spatiotemporal trajectory segments corresponding to merchants, analyzing the user's movement distance and location relationship, and using speed prediction models and duration prediction models, the location information of merchants can be determined, and grid division can be combined to improve positioning accuracy.
This approach ensures the comprehensiveness of merchant location information while improving acquisition efficiency and enhancing the accuracy and efficiency of merchant positioning.
Smart Images

Figure CN119006105A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of data processing technology, and in particular, relates to a merchant positioning method, device, equipment and computer-readable storage medium. Background Art
[0002] With the development of informatization, in order to meet people's growing consumption needs, it is often necessary to locate merchants to ensure that users can find target merchants through positioning information in electronic devices.
[0003] At present, there are various ways to locate merchants. For example, the merchant location information can be collected specifically by purchasing service providers to ensure the comprehensiveness of the merchant location information. However, the information collection process is time-consuming and labor-intensive, and the efficiency is low. For another example, the merchant location information can be obtained through the merchant terminal with positioning function in the merchant; the merchant location information can also be identified through the navigation path data of couriers and deliverymen. The efficiency of obtaining merchant location information through merchant terminals or the navigation path data of couriers and deliverymen is high, but it cannot guarantee that all merchant location information is obtained.
[0004] In summary, the current merchant positioning methods are unable to achieve both comprehensiveness and efficiency in obtaining merchant location information. Summary of the invention
[0005] The embodiments of the present application provide a merchant positioning method, apparatus, device, computer-readable storage medium and computer program product, which can ensure both the comprehensiveness and efficiency of obtaining merchant location information.
[0006] In a first aspect, an embodiment of the present application provides a merchant positioning method, the method comprising:
[0007] Acquire a plurality of first spatiotemporal trajectory segments corresponding to a first merchant, the first spatiotemporal trajectory segments comprising a plurality of first trajectory nodes, the plurality of first trajectory nodes comprising a first merchant node and at least one first reference location node, the first reference location node comprising a first location and a first moment when a user is located at the first location, the first merchant node comprising a second moment when the user conducts a transaction with the first merchant;
[0008] For each of the first spatiotemporal trajectory segments, respectively: obtaining a moving distance of the user within a target duration corresponding to the first spatiotemporal trajectory segment; determining a first area where the first location is located according to the moving distance and its corresponding first location; the target duration is determined according to the first moment and the second moment;
[0009] Determining a target area where the first merchant is located according to a relative position relationship of a plurality of the first areas;
[0010] The location information of the target area is determined as the location information of the first merchant.
[0011] In a possible implementation, the acquiring a plurality of first spatiotemporal trajectory segments corresponding to the first merchant includes:
[0012] Acquire spatiotemporal trajectory information corresponding to a plurality of users respectively, wherein the spatiotemporal trajectory information includes a plurality of trajectory nodes;
[0013] Moving the sliding window according to a preset step length to divide the space-time trajectory corresponding to each of the space-time trajectory information into a plurality of space-time trajectory segments;
[0014] Among the multiple spatiotemporal trajectory segments, the multiple first spatiotemporal trajectory segments including the first reference location node and the first merchant node are screened out.
[0015] In a possible implementation, obtaining the moving distance of the user within the target duration corresponding to the first spatiotemporal trajectory segment includes:
[0016] Obtaining a moving speed of the user within a target duration corresponding to the first spatiotemporal trajectory segment;
[0017] The moving distance is determined according to the moving speed and the target duration.
[0018] In a possible implementation, obtaining the moving speed of the user within the target duration corresponding to the first spatiotemporal trajectory segment includes:
[0019] Acquire a plurality of second spatiotemporal trajectory segments, the second spatiotemporal trajectory segments comprising a plurality of second trajectory nodes, the plurality of second trajectory nodes comprising a second reference position node and a third reference position node, the second reference position node comprising the first position and a third moment when the user is located at the first position, the third reference position node comprising the second position and a fourth moment when the user is located at the second position;
[0020] When the reference duration is less than a first preset threshold, the moving speed is determined according to the third moment, the fourth moment, the first position and the second position, and the reference duration is the duration between the first moment and the third moment.
[0021] In a possible implementation, obtaining the moving speed of the user within the target duration corresponding to the first spatiotemporal trajectory segment includes:
[0022] Acquire first environmental feature information corresponding to the first spatiotemporal trajectory segment, first attribute information of the first reference location node in the first spatiotemporal trajectory segment, second attribute information of the first merchant in the first spatiotemporal trajectory segment, and third attribute information of a user who transacts with the first merchant;
[0023] A speed prediction model is used to perform speed prediction based on the first attribute information, the second attribute information, the third attribute information and the first environmental feature information to obtain the moving speed. The speed prediction model is trained with a first target information sample corresponding to the spatiotemporal trajectory segment sample as input and a moving speed sample as output. The first target information sample includes a first environmental feature information sample corresponding to the spatiotemporal trajectory segment sample, a first attribute information sample of a reference position node sample in the spatiotemporal trajectory segment sample, a second attribute information sample of a first merchant sample in the spatiotemporal trajectory segment sample, and a third attribute information sample of a user who transacts with the first merchant sample.
[0024] In a possible implementation manner, before determining the target area where the first merchant is located according to the relative position relationship of the plurality of first areas, the method further includes:
[0025] Divide the second area where the first merchant is located into grids to obtain a plurality of grids, wherein the second area at least includes the first area;
[0026] The determining the target area where the first merchant is located according to the relative position relationship of the plurality of first areas includes:
[0027] Obtain a first probability that the first merchant is located in each of the grids in the plurality of the first areas;
[0028] At least one of the grids corresponding to a maximum value among the plurality of the first probabilities is determined as the target area.
[0029] In a possible implementation manner, obtaining the first probability corresponding to each of the grids in the plurality of first areas includes:
[0030] For each of the grids in each of the first areas, calculating a second probability according to the target duration;
[0031] In the case where the grid belongs to one of the first regions, determining a second probability corresponding to the grid in the first region as the first probability;
[0032] In the case that the grid belongs to a plurality of the first regions, the sum of the second probabilities respectively corresponding to the plurality of the first regions is determined as the first probability.
[0033] In a possible implementation, before obtaining the moving distance of the user within the target duration, the method further includes:
[0034] Obtaining the shopping time of the user in the first merchant;
[0035] The target duration is determined according to the first time, the second time and the shopping duration.
[0036] In a possible implementation, obtaining the shopping time of the user in the first merchant includes:
[0037] Monitoring the moving speed of the user to obtain a monitoring result;
[0038] If the monitoring result indicates that the moving speed of the user is less than a second preset threshold, recording a fourth moment;
[0039] Obtaining a fifth moment at which the user conducts a transaction at the first merchant;
[0040] When the fourth moment is before the fifth moment and the moving speed between the fourth moment and the fifth moment is continuously less than the second preset threshold, the shopping duration is determined according to the fourth moment and the fifth moment.
[0041] In a possible implementation, obtaining the shopping time of the user in the first merchant includes:
[0042] Acquire second environmental feature information corresponding to the first merchant, fourth attribute information of a user shopping in the first merchant, and fifth attribute information of the first merchant;
[0043] A duration prediction model is used to predict the shopping duration based on the fourth attribute information, the fifth attribute information and the second environmental characteristic information to obtain the shopping duration of the user in the first merchant. The duration prediction model is trained with the second target information sample corresponding to the second merchant sample as input and the shopping duration sample of the user in the second merchant sample as output. The second target information sample includes the second environmental characteristic information sample corresponding to the second merchant sample, the fourth attribute information sample corresponding to the user shopping in the second merchant sample, and the fifth attribute information sample corresponding to the second merchant sample.
