A method, device, electronic device and medium for identifying arrival at a store
By using vehicle driving trajectory, driving data, online service behavior and license plate recognition data, combined with machine learning models, the existing in-store identification solutions are solved, and more accurate and economical in-store identification is achieved.
Patent Information
- Application Number
- CN202010567256.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-06-19
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2040-11-15
AI Technical Summary
The existing in-store identification solutions are costly and have poor accuracy, especially in indoor positioning and mobile Internet environments, where GPS positioning signals are weak, ultra-wideband positioning costs are high, inertial positioning is not suitable for mobile use, and Wi-Fi fingerprint positioning requires Large amount of manpower and high cost, and it is difficult to distinguish between resident and passers-by users.
Based on the target user's vehicle driving trajectory data, vehicle driving data, online access service behavior data and license plate identification data, the machine learning model predicts the probability of a user's arrival at the store, and recognizes the user's arrival behavior based on preset thresholds, reducing costs and improving accuracy .
The accuracy of store identification can be improved without the need for additional high-cost equipment, reduce identification costs, and comprehensively predict the probability of users entering the store through multiple data sources, enhancing the accuracy and reliability of identification.
Smart Images

Figure CN111831967B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of data analysis and processing, and in particular to a method, device, electronic device and medium for store arrival recognition. Background Art
[0002] In-store identification is the process of identifying that a user has arrived at a physical store offline. O2O (Online to Offline) refers to combining offline business opportunities with the Internet, making the Internet a platform for offline transactions. The core of O2O is to facilitate transactions between online users and offline goods and services. If the online transaction platform can identify users in offline stores, it can take a lower-cost approach to facilitate users and merchants to complete more transactions.
[0003] Existing solutions generally use positioning technology to identify customers who have visited a store, such as GPS positioning technology, ultra-wideband positioning, inertial positioning, Wi-Fi fingerprint positioning, etc. However, the signal of GPS positioning is weak, and it is difficult to locate indoors due to the obstruction and reflection of walls; ultra-wideband positioning requires the deployment of anchor nodes and bridge nodes at known locations in advance, which is costly; inertial positioning relies on gyroscopes and accelerometers, which cannot be used alone and are not suitable for use on the mobile Internet; Wi-Fi fingerprint positioning requires a large amount of manpower to collect and update the fingerprint library in advance, and does not consider whether the user is in a resident state, so it is easy to identify users passing by the store as arriving at the store. It can be seen that the existing store identification solutions have technical problems such as high cost and poor identification accuracy. Summary of the invention
[0004] In view of this, the purpose of the present application is to provide a method, device, electronic device and medium for in-store identification, which can improve the accuracy of in-store identification of users and reduce the cost of in-store identification.
[0005] According to a first aspect of the present application, a method for store identification is provided, comprising:
[0006] Predicting the probability of the target user arriving at the target store based on at least one of the target user's vehicle driving trajectory data, vehicle driving data, online access service behavior data, and license plate recognition data;
[0007] If the probability that the target user arrives at the target store is greater than a preset threshold, it is identified that the target user arrives at the target store.
[0008] In a possible implementation, predicting the probability of the target user arriving at a target store based on at least one of the target user's vehicle driving trajectory data, vehicle driving data, online access service behavior data, and license plate recognition data includes:
[0009] Predicting a first probability of the target user arriving at the target store based on the vehicle driving trajectory data of the target user;
[0010] Predicting a second probability of the target user arriving at the target store based on the target user's vehicle driving data;
[0011] Predicting a third probability of the target user arriving at the target store based on the target user's online access service behavior data;
[0012] Predicting a fourth probability of the target user arriving at the target store based on the license plate recognition data of the target user;
[0013] Based on at least one of the first probability, the second probability, the third probability and the fourth probability, the probability of the target user arriving at the target store is predicted.
[0014] In a possible implementation, predicting the probability of the target user arriving at the target store based on at least one of the first probability, the second probability, the third probability, and the fourth probability includes:
[0015] Setting weights for the first probability, the second probability, the third probability and the fourth probability respectively;
[0016] Based on at least one of the first probability, the second probability, the third probability and the fourth probability and their corresponding weights, the probability of the target user arriving at the target store is predicted.
[0017] In a possible implementation manner, setting weights for the first probability, the second probability, the third probability, and the fourth probability respectively includes:
[0018] The machine learning model is trained using the reference user's vehicle driving trajectory data, vehicle driving data, online access service behavior data, and license plate recognition data as sample sets;
[0019] The weights corresponding to the first probability, the second probability, the third probability and the fourth probability are fitted based on the trained machine learning model.
[0020] In a possible implementation, predicting a first probability of a target user arriving at a target store based on the vehicle driving trajectory data of the target user includes:
[0021] Based on the vehicle driving trajectory data of the target user and the location of the target store, a first probability of the target user arriving at the target store is predicted.
