Shopping cart positioning method and device

Abstract

The invention discloses a shopping cart positioning method and device, and the method comprises the steps: employing an inertial navigation positioning mode to position a shopping cart when the shopping cart is not in the coverage range of a current base station; in the inertial navigation positioning process, the signal intensity of surrounding electronic price tags is obtained, and if the electronic price tag positioning condition is met, the shopping cart is positioned in a signal intensity weight calculation mode; if the scanning commodity identifier positioning condition is satisfied, positioning the shopping cart by scanning the commodity identifier to position the position of the commodity; correcting the inertial navigation positioning result based on an electronic price tag positioning result or a scanned commodity identifier positioning result of the shopping cart to obtain a first corrected positioning result of the shopping cart; and according to the first correction positioning result and a set of path points pre-generated based on a supermarket map, matching to obtain a position of the path point closest to the first correction positioning result as a second correction positioning result of the shopping cart. The precision of shopping cart positioning can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of supermarket positioning, and in particular to a method and device for shopping cart positioning. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.

[0003] As the pace of life accelerates, consumers are increasingly demanding convenience in shopping, hoping to reduce the time spent looking for shopping carts and products in shopping malls. At the same time, based on the improvement of store operation efficiency, merchants also need to monitor the location and status of shopping carts in real time. Therefore, the demand for shopping cart positioning in supermarkets is becoming more and more urgent. At the same time, the rapid development of technologies such as the Internet of Things (IOT), wireless communication technology, and big data analysis has made it possible to achieve the technical realization of shopping cart positioning. At present, smart shopping carts can provide functions such as self-service checkout, product recommendation and inquiry, indoor positioning and navigation, shopping cart tracking, and security monitoring. Among them, accurate positioning of shopping carts is an important part. For shopping cart scenarios in supermarkets, the main existing positioning technologies include UWB, Bluetooth beacons, RFID, geomagnetic positioning technologies, etc. These shopping cart positioning methods all have the problem of low positioning accuracy. Summary of the invention

[0004] An embodiment of the present invention provides a method for locating a shopping cart, so as to improve the accuracy of locating a shopping cart. The method includes:

[0005] Determine whether the shopping cart is within the coverage of the current base station;

[0006] When it is determined that the shopping cart is not within the coverage of the current base station, the shopping cart is positioned using an inertial navigation positioning method to obtain an inertial navigation positioning result of the shopping cart;

[0007] During the inertial navigation positioning process, the signal strength of the surrounding electronic price tags is obtained. If the electronic price tag positioning conditions are met, the electronic price tag positioning result of the shopping cart is obtained by solving the signal strength weight.

[0008] During the inertial navigation positioning process, if the product identification scanning positioning condition is met, the product identification scanning positioning result of the shopping cart is obtained by locating the product position by scanning the product identification;

[0009] Performing position correction processing on the inertial navigation positioning result of the shopping cart based on the positioning result of the electronic price tag of the shopping cart or the positioning result of the scanned product logo, to obtain a first corrected positioning result of the shopping cart;

[0010] According to the first corrected positioning result and a set of each path point pre-generated based on the supermarket map, the position of the path point closest to the first corrected positioning result is matched and obtained as the second corrected positioning result of the shopping cart.

[0011] The embodiment of the present invention further provides a shopping cart positioning device, which is used to improve the accuracy of shopping cart positioning. The device includes:

[0012] A determination unit, used to determine whether the shopping cart is within the coverage of the current base station;

[0013] The inertial navigation positioning unit is used to locate the shopping cart by using the inertial navigation positioning method when it is determined that the shopping cart is not within the coverage of the current base station, and obtain the inertial navigation positioning result of the shopping cart;

[0014] The electronic price tag positioning unit is used to obtain the signal strength of the surrounding electronic price tags during the inertial navigation positioning process. If the electronic price tag positioning conditions are met, the electronic price tag positioning result of the shopping cart is obtained by signal strength weighting calculation;

[0015] The product identification scanning and positioning unit is used to obtain the product identification scanning and positioning result of the shopping cart by scanning the product identification and locating the product position if the product identification scanning and positioning conditions are met during the inertial navigation positioning process;

[0016] A first correction positioning unit is used to perform position correction processing on the inertial navigation positioning result of the shopping cart based on the positioning result of the electronic price tag of the shopping cart or the positioning result of scanning the product logo, so as to obtain a first correction positioning result of the shopping cart;

[0017] The second correction positioning unit is used to match the position of the path point closest to the first correction positioning result as the second correction positioning result of the shopping cart based on the first correction positioning result and a set of each path point pre-generated based on the supermarket map.