[0044] In a possible implementation, obtaining the shopping time of the user in the first merchant includes:
[0045] Obtaining the target merchant type of the first merchant;
[0046] According to the correspondence between the merchant type and the shopping time, the shopping time corresponding to the target merchant type is determined.
[0047] In a possible implementation manner, the target duration is smaller than a third preset threshold, and the third preset threshold is determined according to a preset range and a preset moving speed.
[0048] In a second aspect, an embodiment of the present application provides a merchant positioning device, the device comprising:
[0049] a first acquisition module, configured to acquire a plurality of first spatiotemporal trajectory segments corresponding to a first merchant, wherein the first spatiotemporal trajectory segments include a plurality of first trajectory nodes, wherein the plurality of first trajectory nodes include a first merchant node and at least one first reference location node, wherein the first reference location node includes a first location and a first time when a user is located at the first location, and the first merchant node includes a second time when the user conducts a transaction with the first merchant;
[0050] An execution module is configured to execute, for each of the first spatiotemporal trajectory segments, respectively: obtaining a moving distance of the user within a target duration corresponding to the first spatiotemporal trajectory segment; determining a first area where the first location is located according to the moving distance and its corresponding first location; and determining the target duration according to the first moment and the second moment;
[0051] A first determining module, configured to determine a target area where the first merchant is located according to a relative position relationship of a plurality of the first areas;
[0052] The second determining module is used to determine the location information of the target area as the location information of the first merchant.
[0053] In a third aspect, an embodiment of the present application provides an electronic device, the device comprising: a processor and a memory storing computer program instructions;
[0054] When the processor executes the computer program instructions, the processor implements any possible implementation method of the first aspect described above.
[0055] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implements a method in any possible implementation method of the first aspect described above.
[0056] In a fifth aspect, an embodiment of the present application provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes a method as any possible implementation method in the first aspect above.
[0057] In the merchant positioning method, device, equipment, computer-readable storage medium and computer program product of the embodiment of the present application, the first spatiotemporal trajectory segment can characterize the association relationship between the first reference location node and the first merchant. By executing respectively for multiple first spatiotemporal trajectory segments corresponding to the first merchant: determining the target duration according to the first moment corresponding to the first reference location node and the second moment corresponding to the first merchant node in the first spatiotemporal trajectory segment, obtaining the user's moving distance within the target duration, and determining the first area where the first location is located according to the moving distance and its corresponding first position, so that the first area can include the first merchant, and then multiple candidate areas where the first merchant may be located can be determined. In this way, by determining the target area where the first merchant is located according to the relative position relationship between multiple first areas, and determining the location information of the first merchant according to the location information corresponding to the target area, the known location information and the association relationship between the first reference location node and the first merchant can be fully utilized to locate the first merchant, which not only ensures the comprehensiveness of obtaining the merchant location information, but also ensures the efficiency of obtaining the merchant location information. BRIEF DESCRIPTION OF THE DRAWINGS
[0058] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0059] Figure 1 It is a flowchart of a merchant positioning method provided in an embodiment of the present application;
[0060] Figure 2 is a schematic diagram of determining a target area where a first merchant is located according to a relative position relationship of a plurality of first areas provided in an embodiment of the present application;
[0061] Figure 3 It is a flowchart of another merchant positioning method provided in an embodiment of the present application;
[0062] Figure 4 It is a flowchart of another merchant positioning method provided in an embodiment of the present application;
[0063] Figure 5 is a structural schematic diagram of a merchant positioning device provided in an embodiment of the present application;
[0064] Figure 6 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0065] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.
[0066] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article 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, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0067] As described in the background technology section, there are currently various ways to locate merchants. If the merchant location information is specially collected by purchasing service providers in order to ensure the comprehensiveness of the merchant location information, the efficiency of information collection cannot be guaranteed. If the merchant location information is obtained through a merchant terminal with a positioning function in the merchant or the merchant location information is identified through the navigation path data of the courier or takeaway in order to improve the efficiency of obtaining the merchant location information, it cannot be guaranteed that all the merchant location information is obtained. Therefore, the current merchant positioning methods cannot achieve both the comprehensiveness of the merchant location information and the efficiency of obtaining the merchant location information.
[0068] Thus, in order to solve the problems of the prior art, the embodiments of the present application provide a merchant positioning method, device, equipment, computer-readable storage medium and computer program product. Among them, the merchant positioning method can be applied to the scenario of positioning transaction-intensive offline merchants. Transaction-intensive offline merchants can be merchants in transaction-intensive areas such as business districts, snack streets or residential areas.
[0069] The following first introduces the merchant locating method provided in the embodiment of the present application.
[0070] Figure 1FIG. 1 is a flow chart of a merchant location method provided in an embodiment of the present application. The merchant location method can be executed by a processor in a terminal device or a cloud server. Figure 1 As shown, the merchant positioning method provided in the embodiment of the present application includes the following steps:
[0071] S110, acquiring a plurality of first spatiotemporal trajectory segments corresponding to a first merchant, the first spatiotemporal trajectory segments comprising a plurality of first trajectory nodes, the plurality of first trajectory nodes comprising a first merchant node and at least one first reference location node, the first reference location node comprising a first location and a first moment when the user is located at the first location, and the first merchant node comprising a second moment when the user conducts a transaction with the first merchant;
[0072] S120, for each first spatiotemporal trajectory segment, respectively executing: obtaining a moving distance of the user within a target duration corresponding to the first spatiotemporal trajectory segment; determining a first area where the first location is located according to the moving distance and its corresponding first location; and determining the target duration according to the first moment and the second moment;
[0073] S130, determining a target area where the first merchant is located according to a relative position relationship of a plurality of first areas;
[0074] S140: Determine the location information of the target area as the location information of the first merchant.
[0075] In the merchant positioning method of the embodiment of the present application, the first spatiotemporal trajectory segment can characterize the association relationship between the first reference position node and the first merchant. By executing respectively for multiple first spatiotemporal trajectory segments corresponding to the first merchant: determining the target duration according to the first moment corresponding to the first reference position node and the second moment corresponding to the first merchant node in the first spatiotemporal trajectory segment, obtaining the user's moving distance within the target duration, and determining the first area where the first position is located according to the moving distance and its corresponding first position, so that the first area can include the first merchant, and then multiple candidate areas where the first merchant may be located can be determined. In this way, by determining the target area where the first merchant is located according to the relative position relationship between multiple first areas, and determining the location information of the first merchant based on the location information corresponding to the target area, the known location information and the association relationship between the first reference position node and the first merchant can be fully utilized to locate the first merchant, which ensures both the comprehensiveness of obtaining the merchant location information and the efficiency of obtaining the merchant location information.
[0076] The specific implementation methods of the above steps are introduced below.
[0077] In some embodiments, in S110, the first spatiotemporal trajectory segment may represent a user trajectory of a user starting from a first location at a first moment, moving toward a first merchant, and conducting a transaction with the first merchant at a second moment. Among them, multiple first spatiotemporal trajectory segments may correspond to one user or multiple users, which is not limited here. Multiple first spatiotemporal trajectory segments corresponding to different users may be the same or different. Multiple first spatiotemporal trajectory segments corresponding to the same user may be the same or different.