[0022] In a possible implementation, the vehicle driving data of the target user includes: the difference between the mileage when the target store's service was used last time and the current mileage, the recommended mileage for vehicle maintenance, and at least one of the remaining oil and remaining battery power.
[0023] In a possible implementation, predicting the third probability of the target user arriving at the target store based on the online access service behavior data of the target user includes:
[0024] Based on the online access service behavior data of the target user, at least one of the number of times, click rate and stay time of the target service section of the service requester terminal or the service provider terminal operated by the target user within a preset time period is counted;
[0025] Based on at least one of the statistical number of times, click rate and stay time of the target service section of the service requester terminal or the service provider terminal by the target user within a preset time period, a third probability of the target user arriving at the target store is predicted.
[0026] In a possible implementation, predicting a fourth probability of the target user's arrival based on the target user's license plate recognition data includes:
[0027] Obtain the license plate recognition data obtained by the B-end service system used by the target store after performing license plate recognition on the target user's vehicle;
[0028] A fourth probability of the target user's arrival is predicted based on the target user's license plate recognition data.
[0029] According to a second aspect of the present application, a store arrival identification device is provided, comprising:
[0030] A prediction module, configured to predict the probability of the target user arriving at a target store based on at least one of the target user's vehicle driving trajectory data, vehicle driving data, online access service behavior data, and license plate recognition data;
[0031] The identification module is used to identify that the target user has arrived at the target store if the probability that the target user has arrived at the target store is greater than a preset threshold.
[0032] In a possible implementation, the prediction module includes:
[0033] A first prediction unit, configured to predict a first probability of a target user arriving at a target store based on the vehicle driving trajectory data of the target user;
[0034] A second prediction unit, configured to predict a second probability of the target user arriving at the target store based on the vehicle driving data of the target user;
[0035] A third prediction unit, configured to predict a third probability of the target user arriving at the target store based on the online access service behavior data of the target user;
[0036] a fourth prediction unit, configured to predict a fourth probability that the target user arrives at the target store based on the license plate recognition data of the target user;
[0037] The fifth prediction unit is used to predict the probability of the target user arriving at the target store based on at least one of the first probability, the second probability, the third probability and the fourth probability.
[0038] In a possible implementation manner, the fifth prediction unit is specifically configured to:
[0039] Setting weights for the first probability, the second probability, the third probability and the fourth probability respectively;
[0040] Based on at least one of the first probability, the second probability, the third probability and the fourth probability and their corresponding weights, the probability of the target user arriving at the target store is predicted.
[0041] In a possible implementation manner, the fifth prediction unit is specifically configured to:
[0042] The machine learning model is trained using the reference user's vehicle driving trajectory data, vehicle driving data, online access service behavior data, and license plate recognition data as sample sets;
[0043] The weights corresponding to the first probability, the second probability, the third probability and the fourth probability are fitted based on the trained machine learning model.
[0044] In a possible implementation manner, the first prediction unit is specifically configured to predict a first probability that the target user arrives at the target store based on the vehicle driving trajectory data of the target user and the location of the target store.
[0045] In a possible implementation, the second prediction unit is specifically used to predict the second probability of the target user arriving at the target store based on the target user's vehicle driving data; the target user's vehicle driving data includes: the difference between the mileage when the target store's service was last used and the current mileage, the recommended mileage for vehicle maintenance, and at least one of the remaining fuel and remaining power.
[0046] In a possible implementation manner, the third prediction unit is specifically configured to:
[0047] Based on the online access service behavior data of the target user, at least one of the number of times, click rate and stay time of the target service section of the service requester terminal or the service provider terminal operated by the target user within a preset time period is counted;
[0048] Based on at least one of the statistical number of times, click rate and stay time of the target service section of the service requester terminal or the service provider terminal by the target user within a preset time period, a third probability of the target user arriving at the target store is predicted.
[0049] In a possible implementation manner, the fourth prediction unit is specifically configured to:
[0050] Obtain the license plate recognition data obtained by the B-end service system used by the target store after performing license plate recognition on the target user's vehicle;
[0051] A fourth probability of the target user's arrival is predicted based on the target user's license plate recognition data.
[0052] According to the third aspect of the present application, an electronic device is provided, comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the first aspect of the embodiment of the present application and the steps in any possible implementation manner of the first aspect.
[0053] According to the fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the first aspect of the embodiment of the present application and any possible implementation of the first aspect are executed.
[0054] A method for store identification provided in an embodiment of the present application first predicts the probability of the target user arriving at a target store based on at least one of the target user's vehicle driving trajectory data, vehicle driving data, online access service behavior data, and license plate recognition data. Then, if it is determined that the probability of the target user arriving at the target store is greater than a preset threshold, the target user is identified to have arrived at the target store. The present application is based on the existing data in the server (vehicle driving trajectory data, vehicle driving data, online access service behavior data, and license plate recognition data) for store identification. On the one hand, the present application does not need to use additional high-cost equipment for store identification, which can reduce the cost of store identification; on the other hand, compared with the relatively single and inaccurate positioning data for store identification in traditional solutions, the present application uses multiple data for store identification, which can improve the accuracy of user store identification.