[0018] An embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned shopping cart positioning method when executing the computer program.

[0019] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned shopping cart positioning method is implemented.

[0020] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method for locating a shopping cart is implemented.

[0021] Compared with the shopping cart positioning technical solution with low positioning accuracy in the prior art, the shopping cart positioning solution provided by the embodiment of the present invention has the following beneficial technical effects: the embodiment of the present invention determines whether the shopping cart is within the coverage of the current base station; when it is determined that the shopping cart is not within the coverage of the current base station, the shopping cart is positioned by an inertial navigation positioning method to obtain the inertial navigation positioning result of the shopping cart; in the process of inertial navigation positioning, the signal strength of the surrounding electronic price tags is obtained, and if the electronic price tag positioning condition is met, the electronic price tag positioning result of the shopping cart is obtained by a signal strength weight solution method; in the process of inertial navigation positioning, if the scanning commodity identification positioning condition is met, the commodity position is positioned by scanning the commodity identification to obtain the scanning commodity identification positioning result of the shopping cart; based on the electronic price tag positioning result of the shopping cart or the scanning commodity identification positioning result, the inertial navigation positioning result of the shopping cart is corrected to obtain a first corrected positioning result of the shopping cart; according to the first corrected positioning result and a set of each path point pre-generated based on the supermarket map, the position of the path point closest to the first corrected positioning result is matched as the second corrected positioning result of the shopping cart, so as to improve the positioning accuracy of the shopping cart. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0023] Figure 1 A schematic diagram of a flow chart of a method for locating a shopping cart in an embodiment of the present invention;

[0024] Figure 2 Schematic diagram of the Bluetooth arrival angle positioning principle in an embodiment of the present invention;

[0025] Figure 3 It is a schematic diagram of the process of inertial navigation positioning in an embodiment of the present invention;

[0026] Figure 4 A schematic diagram of the process of positioning an electronic price label in an embodiment of the present invention;

[0027] Figure 5 A schematic diagram of a process of scanning a product identification for positioning in an embodiment of the present invention;

[0028] Figure 6 A schematic diagram of a map matching-path point matching process in an embodiment of the present invention;

[0029] Figure 7This is a schematic diagram of the shopping cart positioning principle in an embodiment of the present invention;

[0030] Figure 8 A schematic diagram of a process of locating a shopping cart in an embodiment of the present invention;

[0031] Fig. 9 A schematic diagram of switching path points in an embodiment of the present invention;

[0032] Fig.10 It is a structural schematic diagram of a device for positioning a shopping cart in an embodiment of the present invention. DETAILED DESCRIPTION

[0033] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0034] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of laws and regulations.

[0035] In order to better understand how to implement the present invention, the terms involved in the embodiments of the present invention are first introduced.

[0036] ESL: Electronic Shelf Label

[0037] IOT: Internet of Things

[0038] UWB: Ultra Wide Band

[0039] RSSI: Received Signal Strength Indication

[0040] DF:Direction Finding

[0041] AoA:Angle of Arrival

[0042] AoD: Angel of Departure

[0043] RFID: Radio Frequency Identification

[0044] ID: Identity document unique code, identification code

[0045] IMU: Inertial measurement unit

[0046] AP: Access Point wireless access point

[0047] MQTT: Message Queuing Telemetry Transport

[0048] Elinker: ESL linker electronic price tag connector

[0049] The embodiment of the present invention proposes a solution for positioning a smart shopping cart, which uses a small number of Bluetooth AoA base stations, combined with inertial navigation nine-axis sensors, electronic price tag positioning, scanning product positioning and map matching to achieve high-precision seamless positioning of shopping carts in supermarket scenarios. Without increasing hardware deployment (generally supermarkets will deploy Bluetooth AoA base stations for ESL positioning, so there is no need to increase the cost of building Bluetooth AoA base stations), a seamless positioning solution is provided for shopping carts in supermarkets. The following is a detailed introduction to the shopping cart positioning solution.

[0050] Figure 1 FIG. 1 is a flow chart of a method for locating a shopping cart in an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0051] Step 101: Determine whether the shopping cart is within the coverage of the current base station;

[0052] Step 102: when it is determined that the shopping cart is not within the coverage of the current base station, the shopping cart is positioned using an inertial navigation positioning method to obtain an inertial navigation positioning result of the shopping cart;

[0053] Step 103: During the inertial navigation positioning process, the signal strength of the surrounding electronic price tags is obtained. If the electronic price tag positioning condition is met, the electronic price tag positioning result of the shopping cart is obtained by signal strength weighting.