[0078] In addition, the first location may include, for example, a location where a second merchant is located or a residential location. The second merchant may be different from the first merchant. Specifically, if the first merchant is located in a business district or a snack street, the first location may be a second location where a second merchant different from the first merchant is located in the business district or snack street; if the first merchant is located in a residential area, the first location may be a residential location of a residence in the residential area.
[0079] In addition, the first spatiotemporal trajectory segment may include multiple first trajectory nodes. The multiple first trajectory nodes may include one or more first reference location nodes. Each first reference location node may include the first location described above and the first moment when the user is at the first location. The first location and the first moment corresponding to different first reference location nodes may be different. In addition, the multiple first trajectory nodes may also include a first merchant node corresponding to the first merchant, and the first merchant node may include the second moment when the user conducts a transaction with the first merchant.
[0080] Based on this, in order to improve the accuracy of merchant positioning, in some embodiments, the above S110 may specifically include:
[0081] Acquire spatiotemporal trajectory information corresponding to a plurality of users respectively, the spatiotemporal trajectory information including a plurality of trajectory nodes;
[0082] Move the sliding window according to a preset step size to divide the spatiotemporal trajectory corresponding to each spatiotemporal trajectory information into multiple spatiotemporal trajectory segments;
[0083] Among the multiple spatiotemporal trajectory segments, multiple first spatiotemporal trajectory segments including the first reference location node and the first merchant node are screened out.
[0084] Here, each user may correspond to a space-time trajectory information. Each space-time trajectory information may include the space-time trajectory of the user moving within a preset duration. The preset duration may be, for example, one day, one week, one month, two months, half a year, etc., which is not limited here. Each space-time trajectory information may include multiple trajectory nodes, and the multiple trajectory nodes may include the multiple first reference location nodes and multiple first merchant nodes described above. That is, the multiple trajectory nodes may include multiple first trajectory nodes.
[0085] As an example, a user set including multiple users can be denoted as U <u1,u2,u3,...,u n >. Among them, u i It can represent the i-th user, and the value of i can range from 1 to n. The space-time trajectory corresponding to each user can be recorded as ut i <(t i1 ,m i1 ),(t i2 ,m i2 ),...,(t ik ,m ik )>. (t ij ,m ij ) can be a trajectory node, indicating that user i stops at the jth reference location m at the jth time point t. Among them, the value of j can be from 1 to k. The location information of the jth reference location m may be known or unknown, which is not limited here. The jth reference location m may, for example, include the location corresponding to the first reference location node, the location corresponding to the second reference location node, and the first merchant. If the jth reference location m is a merchant, the jth time point t can represent the time point when the user trades with the merchant.
[0086] In addition, the length of the sliding window can be recorded as M, which can be, for example, 2, 3, 4, etc. The preset step size can be recorded as D, which can be, for example, 1, 2, 3, etc. When M is set to 2 and D is set to 1, the spatiotemporal trajectory ut can be i <(t i1 ,m i1 ),(t i2 ,m i2 ),...,(t ik ,m ik )> divided into multiple space-time trajectory segments uts i <{(t i1 ,m i1 ),(t i2 ,m i2 )},{(t i2 ,m i2 ),(t i3 ,m i3 )},...{(t ik-1 , m ik-1 ),(t ik ,m ik )}>.
[0087] Among the multiple spatiotemporal trajectory segments, if the spatiotemporal trajectory segment includes both the first merchant node and the first reference position node, the spatiotemporal trajectory segment may be determined as the first spatiotemporal trajectory segment corresponding to the first merchant.
[0088] In this way, by first obtaining the spatiotemporal trajectory information corresponding to multiple users, and then determining multiple first spatiotemporal trajectory segments based on the spatiotemporal trajectory information, that is, obtaining multiple first spatiotemporal trajectory segments based on big data technology, the diversity of the multiple first spatiotemporal trajectory segments can be guaranteed, thereby ensuring the accuracy of subsequent merchant positioning based on the multiple first spatiotemporal trajectory segments.
[0089] In some embodiments, in S120 , the second moment may be later than the first moment, and the target duration may be a time period between the second moment and the first moment.
[0090] As an example, for the first spatiotemporal trajectory segment {(t k , m k ),(t k+1 ,m k+1 )},(t k , m k ) can be the first reference location node, (t k+1 ,m k+1 ) can be the first merchant node, t k It can be the first moment, t k+1 It can be the second moment. k It can represent the first position. The position information of the first position is known and can be recorded as P k <lat k ,lng k >. m k+1 Can represent the first merchant.
[0091] In order to accurately determine the moving distance of the user from the first moment to the second moment, in some embodiments, obtaining the moving distance of the user within the target duration corresponding to the first spatiotemporal trajectory segment may specifically include:
[0092] Obtaining a moving speed of the user within a target duration corresponding to the first spatiotemporal trajectory segment;
[0093] Determine the moving distance based on the moving speed and target duration.
[0094] Here, if the moving speed is recorded as V k , and the moving distance is recorded as S k , the moving distance can be determined by the following formula (1):
[0095] S k= V k (t k+1 -t k ) (1)
[0096] In formula (1), V k The unit is meter / second, S k The unit is meter, tk and t k+1 The unit is seconds.
[0097] As an example, if the user corresponding to the first spatiotemporal trajectory segment carries an electronic device that can be used to monitor the user's speed (such as a mobile phone, a sports bracelet, etc.), the average moving speed of the user in a preset time period can be obtained through the electronic device, and the average moving speed is determined as the moving speed of the user in the preset time period. The moving speed obtained based on this method has high usability, can ensure the accuracy of the obtained moving speed, and then accurately determine the moving distance of the user from the first moment to the second moment.
[0098] However, if some users do not carry an electronic device that can be used to monitor the user's speed, the moving speed may not be obtained through the above method.
[0099] In actual situations, the movement speeds of users in similar scenes are usually similar. Similar scenes may include the same starting position and similar starting time of the user's movement. Therefore, in order to ensure that the movement speed can be obtained, the reference movement speed of the user in similar scenes can be obtained first, and then the reference movement speed in the similar scenes can be determined as the movement speed of the user in the target duration corresponding to the first spatiotemporal trajectory segment.
[0100] Based on this, in some embodiments, the above-mentioned obtaining of the moving speed of the user within the target duration corresponding to the first spatiotemporal trajectory segment may specifically include:
[0101] Acquire a plurality of second spatiotemporal trajectory segments, the second spatiotemporal trajectory segments include a plurality of second trajectory nodes, the plurality of second trajectory nodes include a second reference position node and a third reference position node, the second reference position node includes the first position and a third moment when the user is located at the first position, and the third reference position node includes the second position and a fourth moment when the user is located at the second position;
[0102] When the reference duration is less than the first preset threshold, the moving speed is determined according to the third moment, the fourth moment, the first position and the second position, and the reference duration is the duration between the first moment and the third moment.
[0103] Here, the plurality of spatiotemporal trajectory segments may further include a plurality of second spatiotemporal trajectory segments. The second spatiotemporal trajectory segment may represent a user trajectory of a user starting from a first location at a third time, moving toward a second location, and being located at the second location at a fourth time. The second location may include, for example, a location of a third merchant or a residential location. The third merchant may be different from the first merchant.