[0055] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0057] Figure 1 A schematic diagram of the architecture of a store arrival identification service system provided by an embodiment of the present application is shown;
[0058] Figure 2 A flow chart of a store arrival identification method provided by an embodiment of the present application is shown;
[0059] Figure 3 A flowchart showing a specific method for predicting the probability of a target user arriving at a target store in a store arrival identification method provided by an embodiment of the present application;
[0060] Figure 4 A schematic diagram of the structure of a store arrival identification device provided in an embodiment of the present application is shown;
[0061] Figure 5 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION
[0062] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.
[0063] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.
[0064] In order to enable those skilled in the art to use the contents of this application, the following implementation is provided in conjunction with the specific application scenario of "online car-hailing user arrival identification". For those skilled in the art, the general principles defined here can be applied to other embodiments and application scenarios without departing from the spirit and scope of this application. Although this application is mainly described around "online car-hailing user arrival identification", it should be understood that this is only an exemplary embodiment.
[0065] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.
[0066] The terms "passenger", "requester", "service requester" and "customer" in this application are used interchangeably to refer to individuals, entities or tools that can request or order services. The terms "driver", "provider", "service provider" and "supplier" in this application are used interchangeably to refer to individuals, entities or tools that can provide services. The term "user" in this application may refer to an individual, entity or tool that requests a service, orders a service, provides a service, or facilitates the provision of a service. For example, a user may be a passenger, a driver, an operator, etc., or any combination thereof. In this application, "passenger" and "passenger terminal" are used interchangeably, and "driver" and "driver terminal" are used interchangeably.
[0067] The terms "service request" and "order" in this application are used interchangeably to refer to a request initiated by a passenger, a service requester, a driver, a service provider, a supplier, etc., or any combination thereof. The "service request" or "order" may be accepted by a passenger, a service requester, a driver, a service provider, a supplier, etc., or any combination thereof. A service request may be charged or free.
[0068] The positioning technology used in this application can be based on the Global Positioning System (GPS), the Global Navigation Satellite System (GLONASS), the Compass Navigation System (COMPASS), the Galileo Positioning System, the Quasi-Zenith Satellite System (QZSS), the Wireless Fidelity (WiFi) positioning technology, etc., or any combination thereof. One or more of the above positioning systems can be used interchangeably in this application.
[0069] Figure 11 is a schematic diagram of the architecture of a store identification service system provided by an embodiment of the present application. For example, the store identification service system may be a store identification service platform for store identification services such as taxi, chauffeur service, express, carpooling, bus service, driver rental, or shuttle service, or any combination thereof. The store identification service system may include one or more of a server 110, a network 120, a service requester terminal 130, a service provider terminal 140, and a database 150.
[0070] In some embodiments, the server 110 may include a processor. The processor may process information and / or data related to the service request to perform one or more functions described in the present application. For example, the processor may determine the target vehicle based on the service request obtained from the service requester terminal 130. In some embodiments, the processor may include one or more processing cores (e.g., a single-core processor (S) or a multi-core processor (S)). By way of example only, the processor may include a central processing unit (CPU), an application specific integrated circuit (ASIC), an application specific instruction set processor (ASIP), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic device (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), or a microprocessor, or any combination thereof.
[0071] In some embodiments, server 110 may be implemented on a cloud platform. By way of example only, a cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-cloud, etc., or any combination thereof.
[0072] The network 120 can be used for the exchange of information and / or data. In some embodiments, one or more components in the service system (e.g., server 110, service requester terminal 130, service provider terminal 140 and database 150) can send information and / or data to other components. For example, the server 110 can obtain a service request from the service requester terminal 130 via the network 120. In some embodiments, the network 120 can be any type of wired or wireless network, or a combination thereof. As an example only, the network 120 can include a wired network, a wireless network, an optical fiber network, a telecommunication network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a wide area network (WAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, or a near field communication (NFC) network, or any combination thereof. In some embodiments, network 120 may include one or more network access points. For example, network 120 may include a wired or wireless network access point, such as a base station and / or a network switching node, through which one or more components of the service system may connect to network 120 to exchange data and / or information.
[0073] In some embodiments, the device type corresponding to the service requester terminal 130 and the service provider terminal 140 may be a mobile device, such as a mobile device, a tablet computer, a laptop computer, or a built-in device in a motor vehicle, or any combination thereof. In some embodiments, the mobile device may include a smart home device, a wearable device, a smart mobile device, a virtual reality device, or an augmented reality device, or any combination thereof. In some embodiments, the smart home device may include a smart lighting device, a control device for a smart electrical device, a smart monitoring device, a smart TV, a smart camera, or an intercom, or any combination thereof. In some embodiments, the wearable device may include a smart bracelet, a smart shoelace, a smart glass, a smart helmet, a smart watch, a smart clothing, a smart backpack, a smart accessory, or any combination thereof. In some embodiments, the smart mobile device may include a smart phone, a personal digital assistant (PDA), a gaming device, a navigation device, or a point of sale (POS) device, or any combination thereof. In some embodiments, the virtual reality device and / or the augmented reality device may include a virtual reality helmet, a virtual reality glass, a virtual reality patch, an augmented reality helmet, an augmented reality glass, or an augmented reality patch, or any combination thereof. For example, the virtual reality device and / or the augmented reality device may include various virtual reality products, etc. In some embodiments, built-in devices in a motor vehicle may include an on-board computer, an on-board television, and the like.