[0054] Step 104: during the inertial navigation positioning process, if the product identification scanning positioning condition is met, the product identification is scanned to locate the product position, thereby obtaining the product identification scanning positioning result of the shopping cart;

[0055] Step 105: performing position correction processing on the inertial navigation positioning result of the shopping cart based on the positioning result of the electronic price tag of the shopping cart or the positioning result of scanning the product logo, to obtain a first corrected positioning result of the shopping cart;

[0056] Step 106: According to the first corrected positioning result and a set of each path point pre-generated based on the supermarket map, the position of the path point closest to the first corrected positioning result is matched as the second corrected positioning result of the shopping cart.

[0057] Compared with the shopping cart positioning technical solution with low positioning accuracy in the prior art, the shopping cart positioning solution provided by the embodiment of the present invention has the following beneficial technical effects: the embodiment of the present invention determines whether the shopping cart is within the coverage of the current base station; when it is determined that the shopping cart is not within the coverage of the current base station, the shopping cart is positioned by an inertial navigation positioning method to obtain the inertial navigation positioning result of the shopping cart; in the process of inertial navigation positioning, the signal strength of the surrounding electronic price tags is obtained, and if the electronic price tag positioning condition is met, the electronic price tag positioning result of the shopping cart is obtained by a signal strength weight solution method; in the process of inertial navigation positioning, if the scanning commodity identification positioning condition is met, the commodity position is positioned by scanning the commodity identification to obtain the scanning commodity identification positioning result of the shopping cart; based on the electronic price tag positioning result of the shopping cart or the scanning commodity identification positioning result, the inertial navigation positioning result of the shopping cart is corrected to obtain a first corrected positioning result of the shopping cart; according to the first corrected positioning result and a set of each path point pre-generated based on the supermarket map, the position of the path point closest to the first corrected positioning result is matched as the second corrected positioning result of the shopping cart, so as to improve the positioning accuracy of the shopping cart. The method for locating the shopping cart is introduced in detail below.

[0058] Existing smart shopping carts are generally equipped with smart devices such as tablet computers, which can be used to scan products by themselves for shopping and checkout. The positioning and navigation of smart shopping carts is a strong demand for supermarket shopping scenarios. The device for positioning the shopping cart proposed in the embodiment of the present invention (the device is used to execute the method for positioning the shopping cart in the embodiment of the present invention) can be set in the tablet computer, and of course it can also be independently installed at a suitable position on the shopping cart. The tablet on the shopping cart is equipped with an ESL module (the ESL module can be set in the device for positioning the shopping cart proposed in the embodiment of the present invention) to locate the shopping cart. The following is a detailed introduction.

[0059] 1. First, Bluetooth arrival angle positioning is introduced, including the above step 101.

[0060] Figure 2 FIG. 1 is a schematic diagram of the Bluetooth arrival angle positioning principle in an embodiment of the present invention. Figure 2 As shown, the Bluetooth angle of arrival positioning architecture mainly includes three main parts: AP (base station, such as Bluetooth AoA base station), shopping cart tablet (including the shopping cart positioning device provided by the embodiment of the present invention, that is, a device for executing the shopping cart positioning method provided by the embodiment of the present invention) and cloud service.

[0061] AP (base station, such as Bluetooth AoA base station) mainly includes electronic price tag processing module, arrival angle positioning sub-board and electronic price tag sub-board. The business process is that the electronic price tag sub-board receives the electronic price tag ( Figure 2 The arrival angle positioning signal is transmitted by the "electronic price tag" in the shopping cart tablet, and the IQ data is analyzed and sent to the arrival angle positioning client for azimuth and pitch angle calculation. The calculated angle information is sent to the mobile device message queue. When the shopping cart electronic price tag module pulls the angle package, the arrival angle positioning sub-board pulls the connection Device Angular package in .