[0104] As an example, after obtaining multiple spatiotemporal trajectory segments, the multiple spatiotemporal trajectory segments can be screened based on the position information, and the spatiotemporal trajectory segment including both the second reference position node and the third reference position node is determined as the second spatiotemporal trajectory segment.
[0105] In addition, the third moment may be later than the first moment or earlier than the first moment, which is not limited here. The duration between the first moment and the third moment may be recorded as a reference duration. The first preset threshold may be a preset duration threshold for distinguishing whether the starting moments of users starting from the same location are similar.
[0106] As an example, if the reference duration is less than the first preset threshold, it can be determined that the starting time of the users starting from the same location is close, and then the reference moving speed corresponding to the second space-time trajectory segment can be calculated.
[0107] Exemplarily, the moving speed can be determined according to the third moment, the fourth moment, the first position and the second position as shown in the following formula (2):
[0108]
[0109] In formula (2), V k Can represent the moving speed, V j Can represent the reference moving speed, P j can represent the position information corresponding to the first position, P j+1 can represent the position information corresponding to the second position, t j The third moment of the position information corresponding to the first position can be represented by t j+1 It can represent the fourth moment.
[0110] In this way, by first obtaining the reference moving speed of the user in similar scenes based on big data information, and then determining the reference moving speed in similar scenes as the moving speed of the user within the target duration corresponding to the first space-time trajectory segment, it is possible to ensure that the moving speed is obtained.
[0111] In addition, in actual situations, the user's moving speed may be related to the user's own attribute information, the first merchant's attribute information, the first reference location node's attribute information, and the user's environmental information when moving from the first location to the first merchant.
[0112] Therefore, in order to improve the accuracy of the moving speed, in some embodiments, the above-mentioned obtaining of the moving speed of the user within the target duration corresponding to the first spatiotemporal trajectory segment may specifically include:
[0113] Acquire first environmental feature information corresponding to the first spatiotemporal trajectory segment, first attribute information of a first reference location node in the first spatiotemporal trajectory segment, second attribute information of a first merchant in the first spatiotemporal trajectory segment, and third attribute information of a user who transacts with the first merchant;
[0114] A speed prediction model is used to perform speed prediction based on the first attribute information, the second attribute information, the third attribute information and the first environmental feature information to obtain a moving speed. The speed prediction model is trained with a first target information sample corresponding to the spatiotemporal trajectory segment sample as input and a moving speed sample as output. The first target information sample includes a first environmental feature information sample corresponding to the spatiotemporal trajectory segment sample, a first attribute information sample of a reference position node sample in the spatiotemporal trajectory segment sample, a second attribute information sample of a first merchant sample in the spatiotemporal trajectory segment sample, and a third attribute information sample of a user who transacts with the first merchant sample.
[0115] Here, the first environmental feature information corresponding to the first spatiotemporal trajectory segment may represent the environmental information when the user moves from the first location to the first merchant. Environmental information may include weather information, traffic information, light intensity, etc. Among them, weather information may include, for example, sunny days, cloudy days, rainy days, etc. The first attribute information may include type information of the first location (such as residence, merchant, etc.). If the first location is the location corresponding to the merchant, the first attribute information may also include type information of the merchant. The second attribute information may include type information of the first merchant, and time information of the transaction between the user and the first merchant. The third attribute information may include attribute information such as the user's gender, age, and physical condition.
[0116] In addition, the speed prediction model may be a regression prediction model for speed prediction, and the regression prediction model may be a neural network model.
[0117] In order to obtain a speed prediction model that can be used for speed prediction, the first target information sample and the moving speed sample corresponding to the spatiotemporal trajectory segment sample can be first obtained, and then the model training is performed based on the first target information sample and its corresponding moving speed sample. Among them, the spatiotemporal trajectory segment sample may include multiple trajectory node samples, and the multiple trajectory node samples may include reference position node samples and first merchant samples. The first target information sample may include the first environmental feature information sample corresponding to the spatiotemporal trajectory segment sample, the first attribute information sample of the reference position node sample in the spatiotemporal trajectory segment sample, the second attribute information sample of the first merchant sample in the spatiotemporal trajectory segment sample, and the third attribute information sample of the user who trades with the first merchant sample. Among them, the first environmental feature information sample may represent the environmental information when the user moves from the position corresponding to the reference position node sample to the position corresponding to the first merchant sample. The first attribute information sample may include the type information of the position corresponding to the reference position node sample (such as residence, merchant, etc.). The second attribute information sample may include the type information of the first merchant sample, and the time information of the user trading with the first merchant sample. The third attribute information sample may include attribute information such as the user's gender, age, and physical condition.
[0118] The embodiment of the present application uses a speed prediction model to perform speed prediction based on the first attribute information, the second attribute information, the third attribute information and the first environmental feature information to obtain the moving speed, thereby improving the accuracy of the moving speed.
[0119] In addition, in actual situations, there is uncertainty in user transactions, and some users (such as office workers who need to take the subway, bus and other means of transportation) move long distances in a short period of time. Therefore, if the target duration is too long, the user may switch to another means of transportation, thereby reducing the accuracy of the above movement speed and the accuracy of the above movement distance.
[0120] Therefore, in order to ensure the accuracy of the moving distance, in some embodiments, the target duration can be limited to less than a third preset threshold, and the third preset threshold can be determined according to a preset range and a preset moving speed. The preset range can be a regional range where transaction-intensive offline merchants such as business districts, snack streets, and residential areas are located. The preset moving speed can be the user's walking speed. In addition, the third preset threshold can be, for example, 10 minutes.
[0121] As an example, after obtaining multiple first space-time trajectory segments, the first space-time trajectory segments can also be screened based on the size relationship between the target duration and the third preset threshold, to determine the first space-time trajectory segments whose target duration is less than the third preset threshold, and then calculate the moving distance for each first space-time trajectory segment.
[0122] It should be noted that if the value of the third preset threshold is larger, there are more first spatiotemporal trajectory segments that meet the conditions, so the moving distance calculated based on the first spatiotemporal trajectory segments may be less accurate, affecting the accuracy of positioning the first merchant. If the value of the third preset threshold is smaller, there are fewer first spatiotemporal trajectory segments that meet the conditions, but the moving distance calculated based on the first spatiotemporal trajectory segments is more accurate, and the accuracy of positioning the first merchant is higher.
[0123] In addition, after arriving at the first merchant, users often make purchases before transacting with the first merchant. k+1 The time is the payment transaction time, not the store arrival time, which leads to t k+1 -t k The time taken to move the data exceeds the actual time the user moves, resulting in the moving distance being larger than the distance between the first location and the first merchant.
[0124] Therefore, in order to further improve the accuracy of the moving distance, in some embodiments, before obtaining the moving distance of the user within the target duration, the method may further include:
[0125] Obtain the shopping time that the user spends shopping in the first merchant;
[0126] The target duration is determined based on the first moment, the second moment and the shopping duration.
[0127] If the shopping time is recorded as t mci , let the first moment be t k The second moment is t k+1 , the target duration is recorded as t, then the target duration can be calculated by the following formula (3):
[0128] t= t k+1 -t mci -t k (3)
[0129] Based on this, the S k Can be corrected to: S k= V k (t k+1 -t mci -t k ).
[0130] In this way, by taking the shopping duration into consideration when calculating the target duration, the accuracy of the moving distance can be further improved.