[0074] In some embodiments, the database 150 may be connected to the network 120 to communicate with one or more components in the store identification service system (e.g., the server 110, the service requester terminal 130, the service provider terminal 140, etc.). One or more components in the store identification service system may access the data or instructions stored in the database 150 via the network 120. In some embodiments, the database 150 may be directly connected to one or more components in the store identification service system, or the database 150 may also be part of the server 110.
[0075] The following is combined with the above Figure 1 The contents described in the in-store identification service system shown are used to provide a detailed description of the in-store identification solution provided in the embodiment of the present application.
[0076] In traditional solutions, store identification is generally based on positioning technology, such as GPS positioning technology, ultra-wideband positioning, inertial positioning, Wi-Fi fingerprint positioning, and so on. However, the signal of GPS positioning is weak, and it is difficult to locate indoors due to the obstruction and reflection of walls; ultra-wideband positioning requires the deployment of anchor nodes and bridge nodes at known locations in advance, and the cost of use is relatively high; inertial positioning relies on gyroscopes and accelerometers, which cannot be used alone and are not suitable for use on mobile Internet; Wi-Fi fingerprint positioning requires a large manpower cost to collect and update the fingerprint library in advance, and does not consider whether the user is in a resident state, and it is easy to identify users passing by the store as in the store state. It can be seen that the traditional store identification solution has technical problems such as high cost and poor identification accuracy. Based on this, the embodiments of the present application provide a store identification method, device, electronic device and medium, which are described below through embodiments.
[0077] To facilitate understanding of this embodiment, a method for in-store identification disclosed in an embodiment of the present application is first introduced in detail.
[0078] Please refer to Figure 2 , Figure 2 This is a flow chart of a store arrival identification method provided in an embodiment of the present application. The method can be executed by the server 110 in the store arrival identification service system. The specific execution process is as follows:
[0079] Step S201, predicting the probability of the target user arriving at a target store based on at least one of the target user's vehicle driving trajectory data, vehicle driving data, online access service behavior data, and license plate recognition data;
[0080] Step S202: If the probability that the target user arrives at the target store is greater than a preset threshold, it is identified that the target user arrives at the target store.
[0081] Before step S201, a data acquisition step is also included, and the data acquisition step includes: acquiring at least one of the vehicle driving trajectory data, vehicle driving data, online access service behavior data and license plate recognition data of the target user.
[0082] In the data acquisition step, the target users refer to users who have registered on the online ride-hailing platform, such as online ride-hailing driver users who have registered as car owners and passenger users who have registered as passengers.
[0083] Regarding obtaining the target user's vehicle driving trajectory data, first, the positioning system in the vehicle collects the positioning data of the vehicle driven or taken by the target user in real time, and uploads the collected positioning data to the server 110 in real time. Secondly, the server 110 draws and stores the vehicle driving trajectory data based on a number of positioning data. Finally, the server 110 obtains the target user's vehicle driving trajectory data stored in itself. Among them, the vehicle driving trajectory data refers to the trajectory data generated by the vehicle driven or taken by the target user during the driving process.
[0084] Regarding obtaining the vehicle driving data of the target user, the vehicle driving data may include: the difference between the mileage when the target store's service was used last time and the current mileage, the vehicle maintenance recommended mileage, the remaining fuel, and at least one of the remaining power. The odometer in the vehicle records the vehicle mileage data, the fuel monitoring device monitors the fuel data, and the power monitoring device monitors the power data. The server 110 queries the mileage of the target user when the target store's service was used last time and the current mileage recorded by the odometer in the vehicle, and calculates the difference between the mileage when the target store's service was used last time and the current mileage. The server 110 queries the remaining fuel monitored in the fuel monitoring device, and / or the server 110 queries the remaining power monitored in the power monitoring device. Regarding the vehicle maintenance recommended mileage, the vehicle maintenance recommended mileage cycle for Japanese and Korean car series is usually 5,000 kilometers, and the European and American car series is mostly more than 7,500 kilometers or even more than 15,000 kilometers. This embodiment is not limited to this, and the server 110 can also use other methods to determine the vehicle maintenance recommended mileage cycle.