[0062] like Figure 2 As shown, the shopping cart tablet is mainly divided into a display, a tablet application (the program can execute the shopping cart positioning method provided by the embodiment of the present invention), and positioning-related sensors. The sensors mainly include inertial navigation units (IMU) and electronic price tags. The display page mainly interacts with the user through the tablet application, including shopping, positioning, navigation, checkout, etc. The tablet application needs to download the server-side map, base station, electronic price tag location and product information during the store initialization phase, and will be dynamically updated if there are subsequent changes. The application logic of Bluetooth arrival angle positioning is that the shopping cart does not transmit the arrival angle positioning signal when it is not within the coverage range of the AP base station. The arrival angle positioning signal is only emitted when the shopping cart moves to within 4 meters (the first preset distance threshold) of the AP coverage range. The process of triggering arrival angle positioning is that the tablet application sends a message to the ESL module through the serial port ( Figure 2 The "electronic price tag" in the shopping cart tablet) transmits an AoA (angle of arrival) positioning signal. After receiving the message from the serial port, the ESL module immediately assembles the package and sends the angle of arrival positioning signal, delaying for a preset time, such as 90ms to 110ms, preferably 100ms (the delay time is sufficient to wait for the AP to complete the calculation of relevant parameters such as the AoA antenna array angle) to the synchronized AP to pull the AoA angle package information of the mobile device message, and return the AoA angle package to the tablet application. The tablet application receives the angle package information returned by the ESL (electronic price tag) and performs AoA position solution (such as Figure 2 ) and then display the calculated position result on the App screen (as shown in Figure 2 ), and store the location information locally and upload it to the server (such as Figure 2 The AoA (angle of arrival) positioning can be found in the introduction to AoA positioning in the fifth section below.

[0063] Server side (such as Figure 2The cloud platform shown in the figure is mainly responsible for the maintenance of positioning maps and locations. When the tablet application is opened, an initialization check is performed. If there is no information about maps, base stations, ESLs, and products, it is necessary to pull this information from the server. Data updates are updated and pulled by configuring intervals. The tablet application needs to record historical positioning information, package and report historical location data through scheduled tasks, and delete local historical data at the same time. The time interval for positioning tasks is configured on the server. If the Web side (accessed through a computer browser to view the real-time location of the shopping cart) has a need to display real-time location data, it is necessary to notify the tablet application to report the location information in real time through server-side scheduling. And notify the tablet application to end real-time reporting of location information after the real-time task is completed.

[0064] 2. Next, the inertial navigation positioning in the embodiment of the present invention, namely the above-mentioned step 102, is introduced.

[0065] Figure 3 The figure is a flow chart of inertial navigation positioning in the embodiment of the present invention. The initial position of the inertial navigation needs to be given by the Bluetooth arrival angle positioning result. The six-axis gyroscope and accelerometer of the IMU mainly update the attitude and convert the proportional coordinates. The integral of the acceleration obtains the velocity value. The gravity and gravitational model are used to correct the velocity. The displacement is obtained by integrating the velocity. The last positioning result is combined with the heading angle and displacement to obtain the position update. The attitude, velocity and position are output as inertial navigation parameters for the next cycle of inertial navigation calculation. Figure 3 As shown, the steps are as follows:

[0066] 1. Correction positioning results provide initial position (such as Figure 3 "Bluetooth Angle of Arrival Positioning Results", "Initialization Process"): When the system starts, positioning technology, such as Bluetooth AoA, is used to determine the initial position. This is because the inertial navigation system (INS) requires an accurate starting position to start navigation.

[0067] 2.IMU six-axis update and conversion (such as Figure 3 "IMU Gyroscope and Accelerometer" shown in the figure): Then, the IMU's six-axis gyroscope and accelerometer measurements are used to calculate the device's attitude and acceleration. The six-axis data includes a three-axis gyroscope (measuring angular velocity) and a three-axis accelerometer (measuring linear acceleration). Among them, the angular velocity measured by the gyroscope is used to update the device's attitude in real time. After obtaining the attitude, the accelerometer measurement results are converted from the device coordinate system to the navigation coordinate system using the attitude.

[0068] 3. Integrate the acceleration to get the velocity (e.g. Figure 3 Accelerometer, scaled coordinates, velocity as shown in ): By integrating the converted acceleration, the system can calculate the velocity of the device. This is the accumulation of acceleration over continuous time.

[0069] 4. Speed ​​correction (such as Figure 3 Speed ​​update shown): The system uses gravity and gravitational models to correct the calculated speed to eliminate the deviation caused by gravitational acceleration.

[0070] 5. Obtain displacement by velocity integration (e.g. Figure 3 Speed ​​update, position update shown): The corrected speed is converted into displacement data by integrating again, that is, the spatial movement distance from the last known position to the current position.

[0071] 6. Update the position by combining the heading angle and displacement (e.g. Figure 3 Position update shown): The system combines the last positioning result, heading angle (the direction of rotation of the device), and displacement data to update the current position. The heading angle can help determine the direction of movement, and the displacement gives the distance moved.

[0072] 7. Output attitude, speed and position parameters (such as Figure 3 Inertial navigation results shown): Finally, the updated attitude, velocity and position data are output as inertial navigation parameters for use in the next navigation cycle.