[0131] Based on this, in order to ensure the accuracy of the shopping duration and further accurately determine the moving distance of the user from the first moment to the second moment, in some embodiments, the above-mentioned acquisition of the shopping duration of the user in the first merchant may specifically include:
[0132] Monitor the user's moving speed and obtain monitoring results;
[0133] If the monitoring result indicates that the moving speed of the user is less than the second preset threshold, recording the fourth moment;
[0134] Obtain the fifth moment when the user conducts a transaction at the first merchant;
[0135] When the fourth moment is before the fifth moment and the moving speed between the fourth moment and the fifth moment is continuously less than the second preset threshold, the shopping duration is determined according to the fourth moment and the fifth moment.
[0136] If the user carries an electronic device that can be used to monitor the user's speed (such as a mobile phone, a sports bracelet, etc.), the user's moving speed can be monitored by the electronic device to obtain a monitoring result. The monitoring result may include the moving speed.
[0137] Generally, the speed of a user walking on the road is often greater than the speed of the user shopping in a store, so the second preset threshold can be a preset speed threshold for distinguishing whether the user is walking or shopping. If the user's moving speed is monitored to be less than the second preset threshold, it can be determined that the user has entered the store to start shopping, and the fourth moment when the user enters the store is recorded.
[0138] In addition, if the user conducts a transaction with the first merchant, the fifth time when the transaction occurs can be determined through the transaction message.
[0139] In order to accurately determine whether the merchant that the user is shopping at is the first merchant, the moving speed between the fourth moment and the fifth moment can be continuously monitored. If the moving speed is continuously less than the second preset threshold, it can be indicated that the user has been shopping at the first merchant until the transaction is paid. Therefore, the time between the fourth moment and the fifth moment can be determined as the shopping time.
[0140] The embodiment of the present application has high usability by determining the shopping duration based on the moving speed, and can ensure the accuracy of the shopping duration, thereby accurately determining the moving distance of the user from the first moment to the second moment.
[0141] However, if some users do not carry electronic devices that can be used to monitor user speed, the purchase time may not be obtained through the above method.
[0142] Based on this, in order to ensure that the shopping time can be obtained, in some embodiments, the above-mentioned obtaining of the shopping time of the user in the first merchant may specifically include:
[0143] Get the target merchant type of the first merchant;
[0144] According to the correspondence between the merchant type and the shopping time, the shopping time corresponding to the target merchant type is determined.
[0145] In actual situations, the merchant type and shopping time are closely related. For example, the shopping time of fast food restaurants and milk tea shops without dine-in service can be divided into a few minutes. However, for merchants such as supermarkets with a large business scope, the shopping time can often reach more than 20 minutes. Therefore, combined with expert experience, a corresponding relationship between merchant type and shopping time can be constructed, and then the shopping time corresponding to the target merchant type can be determined based on the corresponding relationship.
[0146] In addition, in actual situations, the user's shopping time may be strongly correlated with the user's own attribute information, the first merchant's attribute information, and the environment information of the first merchant.
[0147] Therefore, in order to improve the accuracy of the shopping time, in some embodiments, the above-mentioned acquisition of the shopping time of the user in the first merchant may specifically include:
[0148] Acquire second environmental feature information corresponding to the first merchant, fourth attribute information of a user shopping in the first merchant, and fifth attribute information of the first merchant;
[0149] The duration prediction model is used to predict the shopping duration based on the fourth attribute information, the fifth attribute information and the second environmental characteristic information to obtain the shopping duration of the user in the first merchant. The duration prediction model takes the second target information sample corresponding to the second merchant sample as input and the shopping duration sample of the user in the second merchant sample as output for model training. The second target information sample includes the second environmental characteristic information sample corresponding to the second merchant sample, the fourth attribute information sample corresponding to the user shopping in the second merchant sample, and the fifth attribute information sample corresponding to the second merchant sample.
[0150] Here, the second environmental characteristic information corresponding to the first merchant may represent the environmental information when the user is shopping in the first merchant. The environmental information may include weather information, the queue market when the user is trading in the first merchant, etc. Among them, the weather information may include, for example, sunny days, cloudy days, rainy days, etc. The fourth attribute information may include attribute information such as the user's gender, age, physical condition, shopping preferences, etc. The fifth attribute information may include the type information of the first merchant.
[0151] In addition, the duration prediction model may be a regression prediction model for duration prediction, and the regression prediction model may be a neural network model.
[0152] In order to obtain a speed prediction model that can be used for duration prediction, the second target information sample corresponding to the second merchant sample and the purchase duration sample of the user in the second merchant sample can be first obtained, and then the model training is performed based on the second target information sample and its corresponding purchase duration sample. Among them, the second target information sample may include the second environmental feature information sample corresponding to the second merchant sample, the fourth attribute information sample corresponding to the user who purchases in the second merchant sample, and the fifth attribute information sample corresponding to the second merchant sample. Among them, the second environmental feature information sample can represent the environmental information when the user purchases in the second merchant sample. The environmental information may include weather information, the queue market when the user trades in the first merchant, etc. Among them, the weather information may include, for example, sunny days, cloudy days, rainy days, etc. The fourth attribute information sample may include attribute information such as the user's gender, age, physical condition, and purchase preferences. The fifth attribute information sample may include type information of the second merchant sample.
[0153] The embodiment of the present application uses a duration prediction model to predict the shopping duration based on the fourth attribute information, the fifth attribute information and the second environmental feature information, and obtains the shopping duration of the user in the first merchant, which can improve the accuracy of the shopping duration.
[0154] It should be noted that if the first spatiotemporal trajectory segment includes multiple first reference location nodes, the moving distance can be calculated once based on each first reference location node and the first merchant node to obtain multiple moving distances corresponding to the first spatiotemporal trajectory segment.
[0155] After determining at least one moving distance corresponding to each first spatiotemporal trajectory segment, a first area where the first location is located can be determined for each moving distance according to the moving distance and its corresponding first location. The first area can generally include a first merchant. There can be an intersection area between multiple first areas.
[0156] As an example, the first area can be a circle, a rectangle, a square, etc., which is not limited here. After determining multiple moving distances, the moving distance can be used as a radius, and a circle can be drawn with the first position corresponding to the moving distance as the center to obtain multiple circular first areas.
[0157] In some embodiments, in S130, there may be one intersection area or multiple intersection areas among multiple first areas. If there is one intersection area among multiple first areas, the intersection area can be determined as the target area where the first merchant is located. If there are multiple intersection areas among multiple first areas, the multiple intersection areas can be further screened to determine the target area. Specifically, the target area can be determined based on the number of first areas corresponding to the multiple intersection areas. For example, if three first areas jointly cover the first intersection area, and three first areas jointly cover the second intersection area, the second intersection area can be determined as the target area.
[0158] A schematic diagram of determining a target area where a first merchant is located according to a relative position relationship of a plurality of first areas provided in an embodiment of the present application can be as follows: Figure 2 shown.
[0159] In some embodiments, in S140, the location information of the target area may be known. After the target area is determined, the location information of the target area may be determined as the location information of the first merchant.
[0160] In addition, in order to further improve the accuracy of merchant positioning, as another implementation method of the present application, the present application also provides another implementation method of the merchant positioning method, please refer to the following embodiments for details.
[0161] See also Figure 3 The merchant locating method provided in the embodiment of the present application may further include the following steps before S130 shown in the above embodiment:
[0162] S310, dividing the second area where the first merchant is located into grids to obtain a plurality of grids, wherein the second area at least includes the first area.