[0085] Regarding obtaining the target user's online access service behavior data, assuming that the target user is a ride-hailing driver user, the server 110 obtains the target user's online access service behavior data by monitoring the operation data of the service provider terminal 140. Specifically, the service provider terminal 140 is the user terminal corresponding to the ride-hailing driver user, and the ride-hailing driver user can use the user terminal to request services from the server 110, and provide services to the passenger user. Among them, the online access service behavior data may include: at least one of the number of times, click-through rate, and length of stay of the target service section of the service provider terminal 140 operated within a preset time period. Assuming that the target user is a passenger user, the server 110 obtains the target user's online access service behavior data by monitoring the operation data of the service requester terminal 130. Specifically, the service requester terminal 130 is the user terminal corresponding to the passenger user, and the passenger user can use the user terminal to request services from the server 110 or the service provider terminal 140. Among them, the online access service behavior data may include: at least one of the number of times, click-through rate, and length of stay of the target service section of the service requester terminal 130 operated within a preset time period.
[0086] Regarding obtaining the target user's license plate recognition data, the service provider terminal 140 may also refer to the B-end service system used by the store. In order to create a B-end ecosystem, a B-end service system is provided to merchants. The B-end service system is a service system for merchants and is an important part of the online car-hailing ecosystem layout. In this embodiment, the license plate recognition function of its B-end service system is used to identify the target user's vehicle and obtain license plate recognition data. The B-end service system used by the store uploads the obtained license plate recognition data to the server 110. Among them, the license plate recognition data refers to the license plate recognition data obtained after the B-end service system used by the store identifies the target user's vehicle.
[0087] In step S201, based on at least one of the vehicle driving trajectory data, vehicle driving data, online access service behavior data, and license plate recognition data of the target user obtained above, the probability of the target user arriving at the target store is predicted. Specifically, Figure 3 As shown, step S201 may include the following sub-steps:
[0088] Step S2011, predicting a first probability of the target user arriving at a target store based on the vehicle driving trajectory data of the target user;
[0089] Step S2012: predicting a second probability of the target user arriving at the target store based on the target user's vehicle driving data;
[0090] Step S2013: predicting a third probability of the target user arriving at the target store based on the online access service behavior data of the target user;
[0091] Step S2014: predicting a fourth probability that the target user arrives at the target store based on the license plate recognition data of the target user;
[0092] Step S2015: predict the probability of the target user arriving at the target store based on at least one of the first probability, the second probability, the third probability and the fourth probability.
[0093] In the above step S2011, based on the target user's vehicle driving trajectory data and the location of the target store, the first probability of the target user arriving at the target store is predicted. After analyzing the target user's vehicle driving trajectory data, the stores that the target user has passed through are obtained. If the target store is included in the stores that the target user has passed through, then the probability that the target user will arrive at the target store will be higher. In one possible implementation, a first probability prediction model is learned from a training sample set, a feature data set of the target user is obtained, and the feature data set of the target user is used as an input to the first probability prediction model, and the first probability of the target user arriving at the target store is obtained through the first probability prediction model. Optionally, the first probability of the target user arriving at the target store can also be predicted based on subjective experience.
[0094] In the above step S2012, the target user's vehicle driving data includes at least one of: the difference between the mileage when the target store's service was used last time and the current mileage, the vehicle maintenance recommended mileage, the remaining fuel (e.g., 20% of the fuel tank has 20% of the fuel left), and the remaining power (30% of the power left after charging). For example, if the difference between the mileage when the target store's service was used last time and the current mileage is large, it means that the target user has a high probability of needing to use the target store's service again, and the target user has a high probability of arriving at the target store. If the vehicle maintenance recommended mileage reaches the target mileage, the target user has a high probability of needing to repair and maintain the vehicle again, and the target user has a high probability of arriving at the repair and maintenance store. If there is 20% of the fuel left in the tank, it means that the user needs to refuel the vehicle in the near future, and the target user has a high probability of arriving at the gas station. If there is 30% of the power left after charging, it means that the user needs to charge the vehicle in the near future, and the target user has a high probability of arriving at the charging station. In a possible implementation, a second probability prediction model is learned from a training sample set, a feature data set of a target user is obtained, the feature data set of the target user is used as an input of the second probability prediction model, and a second probability of the target user arriving at the target store is obtained through the second probability prediction model. Optionally, the second probability of the target user arriving at the target store can also be predicted based on subjective experience.
[0095] In the above step S2013, based on the online access service behavior data of the target user, at least one of the number of times, click-through rate and stay time of the target service section of the service requester terminal 130 or the service provider terminal 140 operated by the target user within the preset time period is counted; based on the statistics of at least one of the number of times, click-through rate and stay time of the target service section of the service requester terminal 130 or the service provider terminal 140 operated by the target user within the preset time period, the third probability of the target user arriving at the target store is predicted. If the target user operates the target service section of the service requester terminal 130 or the service provider terminal 140 more times, has a higher click-through rate and a longer stay time within the preset time period, it means that the target user has a high interest in the services of the target service section within the preset time period, and then the probability of the target user arriving at the target store where the services of the target service section are located will be higher. In a possible implementation, a third probability prediction model is learned from a training sample set, a feature data set of the target user is obtained, and the feature data set of the target user is used as an input of the third probability prediction model, and the third probability of the target user arriving at the target store is obtained through the third probability prediction model. Optionally, the third probability of the target user arriving at the target store may also be predicted based on subjective experience.