[0073] Since the inertial navigation has cumulative errors and depends on the accuracy of the input position, the shopping cart positioning result needs to provide a high-precision position for initial positioning and correction during the inertial navigation positioning process. The following introduces the relevant correction scheme.

[0074] 3. Next, the electronic price label positioning according to the embodiment of the present invention, namely the above-mentioned step 103, is introduced.

[0075] The embodiment of the present invention calculates the location of the shopping cart by scanning the RSSI information (signal strength information) of the surrounding ESL and then directly calculating the RSSI weight.

[0076] Figure 4 FIG. 1 is a flow chart of the electronic price label positioning process in an embodiment of the present invention. Figure 4 As shown in the figure, the shopping cart tablet needs to download the location information of the ESL in the supermarket from the server during the initialization phase. Since the ESL movement frequency is very low, the ESL location information in the supermarket can be updated once every half a day or a day. Figure 2 The "electronic price tag" shown in the figure needs to be set to long monitoring mode to monitor the heartbeat signals of the ESLs on the surrounding shelves and cache the IDs and RSSIs of these ESLs. The APP inside the tablet is responsible for scheduling, and the IMU module inside the tablet (such as Figure 2The "inertial navigation" shown in the figure can detect the movement state of the shopping cart. If the shopping cart is in motion, the ESL module on the tablet will obtain the monitored surrounding ESL at a higher frequency to avoid inaccurate surrounding ESL signals scanned after moving, which will lead to a decrease in positioning accuracy. Generally, shopping carts are in low-dynamic motion, and the threshold can be set to 1 second. The ESL module on the tablet only obtains the ESL results scanned in the last 1 second; if the shopping cart is stationary, the ESL module on the tablet can obtain the results of the surrounding ESL scanned in the last N seconds based on the length of time it is stationary.

[0077] The positioning APP in the tablet (such as Figure 2 The "tablet application" in the figure is responsible for positioning according to the results of scanning the surrounding ESLs. The more surrounding ESLs are scanned, the better the positioning effect. In order to ensure the positioning accuracy, it is necessary to meet the requirement that the number of surrounding ESLs is greater than or equal to the preset price tag number threshold, such as 3, and the RSSI (signal strength) is greater than or equal to -65dBm (the preset price tag signal strength threshold, which can be adjusted according to the ESL transmission power) to meet the conditions for electronic price tag positioning. General Bluetooth RSSI positioning methods include fingerprint matching positioning and RSSI weighted positioning. However, since the frequency of ESL sending heartbeats is not high, it cannot be guaranteed that the RSSI information of several surrounding ESLs will be scanned. In addition, the fingerprint matching method also requires the collection of fingerprint information in advance, so the embodiment of the present invention adopts the RSSI weighted positioning method.

[0078] The core of RSSI weighted positioning (i.e., signal strength weight calculation method) is to give a high weight ratio (greater than the preset weight threshold) to ESL (electronic price tag) that is close to the shopping cart (less than the preset weight calculation distance threshold) and has a large RSSI value (greater than the preset weight calculation strength threshold), and give a lower weight ratio (less than the preset weight threshold) to the electronic price tag that is far away from the shopping cart (greater than the preset weight calculation distance threshold) and has a large error (error greater than the preset error threshold). The weighted sum takes into account the location of the shopping cart. The weighted calculation formula can be: X=(X1*W1+X2*W2+X3*W3+...+Xn*Wn)*sumW, Wn=1 / (Rn-R1+A), where X represents the horizontal coordinate of the location of the shopping cart, X1, X2, X3...Xn are the horizontal coordinates of the locations of the electronic price tags participating in the positioning near the shopping cart, and W1, W2, W3...Wn are the horizontal coordinate weight information assigned to the electronic price tags corresponding to the horizontal coordinate positions X1, X2, X3...Xn, that is, according to: For electronic price tags that are close to the shopping cart and have large RSSI values, high weight ratios are given, and electronic price tags that are far away from the shopping cart and have large errors are given lower weights. This weight configuration strategy gives each electronic price tag a horizontal coordinate position weight, sumW represents the sum of all horizontal coordinate corresponding weights, A represents a constant, which can be 2, R1, R2, ... Rn are the field strength values ​​corresponding to the electronic price tags at each horizontal coordinate position X1, X2, X3 ... Xn; similarly, the vertical coordinate calculation of the shopping cart positioning position can be Referring to the calculation method of the horizontal coordinate of the positioning position of the shopping cart, the specific calculation method is as follows: Y=(Y1*W1'+Y2*W2'+Y3*W3'+...+Yn*Wn')*sumW', Wn'=1 / (Rn'-R1'+A), where Y represents the vertical coordinate of the positioning position of the shopping cart, Y1, Y2, Y3...Yn are the vertical coordinates of the positions of the electronic price tags participating in the positioning near the shopping cart, and W1', W2', W3'...Wn' are the electronic price tags corresponding to the vertical coordinate positions. The weight information assigned to the sub-price tags is based on the weight configuration strategy of "giving a high weight ratio to the electronic price tags that are closer to the shopping cart and have a large RSSI value, and giving a lower weight to the electronic price tags that are far away from the shopping cart and have a large error". sumW' represents the sum of the weights corresponding to all vertical coordinates, A represents a constant, which can be 2, and R1', R2', ... Rn' are the field strength values ​​corresponding to the electronic price tags at each vertical coordinate position Y1, Y2, Y3...Yn respectively.