[0163] Here, the second area may be, for example, the city where the first merchant is located. By dividing the second area into grids, it is convenient to subsequently locate the grid to which the merchant belongs.
[0164] As an example, the city is divided into N rectangular grids according to rectangles, and each small grid is L meters long and W meters wide, where N, L, and W can be customized according to actual conditions. For example, the second area can be divided into 10,000 rectangular grids, each of which is 1420 meters long and 1326 meters wide. A finer-grained division can also be implemented, such as dividing it into blocks with a length and width of about 500 meters. If the transaction data is extremely rich and the availability of the first space-time trajectory fragment is high, a fine-grained boundary division method can be used, and L and W can even be at the 10-meter level. Among them, the smaller the grid, the higher the accuracy of merchant positioning can be.
[0165] Based on this, the above S130 may specifically include:
[0166] S131, obtaining a first probability that a first merchant is located in each grid in a plurality of first areas.
[0167] Here, the probabilities of multiple grids in the same first area may be the same. The probabilities of grids in different first areas may be the same or different. The first probability may be the probability corresponding to each grid. If the grid belongs to one first area, the probability of the grid in the first area may be the first probability. If the grid belongs to multiple first areas, the probability of the grid in the multiple first areas may be the first probability.
[0168] Based on this, in order to accurately determine the first probability, in some embodiments, the obtaining of the first probability corresponding to each grid in the plurality of first areas may specifically include:
[0169] For each grid in each first area, calculating a second probability according to the target duration;
[0170] In the case where the grid belongs to a first region, determining the second probability corresponding to the grid in the first region as the first probability;
[0171] In the case where the grid belongs to a plurality of first regions, the sum of the second probabilities respectively corresponding to the plurality of first regions is determined as the first probability.
[0172] In actual situations, if the time difference between when the user is at the first location and when the user conducts a transaction with the first merchant is shorter, it means that the user's movement distance is smaller and the credibility of the first area is higher; if the time difference between when the user is at the first location and when the user conducts a transaction with the first merchant is longer, variables are more likely to occur, thereby reducing the credibility of the first area.
[0173] Therefore, in order to accurately determine the second probability of the grid in each first area, the second probability can be calculated according to the target duration. k The method can be shown as follows:
[0174]
[0175] In formula (4), t k+1 ,t mci ,t k The unit can be minutes.
[0176] In the case where the grid belongs to multiple first areas, the first probability TPo can be calculated by the following formula (5):
[0177] TPo=∑Po k (5)
[0178] In this way, by calculating the second probability according to the target duration, the rationality of the second probability can be guaranteed, thereby ensuring the accuracy of the first probability.
[0179] S132: Determine at least one grid corresponding to a maximum value among the multiple first probabilities as a target area.
[0180] As an example, if the maximum value of the first probability corresponds to a grid, and the maximum value is much higher than the other first probabilities (such as 2-3 times the other first probabilities), the grid corresponding to the maximum value can be directly determined as the target area. If there are fewer first spatiotemporal trajectory segments, the maximum value of the first probability corresponds to a grid, and the maximum value is not much different from the other first probabilities, then the grids corresponding to the B larger first probabilities can be determined as the target area.
[0181] As another example, if the maximum value of the first probability corresponds to multiple grids, the multiple grids may be determined as the target area.
[0182] In addition, the other steps of the method in the embodiment of the present application can be seen above Figure 1 The relevant description of the illustrated embodiment will not be repeated here.
[0183] The embodiment of the present application divides the second area into grids to obtain multiple grids, and determines the target area based on the grids, which can further improve the accuracy of determining the target area and further improve the accuracy of merchant positioning.
[0184] In order to better describe the entire solution, some specific examples are given based on the above embodiments.
[0185] For example, Figure 4 As shown, the embodiment of the present application may include the following steps:
[0186] S41, dividing the city where the first merchant is located into grids to obtain multiple grids;
[0187] S42, obtaining a plurality of first spatiotemporal trajectory segments corresponding to the first merchant;
[0188] S43, for each first space-time trajectory segment, draw a circle with the first position as the center and the moving distance as the radius, to obtain at least one first area corresponding to each first space-time trajectory segment;
[0189] S44, determining a target area where the first merchant is located according to the probability of each grid in each first area;
[0190] S45: Determine the location information of the target area as the location information of the first merchant.
[0191] The embodiment of the present application combines the first spatiotemporal trajectory segment and the first position of the known position information, draws a circle with the first position as the center and the user's moving distance as the radius, and based on the intersection of multiple circles, can accurately identify the area to which the merchant belongs. Compared with the existing method, the user's moving distance is taken into consideration, which is more accurate.
[0192] Based on the merchant positioning method provided in the above embodiment, the present application also provides a specific implementation of a merchant positioning device. Please refer to the following embodiment.
[0193] like Figure 5 As shown, the merchant positioning device 500 provided in the embodiment of the present application includes the following modules:
[0194] A first acquisition module 510 is used to acquire a plurality of first spatiotemporal trajectory segments corresponding to a first merchant, the first spatiotemporal trajectory segments including a plurality of first trajectory nodes, the plurality of first trajectory nodes including a first merchant node and at least one first reference location node, the first reference location node including a first location and a first moment when the user is located at the first location, and the first merchant node including a second moment when the user conducts a transaction with the first merchant;
[0195] The execution module 520 is used to respectively execute, for each first spatiotemporal trajectory segment: obtaining a moving distance of the user within a target duration corresponding to the first spatiotemporal trajectory segment; determining a first area where the first location is located according to the moving distance and its corresponding first location; and determining the target duration according to the first moment and the second moment;
[0196] A first determination module 530, configured to determine a target area where the first merchant is located according to a relative position relationship of a plurality of first areas;
[0197] The second determining module 540 is configured to determine the location information of the target area as the location information of the first merchant.
[0198] The above merchant positioning device 500 is described in detail below, as shown below:
[0199] In some embodiments, the first acquisition module 510 may specifically include:
[0200] A first acquisition submodule is used to acquire spatiotemporal trajectory information corresponding to a plurality of users respectively, where the spatiotemporal trajectory information includes a plurality of trajectory nodes;
[0201] A division submodule is used to move the sliding window according to a preset step size to divide the space-time trajectory corresponding to each space-time trajectory information into multiple space-time trajectory segments;
[0202] The screening submodule is used to screen out a plurality of first spatiotemporal trajectory segments including a first reference location node and a first merchant node from the plurality of spatiotemporal trajectory segments.
[0203] In some embodiments, the execution module 520 may specifically include:
[0204] The second acquisition submodule is used to acquire the moving speed of the user within the target duration corresponding to the first spatiotemporal trajectory segment;
[0205] The first determination submodule is used to determine the moving distance according to the moving speed and the target duration.
[0206] In some embodiments, the second acquisition submodule may specifically include:
[0207] a first acquisition unit, configured to acquire a plurality of second spatiotemporal trajectory segments, the second spatiotemporal trajectory segments comprising a plurality of second trajectory nodes, the plurality of second trajectory nodes comprising a second reference position node and a third reference position node, the second reference position node comprising a first position and a third moment when the user is located at the first position, and the third reference position node comprising a second position and a fourth moment when the user is located at the second position;
[0208] The first determining unit is used to determine the moving speed according to the third moment, the fourth moment, the first position and the second position when the reference time is less than a first preset threshold, and the reference time is the time between the first moment and the third moment.