[0096] In the above step S2014, the license plate recognition data obtained after the B-end service system used by the target store recognizes the license plate of the target user's vehicle is obtained; based on the license plate recognition data of the target user, the fourth probability of the target user's arrival is predicted. The probability of the target user's arrival can be predicted by the license plate recognition data of the target user in the B-end service system provided to the store by the online car-hailing platform. In one possible implementation, a fourth probability prediction model is learned from the training sample set, a feature data set of the target user is obtained, and the feature data set of the target user is used as the input of the fourth probability prediction model, and the fourth probability of the target user arriving at the target store is obtained through the fourth probability prediction model. Optionally, the fourth probability of the target user arriving at the target store can also be predicted based on subjective experience.
[0097] In the above step S2015, weights are set for the first probability, the second probability, the third probability and the fourth probability respectively; based on at least one of the first probability, the second probability, the third probability and the fourth probability and their corresponding weights, the probability of the target user arriving at the target store is predicted.
[0098] In a possible implementation, the first probability is set to p1, the second probability is set to p2, the third probability is set to p3, and the fourth probability is set to p4. The weight corresponding to the first probability is ω1, the weight corresponding to the second probability is ω2, the weight corresponding to the third probability is ω3, and the weight corresponding to the fourth probability is ω4. p1×ω1+p2×ω2+p3×ω3+p4×ω4 is the predicted probability of the target user arriving at the target store. It should be noted that the embodiment of the present application predicts the probability of the target user arriving at the target store by weighted summation in order to teach those skilled in the art how to implement the present invention. The embodiment of the present application is not limited thereto, and other calculation methods may also be used to predict the probability of the target user arriving at the target store.
[0099] Regarding the allocation of weights, the vehicle driving trajectory data, vehicle driving data, online access service behavior data and license plate recognition data of the reference user are used as sample sets to train the machine learning model. The weights corresponding to the first probability, the second probability, the third probability and the fourth probability are fitted based on the trained machine learning model. In particular, the weights can also be configured through experience.
[0100] In a possible implementation, with reference to a user's vehicle driving trajectory data, vehicle driving data, online access service behavior data, and license plate recognition data as sample sets, a scheme for training a machine learning model may include: initializing the current weight of each training data in the sample set to the same value, and obtaining a preset number of executions; determining the current feature weights of various training data as the first weights corresponding to each training data; for each training data, using the training data as the first training data, and calculating the Euclidean distance between the first training data and other training data based on the first weight of each training data; determining the sample weights of other training data based on the Euclidean distance between the first training data and other training data; determining the current weight of the first training data based on the sample weights of other training data, the first weight of the first training data, and a pre-constructed multi-objective optimization function; determining whether the number of executed cycles is the preset number of executions; if not, returning to the step of determining the current weights of various training data as the first weights corresponding to each training data.
[0101] In summary, the embodiment of the present application provides a method for store identification, which first predicts the probability of the target user arriving at the target store based on at least one of the target user's vehicle driving trajectory data, vehicle driving data, online access service behavior data, and license plate recognition data. Then, if it is determined that the probability of the target user arriving at the target store is greater than a preset threshold, the target user is identified to have arrived at the target store. The present application is based on the existing data in the server (vehicle driving trajectory data, vehicle driving data, online access service behavior data, and license plate recognition data) for store identification. On the one hand, the present application does not need to use additional high-cost equipment for store identification, which can reduce the cost of store identification; on the other hand, compared with the relatively single and inaccurate positioning data for store identification in the traditional solution, the present application uses multiple data for store identification, which can improve the accuracy of user store identification.
[0102] Based on the same technical concept, the embodiments of the present application also provide a store arrival identification device, an electronic device, and a computer storage medium, etc. For details, please refer to the following embodiments.
[0103] Please refer to Figure 4 , is a schematic diagram of the structure of a store arrival identification device provided in an embodiment of the present application. Figure 4 As shown, the device may include:
[0104] Prediction module 401, used to predict the probability of the target user arriving at the target store based on at least one of the target user's vehicle driving trajectory data, vehicle driving data, online access service behavior data, and license plate recognition data;
[0105] The identification module 402 is used to identify that the target user has arrived at the target store if the probability that the target user has arrived at the target store is greater than a preset threshold.