[0079] Since ESL needs to run at low power consumption, the heartbeat cycle of ESL is generally a few minutes. Although there are many price tags, the heartbeat frequency is low. Therefore, if it cannot scan enough effective surrounding ESLs within a short time in motion (related to the moving speed, if the moving distance exceeds the threshold (for example, 3 meters)), it will not be positioned. In static state, the scanning time can be extended. If enough surrounding ESLs are scanned, positioning will be performed. The static state time can be accumulated longer, and the positioning accuracy can be improved. According to the positioning results, the spatial relationship (points within the surface) is used to determine which channel area it is in. If it is located in an inaccessible area such as a shelf or wall, it is pulled to the nearest channel area.

[0080] From the above, it can be seen that in one embodiment, during the inertial navigation positioning process, the signal strength of the surrounding electronic price tags is obtained. If the electronic price tag positioning conditions are met, the electronic price tag positioning result of the shopping cart is obtained by signal strength weighting, including:

[0081] Determine whether the current state of the shopping cart is static;

[0082] If the current state of the shopping cart is static, obtain the heartbeat of the scanned surrounding electronic price tags;

[0083] If the number of electronic price tags scanned with heartbeats is greater than or equal to the preset price tag number threshold, and the signal strength is greater than or equal to the preset price tag signal strength threshold, the signal strength weight solution is used to scan the surrounding electronic price tags and locate the electronic price tags of the shopping cart to obtain the positioning result.

[0084] In specific implementation, the above implementation method of scanning the RSSI information of the surrounding ESLs and then directly calculating the location of the shopping cart by RSSI weight calculation can improve the accuracy of ESL positioning, thereby improving the accuracy of shopping cart positioning.

[0085] From the above, it can be seen that in one embodiment, during the inertial navigation positioning process, the signal strength of the surrounding electronic price tags is obtained. If the electronic price tag positioning condition is met, the electronic price tag positioning result of the shopping cart is obtained by signal strength weighting solution, which may also include:

[0086] If the current state of the shopping cart is a moving state, determining whether the shopping cart has turned or traveled a distance greater than a third preset distance threshold;

[0087] If the collection of scanned surrounding electronic price tags is cleared, the surrounding electronic price tags are rescanned using the preset electronic price tag screening strategy;

[0088] If the number of electronic price tags whose heartbeats are scanned is greater than the preset threshold, and the signal strength is greater than or equal to the preset price tag signal strength threshold, the signal strength weight solution is used to scan the surrounding electronic price tags and locate the electronic price tags of the shopping cart to obtain the positioning result.

[0089] In specific implementation, the above implementation method of detecting the current state of the shopping cart and then locating the shopping cart can improve the accuracy of ESL positioning, thereby improving the accuracy of shopping cart positioning.

[0090] Fourth, the scanning and positioning of goods according to the embodiment of the present invention, namely the above-mentioned step 104, is introduced again.

[0091] Figure 5 FIG. 1 is a flow chart of scanning a commodity identification for positioning in an embodiment of the present invention. Figure 5 As shown, the logic of scanning and positioning of goods: when scanning goods through the shopping cart, the positioning status of the shopping cart is judged. If it is within the 10-second threshold (preset second threshold range) of the arrival angle positioning result or within the coverage range of the current base station, no correction is considered. If the electronic price tag positioning result is just completed within the 10-second threshold range, no correction is made; if neither of the above two situations is true or the confidence of the current output correction positioning result is low (lower than the preset confidence threshold), it is judged whether the shopping cart is scanning the product identification for the first time. If it is the first scan, the scanning time and location are recorded. If it is not the first scan, the distance between the current scanned product location and the last scanned product location is judged, and the speed of the shopping cart is calculated by the time interval between the two scans. If the speed is greater than the threshold (temporarily set to 2m / s), no correction (correction) is performed. If the speed is less than or equal to 2m / s, correction is performed. If the current product is bound to multiple ESLs, the sum of the Euclidean distances between the previous N (for example, 2) positioning results of the shopping cart and multiple ESLs is judged, and the one with the smallest sum of Euclidean distances is selected as the current positioning result. If only one ESL is bound, the current ESL position is the positioning result of the shopping cart.