[0209] In some embodiments, the second acquisition submodule may specifically include:
[0210] A second acquisition unit is used to acquire first environmental feature information corresponding to the first spatiotemporal trajectory segment, first attribute information of a first reference location node in the first spatiotemporal trajectory segment, second attribute information of a first merchant in the first spatiotemporal trajectory segment, and third attribute information of a user who transacts with the first merchant;
[0211] The prediction unit is used to use a speed prediction model to perform speed prediction based on the first attribute information, the second attribute information, the third attribute information and the first environmental feature information to obtain a moving speed. The speed prediction model is obtained by taking the first target information sample corresponding to the spatiotemporal trajectory segment sample as input and the moving speed sample as output for model training. The first target information sample includes the first environmental feature information sample corresponding to the spatiotemporal trajectory segment sample, the first attribute information sample of the reference position node sample in the spatiotemporal trajectory segment sample, the second attribute information sample of the first merchant sample in the spatiotemporal trajectory segment sample, and the third attribute information sample of the user who trades with the first merchant sample.
[0212] In some embodiments, the merchant locating device 500 may further include:
[0213] The division module is used to divide the second area where the first merchant is located into grids to obtain multiple grids before determining the target area where the first merchant is located according to the relative position relationship of multiple first areas, and the second area at least includes the first area.
[0214] Based on this, the first determining module 530 may specifically include:
[0215] A third acquisition submodule is used to acquire a first probability that the first merchant is located in each grid of the plurality of first areas;
[0216] The second determining submodule is used to determine at least one grid corresponding to the maximum value among the multiple first probabilities as the target area.
[0217] In some embodiments, the third acquisition submodule may specifically include:
[0218] A calculation unit, configured to calculate a second probability according to a target duration for each grid in each first area;
[0219] A second determining unit is used to determine, when the grid belongs to a first area, a second probability corresponding to the grid in the first area as the first probability;
[0220] The third determining unit is configured to determine, when the grid belongs to a plurality of first regions, a sum of the second probabilities respectively corresponding to the plurality of first regions as the first probability.
[0221] In some embodiments, the merchant locating device 500 may further include:
[0222] A second acquisition module is used to acquire the shopping time of the user in the first merchant before acquiring the moving distance of the user within the target time;
[0223] The third determining module is used to determine the target duration according to the first moment, the second moment and the shopping duration.
[0224] In some embodiments, the second acquisition module may specifically include:
[0225] The monitoring submodule is used to monitor the user's moving speed and obtain monitoring results;
[0226] A recording submodule, configured to record a fourth moment when the monitoring result indicates that the user's moving speed is less than a second preset threshold;
[0227] A fourth acquisition submodule, used to acquire a fifth moment when the user performs a transaction at the first merchant;
[0228] The third determining submodule is used to determine the shopping duration according to the fourth moment and the fifth moment when the fourth moment is before the fifth moment and the moving speed between the fourth moment and the fifth moment is continuously less than the second preset threshold.
[0229] In some embodiments, the second acquisition module may specifically include:
[0230] A fifth acquisition submodule, used to acquire second environmental feature information corresponding to the first merchant, fourth attribute information of the user shopping in the first merchant, and fifth attribute information of the first merchant;
[0231] The prediction submodule is used to use the duration prediction model to predict the shopping duration based on the fourth attribute information, the fifth attribute information and the second environmental feature information to obtain the shopping duration of the user in the first merchant. The duration prediction model takes the second target information sample corresponding to the second merchant sample as input and the shopping duration sample of the user in the second merchant sample as output for model training. The second target information sample includes the second environmental feature information sample corresponding to the second merchant sample, the fourth attribute information sample corresponding to the user shopping in the second merchant sample, and the fifth attribute information sample corresponding to the second merchant sample.
[0232] In some embodiments, the second acquisition module may specifically include:
[0233] A sixth acquisition submodule, used to acquire a target merchant type of the first merchant;
[0234] The fourth determination submodule is used to determine the shopping time corresponding to the target merchant type according to the corresponding relationship between the merchant type and the shopping time.
[0235] In some of the embodiments, the target duration is less than a third preset threshold, and the third preset threshold is determined according to a preset range and a preset moving speed.
[0236] In the merchant positioning device of the embodiment of the present application, the first spatiotemporal trajectory segment can characterize the association relationship between the first reference position node and the first merchant. By executing respectively for the multiple first spatiotemporal trajectory segments corresponding to the first merchant: determining the target duration according to the first moment corresponding to the first reference position node and the second moment corresponding to the first merchant node in the first spatiotemporal trajectory segment, obtaining the user's moving distance within the target duration, and determining the first area where the first position is located according to the moving distance and its corresponding first position, so that the first area can include the first merchant, and then multiple candidate areas where the first merchant may be located can be determined. In this way, by determining the target area where the first merchant is located according to the relative position relationship between multiple first areas, and determining the location information of the first merchant according to the location information corresponding to the target area, the known location information and the association relationship between the first reference position node and the first merchant can be fully utilized to locate the first merchant, which ensures both the comprehensiveness of obtaining the merchant location information and the efficiency of obtaining the merchant location information.
[0237] Based on the merchant locating method provided in the above embodiment, the embodiment of the present application also provides a specific implementation of the electronic device. Figure 6 A schematic diagram of an electronic device 600 provided in an embodiment of the present application is shown.
[0238] The electronic device 600 may include a processor 610 and a memory 620 storing computer program instructions.
[0239] Specifically, the processor 610 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.
[0240] The memory 620 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 620 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 620 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 620 may be inside or outside the electronic device 600. In a particular embodiment, the memory 620 is a non-volatile solid-state memory.
[0241] The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to the first aspect of the present application.
[0242] The processor 610 implements any one of the merchant locating methods in the above embodiments by reading and executing computer program instructions stored in the memory 620 .
[0243] In one example, the electronic device 600 may further include a communication interface 630 and a bus 640. Figure 6 As shown, the processor 610, the memory 620, and the communication interface 630 are connected via a bus 640 and communicate with each other.
[0244] The communication interface 630 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.
[0245] Bus 640 includes hardware, software or both, and the parts of electronic equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 640 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.
[0246] Exemplarily, the electronic device 600 may be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA).
[0247] The electronic device can execute the merchant positioning method in the embodiment of the present application, thereby realizing the combination Figures 1 to 5 The merchant positioning method and device described.
[0248] In addition, in combination with the merchant positioning method in the above embodiment, the embodiment of the present application can provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any merchant positioning method in the above embodiment is implemented.
[0249] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.
[0250] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.
[0251] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.
[0252] The above reference is according to the method of the embodiment of the present application, the flow chart of the device (system) and the computer program product and / or the block diagram described various aspects of the present application.It should be understood that each square box in the flow chart and / or the block diagram and the combination of each square box in the flow chart and / or the block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the realization of the function / action specified in one or more square boxes of the flow chart and / or the block diagram.Such a processor can be but is not limited to a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit.It can also be understood that each square box in the block diagram and / or the flow chart and the combination of the square boxes in the block diagram and / or the flow chart can also be realized by the dedicated hardware that performs the specified function or action, or can be realized by the combination of dedicated hardware and computer instructions.
[0253] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.