[0106] In a possible implementation, the prediction module 401 includes:
[0107] A first prediction unit, configured to predict a first probability of a target user arriving at a target store based on the vehicle driving trajectory data of the target user;
[0108] A second prediction unit, configured to predict a second probability of the target user arriving at the target store based on the vehicle driving data of the target user;
[0109] A third prediction unit, configured to predict a third probability of the target user arriving at the target store based on the online access service behavior data of the target user;
[0110] a fourth prediction unit, configured to predict a fourth probability that the target user arrives at the target store based on the license plate recognition data of the target user;
[0111] The fifth prediction unit is used to predict the probability of the target user arriving at the target store based on at least one of the first probability, the second probability, the third probability and the fourth probability.
[0112] In a possible implementation manner, the fifth prediction unit is specifically configured to:
[0113] Setting weights for the first probability, the second probability, the third probability and the fourth probability respectively;
[0114] Based on at least one of the first probability, the second probability, the third probability and the fourth probability and their corresponding weights, the probability of the target user arriving at the target store is predicted.
[0115] In a possible implementation manner, the fifth prediction unit is specifically configured to:
[0116] The machine learning model is trained using the reference user's vehicle driving trajectory data, vehicle driving data, online access service behavior data, and license plate recognition data as sample sets;
[0117] The weights corresponding to the first probability, the second probability, the third probability and the fourth probability are fitted based on the trained machine learning model.
[0118] In a possible implementation manner, the first prediction unit is specifically configured to predict a first probability that the target user arrives at the target store based on the vehicle driving trajectory data of the target user and the location of the target store.
[0119] In a possible implementation, the second prediction unit is specifically used to predict the second probability of the target user arriving at the target store based on the target user's vehicle driving data; the target user's vehicle driving data includes: the difference between the mileage when the target store's service was last used and the current mileage, the recommended mileage for vehicle maintenance, and at least one of the remaining fuel and remaining power.
[0120] In a possible implementation manner, the third prediction unit is specifically configured to:
[0121] Based on the online access service behavior data of the target user, at least one of the number of times, click rate and stay time of the target service section of the service requester terminal or the service provider terminal operated by the target user within a preset time period is counted;
[0122] Based on at least one of the statistical number of times, click rate and stay time of the target service section of the service requester terminal or the service provider terminal by the target user within a preset time period, a third probability of the target user arriving at the target store is predicted.
[0123] In a possible implementation manner, the fourth prediction unit is specifically configured to:
[0124] Obtain the license plate recognition data obtained by the B-end service system used by the target store after performing license plate recognition on the target user's vehicle;
[0125] A fourth probability of the target user's arrival is predicted based on the target user's license plate recognition data.
[0126] The present application embodiment discloses an electronic device, such as Figure 5 As shown, it includes: a processor 501, a memory 502 and a bus 503. The memory 502 stores machine-readable instructions executable by the processor 501. When the electronic device is running, the processor 501 communicates with the memory 502 through the bus 503. When the machine-readable instructions are executed by the processor 501, the method described in the previous method embodiment is performed. For specific implementation, please refer to the method embodiment, which will not be repeated here.
[0127] A computer program product of a store arrival identification method provided in an embodiment of the present application includes a computer-readable storage medium storing a non-volatile program code executable by a processor, wherein the instructions included in the program code can be used to execute the method described in the previous method embodiment. For specific implementation, please refer to the method embodiment, which will not be described in detail here.
[0128] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in this application. In the several embodiments provided in this application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.
[0129] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0130] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0131] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.
[0132] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A method for identifying a store visit, characterized in that: include: Based on the target user's vehicle driving trajectory data, vehicle driving data, online access service behavior data and license plate recognition data, predict the probability of the target user arriving at the target store; If the probability that the target user arrives at the target store is greater than a preset threshold, identifying that the target user arrives at the target store; The method of predicting the probability of the target user arriving at the target store based on the target user's vehicle driving trajectory data, vehicle driving data, online access service behavior data, and license plate recognition data includes: Respectively determining the probabilities corresponding to the vehicle driving trajectory data, vehicle driving data, online access service behavior data and license plate recognition data of the target user; respectively determining weights corresponding to the probabilities; The probabilities and the weights corresponding to the probabilities are weighted to predict the probability of the target user arriving at the target store.
2. The method according to claim 1, characterized in that Based on the target user's vehicle driving trajectory data, vehicle driving data, online access service behavior data, and license plate recognition data, the probability of the target user arriving at the target store is predicted, including: Predicting a first probability of the target user arriving at the target store based on the vehicle driving trajectory data of the target user; Predicting a second probability of the target user arriving at the target store based on the target user's vehicle driving data; Predicting a third probability of the target user arriving at the target store based on the target user's online access service behavior data; Predicting a fourth probability of the target user arriving at the target store based on the license plate recognition data of the target user; Based on the first probability, the second probability, the third probability and the fourth probability, the probability of the target user arriving at the target store is predicted.
3. The method according to claim 2, characterized in that Predicting the probability of the target user arriving at the target store based on the first probability, the second probability, the third probability, and the fourth probability includes: Setting weights for the first probability, the second probability, the third probability and the fourth probability respectively; Based on the first probability, the second probability, the third probability and the fourth probability and their corresponding weights, the probability of the target user arriving at the target store is predicted.