[0092] As can be seen from the above, in one embodiment, during the inertial navigation positioning process, if the product identification scanning positioning condition is met, the product identification scanning positioning result of the shopping cart is obtained by locating the product position by scanning the product identification, which may include:

[0093] Determine the current positioning status of the shopping cart;

[0094] If the current positioning state of the shopping cart is not the following: the arrival angle positioning is completed within the preset second threshold range or within the current base station coverage range, the electronic price tag positioning is completed within the preset second threshold range, or the confidence of the current positioning result is lower than the preset confidence threshold, determine whether the shopping cart is scanning the product identification for the first time;

[0095] If it is not the first time to scan the product identification, determine the distance between the position of the product whose identification is currently scanned and the position of the product whose identification was last scanned;

[0096] Calculate the speed of the shopping cart based on the distance and the time interval between the current scanning of the product identification and the last scanning of the product identification;

[0097] If the speed of the shopping cart is less than or equal to the preset speed threshold, the scanning commodity identification positioning result of the shopping cart is obtained.

[0098] In a specific implementation, if the speed of the shopping cart is less than or equal to a preset speed threshold, obtaining the positioning result of the shopping cart's scanned product identification may include: if the speed of the shopping cart is less than or equal to the preset speed threshold, the position corresponding to the currently scanned product identification may be used as the current positioning position of the shopping cart.

[0099] In specific implementation, the above implementation method of locating the shopping cart by scanning the product identification can improve the accuracy of scanning the product identification and positioning, thereby improving the accuracy of shopping cart positioning.

[0100] As can be seen from the above, in one embodiment, during the inertial navigation positioning process, if the product identification positioning condition is met, the product identification is scanned to locate the product position, and the scanning product identification positioning result of the shopping cart is obtained, which may also include:

[0101] If the current product identified by the scan is bound to multiple electronic price tags, determine the sum of the Euclidean distances between the previous N positioning results of the shopping cart and each bound electronic price tag, where N is a positive integer greater than or equal to 2;

[0102] The electronic price tag position with the smallest total Euclidean distance is selected as the scanning product identification positioning result of the shopping cart.

[0103] In specific implementation, the above further implementation method of locating the shopping cart by scanning the product identification can improve the accuracy of scanning the product identification to obtain the product location, thereby improving the accuracy of shopping cart positioning.

[0104] 5. Again, a correction positioning is introduced, namely the above-mentioned step 105.

[0105] Figure 7 FIG. 1 is a schematic diagram of the principle of correcting and positioning in an embodiment of the present invention. Figure 7As shown in the figure, since Bluetooth arrival angle positioning belongs to absolute positioning, the accuracy can reach sub-meter level, and even in areas with good coverage angle of Bluetooth AoA base station, the positioning accuracy can reach decimeter level, so the scene of shopping cart correction positioning gives priority to the positioning scene of Bluetooth AoA. If it is within the coverage range of Bluetooth base station, Bluetooth AoA is used for positioning first. If it is not within the coverage range of base station, inertial navigation positioning is mainly used. Since inertial navigation positioning has cumulative errors, ESL system positioning (electronic price tag positioning) and scanning product positioning (scanning product logo positioning) are also needed to achieve seamless positioning in supermarket scenes for auxiliary positioning of special scenes. Before the positioning result is output, it is also necessary to correct the position (correction) and identify the channel through map matching to ensure that the positioning result appears in the reachable area of ​​the shopping cart. Figure 8 FIG. 1 is a flow chart of the shopping cart positioning process in an embodiment of the present invention. Figure 8 As shown, the correction positioning specifically includes:

[0106] During the initialization phase of the shopping cart, it is necessary to download the store map, all electronic price tag locations, product binding information, and base station information and store them on the local device (device installed on the shopping cart, such as a tablet). The positioning of the shopping cart starts when the tablet is taken off the charging wall and placed on the shopping cart. When it is placed on the shopping cart, the Hall sensor will have a trigger signal, which means the positioning of the shopping cart begins. The ESL module in the shopping cart tablet initially monitors the signals of the surrounding APs and the heartbeat signals of the surrounding ESLs.