Claims
1. A merchant positioning method, characterized in that: include: Acquire a plurality of first spatiotemporal trajectory segments corresponding to a first merchant, the first spatiotemporal trajectory segments comprising a plurality of first trajectory nodes, the plurality of first trajectory nodes comprising a first merchant node and at least one first reference location node, the first reference location node comprising a first location and a first moment when a user is located at the first location, the first merchant node comprising a second moment when the user conducts a transaction with the first merchant; For each of the first spatiotemporal trajectory segments, respectively: obtaining a moving distance of the user within a target duration corresponding to the first spatiotemporal trajectory segment; determining a first area where the first location is located according to the moving distance and its corresponding first location; The target duration is determined according to the first moment and the second moment; Determining a target area where the first merchant is located according to a relative position relationship of a plurality of the first areas; The location information of the target area is determined as the location information of the first merchant.
2. The method according to claim 1, characterized in that: The obtaining of a plurality of first spatiotemporal trajectory segments corresponding to the first merchant includes: Acquire spatiotemporal trajectory information corresponding to a plurality of users respectively, wherein the spatiotemporal trajectory information includes a plurality of trajectory nodes; Moving the sliding window according to a preset step length to divide the space-time trajectory corresponding to each of the space-time trajectory information into a plurality of space-time trajectory segments; Among the multiple spatiotemporal trajectory segments, the multiple first spatiotemporal trajectory segments including the first reference location node and the first merchant node are screened out.
3. The method according to claim 1, characterized in that The obtaining of the moving distance of the user within the target duration corresponding to the first spatiotemporal trajectory segment includes: Obtaining a moving speed of the user within a target duration corresponding to the first spatiotemporal trajectory segment; The moving distance is determined according to the moving speed and the target duration.
4. The method according to claim 3, characterized in that The obtaining of the moving speed of the user within the target duration corresponding to the first spatiotemporal trajectory segment includes: Acquire a plurality of second spatiotemporal trajectory segments, the second spatiotemporal trajectory segments comprising a plurality of second trajectory nodes, the plurality of second trajectory nodes comprising a second reference position node and a third reference position node, the second reference position node comprising the first position and a third moment when the user is located at the first position, the third reference position node comprising the second position and a fourth moment when the user is located at the second position; When the reference duration is less than a first preset threshold, the moving speed is determined according to the third moment, the fourth moment, the first position and the second position, and the reference duration is the duration between the first moment and the third moment.
5. The method according to claim 3, characterized in that: The obtaining of the moving speed of the user within the target duration corresponding to the first spatiotemporal trajectory segment includes: Acquire first environmental feature information corresponding to the first spatiotemporal trajectory segment, first attribute information of the first reference location node in the first spatiotemporal trajectory segment, second attribute information of the first merchant in the first spatiotemporal trajectory segment, and third attribute information of a user who transacts with the first merchant; A speed prediction model is used to perform speed prediction based on the first attribute information, the second attribute information, the third attribute information and the first environmental feature information to obtain the moving speed. The speed prediction model is trained with a first target information sample corresponding to the spatiotemporal trajectory segment sample as input and a moving speed sample as output. The first target information sample includes a first environmental feature information sample corresponding to the spatiotemporal trajectory segment sample, a first attribute information sample of a reference position node sample in the spatiotemporal trajectory segment sample, a second attribute information sample of a first merchant sample in the spatiotemporal trajectory segment sample, and a third attribute information sample of a user who transacts with the first merchant sample.
6. The method according to claim 1, characterized in that Before determining the target area where the first merchant is located according to the relative position relationship of the plurality of first areas, the method further includes: Divide the second area where the first merchant is located into grids to obtain a plurality of grids, wherein the second area at least includes the first area; The determining the target area where the first merchant is located according to the relative position relationship of the plurality of first areas includes: Obtain a first probability that the first merchant is located in each of the grids in the plurality of the first areas; At least one of the grids corresponding to a maximum value among the plurality of the first probabilities is determined as the target area.
7. The method according to claim 6, characterized in that The obtaining of the first probability corresponding to each of the grids in the plurality of the first areas comprises: For each of the grids in each of the first areas, calculating a second probability according to the target duration; In the case where the grid belongs to one of the first regions, determining a second probability corresponding to the grid in the first region as the first probability; In the case that the grid belongs to a plurality of the first regions, the sum of the second probabilities respectively corresponding to the plurality of the first regions is determined as the first probability.
8. The method according to any one of claims 1 to 7, characterized in that: Before obtaining the moving distance of the user within the target duration, the method further includes: Obtaining the shopping time of the user in the first merchant; The target duration is determined according to the first time, the second time and the shopping duration.
9. The method according to claim 8, characterized in that The obtaining of the shopping time of the user in the first merchant includes: Monitoring the moving speed of the user to obtain a monitoring result; If the monitoring result indicates that the moving speed of the user is less than a second preset threshold, recording a fourth moment; Obtaining a fifth moment at which the user conducts a transaction at the first merchant; When the fourth moment is before the fifth moment and the moving speed between the fourth moment and the fifth moment is continuously less than the second preset threshold, the shopping duration is determined according to the fourth moment and the fifth moment.
10. The method according to claim 8, characterized in that The obtaining of the shopping time of the user in the first merchant includes: Acquire second environmental feature information corresponding to the first merchant, fourth attribute information of a user shopping in the first merchant, and fifth attribute information of the first merchant; A duration prediction model is used to predict the shopping duration based on the fourth attribute information, the fifth attribute information and the second environmental characteristic information to obtain the shopping duration of the user in the first merchant. The duration prediction model is trained with the second target information sample corresponding to the second merchant sample as input and the shopping duration sample of the user in the second merchant sample as output. The second target information sample includes the second environmental characteristic information sample corresponding to the second merchant sample, the fourth attribute information sample corresponding to the user shopping in the second merchant sample, and the fifth attribute information sample corresponding to the second merchant sample.
11. The method according to claim 8, characterized in that The obtaining of the shopping time of the user in the first merchant includes: Obtaining the target merchant type of the first merchant; According to the correspondence between the merchant type and the shopping time, the shopping time corresponding to the target merchant type is determined.
12. The method according to any one of claims 1 to 7, characterized in that: The target duration is less than a third preset threshold, and the third preset threshold is determined according to a preset range and a preset moving speed.
13. A merchant positioning device, characterized in that: The device comprises: a first acquisition module, configured to acquire a plurality of first spatiotemporal trajectory segments corresponding to a first merchant, wherein the first spatiotemporal trajectory segments include a plurality of first trajectory nodes, wherein the plurality of first trajectory nodes include a first merchant node and at least one first reference location node, wherein the first reference location node includes a first location and a first time when a user is located at the first location, and the first merchant node includes a second time when the user conducts a transaction with the first merchant; An execution module is configured to execute, for each of the first spatiotemporal trajectory segments, respectively: obtaining a moving distance of the user within a target duration corresponding to the first spatiotemporal trajectory segment; determining a first area where the first location is located according to the moving distance and its corresponding first location; and determining the target duration according to the first moment and the second moment; A first determining module, configured to determine a target area where the first merchant is located according to a relative position relationship of a plurality of the first areas; The second determining module is used to determine the location information of the target area as the location information of the first merchant.
14. An electronic device, characterized in that: The electronic device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the merchant locating method according to any one of claims 1 to 12 is implemented.
15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the merchant locating method according to any one of claims 1 to 12 is implemented.
16. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the merchant locating method according to any one of claims 1 to 12.
Citation Information
Cited By
Position verification method and device, equipment and storage medium
CN120973876A