4. The method according to claim 3, characterized in that Setting weights for the first probability, the second probability, the third probability, and the fourth probability respectively includes: The machine learning model is trained using the reference user's vehicle driving trajectory data, vehicle driving data, online access service behavior data, and license plate recognition data as sample sets; The weights corresponding to the first probability, the second probability, the third probability and the fourth probability are fitted based on the trained machine learning model.
5. The method according to claim 2, characterized in that: The target user's vehicle driving data includes: the difference between the mileage when the target store's service was used last time and the current mileage, the vehicle maintenance recommended mileage, and at least one of the remaining oil and remaining battery power.
6. The method according to claim 2, characterized in that Predicting a third probability of the target user arriving at the target store based on the online access service behavior data of the target user includes: Based on the online access service behavior data of the target user, at least one of the number of times, click rate and stay time of the target service section of the service requester terminal or the service provider terminal operated by the target user within a preset time period is counted; Based on at least one of the statistical number of times, click rate and stay time of the target service section of the service requester terminal or the service provider terminal by the target user within a preset time period, a third probability of the target user arriving at the target store is predicted.
7. The method according to claim 2, characterized in that Predicting a fourth probability of the target user's arrival based on the target user's license plate recognition data includes: Obtain the license plate recognition data obtained by the B-end service system used by the target store after performing license plate recognition on the target user's vehicle; A fourth probability of the target user's arrival is predicted based on the target user's license plate recognition data.
8. A store arrival identification device, characterized in that: include: A prediction module, used to predict the probability of the target user arriving at the target store based on the target user's vehicle driving trajectory data, vehicle driving data, online access service behavior data and license plate recognition data; an identification module, configured to identify that the target user has arrived at the target store if the probability that the target user has arrived at the target store is greater than a preset threshold; The prediction module is specifically used to respectively determine the probabilities corresponding to the target user's vehicle driving trajectory data, vehicle driving data, online access service behavior data and license plate recognition data; respectively determine the weights corresponding to the probabilities; and perform weighted processing on the probabilities and the weights corresponding to the probabilities to predict the probability of the target user arriving at the target store.
9. The device according to claim 8, characterized in that The prediction module comprises: A first prediction unit, configured to predict a first probability of a target user arriving at a target store based on the vehicle driving trajectory data of the target user; A second prediction unit, configured to predict a second probability of the target user arriving at the target store based on the vehicle driving data of the target user; A third prediction unit, configured to predict a third probability of the target user arriving at the target store based on the online access service behavior data of the target user; a fourth prediction unit, configured to predict a fourth probability that the target user arrives at the target store based on the license plate recognition data of the target user; The fifth prediction unit is used to predict the probability of the target user arriving at the target store based on the first probability, the second probability, the third probability and the fourth probability.
10. The device according to claim 9, characterized in that The fifth prediction unit is specifically used for: Setting weights for the first probability, the second probability, the third probability and the fourth probability respectively; Based on the first probability, the second probability, the third probability and the fourth probability and their corresponding weights, the probability of the target user arriving at the target store is predicted.
11. The device according to claim 10, characterized in that The fifth prediction unit is specifically used for: The machine learning model is trained using the reference user's vehicle driving trajectory data, vehicle driving data, online access service behavior data, and license plate recognition data as sample sets; The weights corresponding to the first probability, the second probability, the third probability and the fourth probability are fitted based on the trained machine learning model.
12. The device according to claim 9, characterized in that The second prediction unit is specifically used for: A second probability of the target user arriving at the target store is predicted based on the target user's vehicle driving data; the target user's vehicle driving data includes: the difference between the mileage when the target store's service was last used and the current mileage, the recommended mileage for vehicle maintenance, and at least one of the remaining oil and remaining battery power.
13. The device according to claim 9, characterized in that The third prediction unit is specifically used for: Based on the online access service behavior data of the target user, at least one of the number of times, click rate and stay time of the target service section of the service requester terminal or the service provider terminal operated by the target user within a preset time period is counted; Based on at least one of the statistical number of times, click rate and stay time of the target service section of the service requester terminal or the service provider terminal by the target user within a preset time period, a third probability of the target user arriving at the target store is predicted.
14. The device according to claim 9, characterized in that The fourth prediction unit is specifically used for: Obtain the license plate recognition data obtained by the B-end service system used by the target store after performing license plate recognition on the target user's vehicle; A fourth probability of the target user's arrival is predicted based on the target user's license plate recognition data.
15. An electronic device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of any method as claimed in claims 1 to 7.
16. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are executed.
Citation Information
Patent Citations
Method and device for determining characteristic weight aiming at data classification
CN106682229A
License plate identification-based data processing method and related device
CN108389074A
Store arrival prediction method and device, readable storage medium and electronic equipment
CN110472995A
Store arrival identification method and device, electronic equipment and readable storage medium
CN110688589A
Systems and methods for distributing request for service
US20180202818A1