[0107] like Figure 8 As shown, Bluetooth AoA (angle of arrival positioning) positioning, the AOA base station can currently configure the highest frequency of sending configurations is 1 time / s, the shopping cart can obtain RSSI information (signal strength information) and base station AP offset (the base station location is obtained based on the base station information downloaded by buyboost) once per second, if the RSSI is greater than or equal to the threshold (the preset base station signal strength threshold, the RSSI signal strength of the AoA coverage radius, for example Figure 8 or the distance between the shopping cart and the AOA base station is less than or equal to the first preset distance threshold (e.g. Figure 8 In one embodiment, in step 101, if the signal strength of the shopping cart corresponding to the current base station is greater than or equal to the preset base station signal strength threshold, or the distance between the shopping cart position and the current base station position is less than or equal to the first preset distance threshold, it is determined that the shopping cart is within the coverage of the current base station, and whether to transmit the Bluetooth AoA signal for positioning is controlled according to the current state, that is, when it is determined that the shopping cart is within the coverage of the current base station, the state of the shopping cart is determined, and if it is stationary, the transmission is stopped (such as Figure 8 If the arrival angle positioning signal is transmitted quickly in a moving state (such as Figure 8"Rapid Transmit AoA (3HZ)"), that is, when the shopping cart is judged to be in motion, the electronic price tag module of the shopping cart is controlled to send the arrival angle positioning signal to the current base station. If these two conditions are not met, it is determined that the shopping cart is outside the coverage of the AOA base station. That is, in one embodiment, in the above step 101, when the signal strength of the shopping cart corresponding to the current base station is less than the preset base station signal strength threshold, and the distance between the shopping cart position and the current base station position is greater than the first preset distance threshold, it is determined that the shopping cart is not within the coverage of the current base station. Figure 8 As shown, if the received base station RSSI signal is less than the threshold (-55dBm), it is directly positioned directly below the base station. For the detailed logic of arrival angle positioning, please refer to the introduction of Bluetooth arrival angle positioning in the first part. At this time, according to the arrival angle angle packet information obtained based on the arrival angle positioning signal fed back by the base station, the arrival angle position is solved to obtain the arrival angle positioning result. If the position result (arrival angle positioning result) solved by Bluetooth AoA is within the threshold (the second preset distance threshold, for example) with the current base station The Euclidean distance Figure 8 If the Euclidean distance between the angle of arrival positioning result and the current base station is less than or equal to the second preset distance threshold, then the AoA positioning result is used. ... Figure 8 When "s<=2 (threshold)" in the value, the arrival angle positioning result is used as the shopping cart positioning result. When the positioning App (tablet application) notifies the price tag module on the shopping cart to start fast reporting, it needs to read the package number of the price tag module through the serial port and record the package number for delay correction. Taking into account the ESL transmission signal, base station AoA signal processing and solution, ESL acquisition of AoA angle package information and network delay, the Bluetooth AoA solves the position and matches the position when the AoA signal is transmitted according to the package number, calculates the Bluetooth AoA correction (correction) XY, and then compensates the corrected XY to the current positioning result. Finally, the positioning result is input into the map matching module. The map matching module (the map matching module mentioned in the embodiment of the present invention is as follows Figure 8 After completing the path matching and the path point matching, the positioning result is output to the shopping cart tablet interface, and the positioning result is returned for correcting the inertial navigation.

[0108] Inertial navigation positioning: If the shopping cart is not within the coverage of the base station or the result of the angle of arrival positioning does not meet the conditions for correcting the position of the shopping cart, inertial navigation is used for continuous positioning. The sensor output data mode set by the inertial navigation is Game mode, and the time interval for outputting nine-axis data is 16~19ms. The inertial navigation module completes the position solution every 340ms, and the solved positioning result is input into the map matching module. After completing the path matching and path point matching, the map matching module outputs the positioning result to the shopping cart tablet interface and returns the positioning result for correcting the inertial navigation.

[0109] Scan around ESL positioning (i.e. Figure 8 The ESL module scans the heartbeats of the surrounding price tags (ESL) in real time to determine whether the current shopping cart is stationary. If it is stationary, it collects the heartbeats of the scanned surrounding price tags and performs a price tag screening strategy (preset electronic price tag screening strategy) at intervals of 5 seconds, 10 seconds, 15 seconds, etc. If the scanned ESL is greater than the threshold (preset price tag number threshold, such as 3) and the signal strength is greater than or equal to the preset price tag signal strength threshold, such as RSSI>=-65 (threshold), the number of scanned ESLs can also be equal to the preset price tag number threshold, such as Figure 4 As shown in "Number of surrounding price tags ≥ 3 && RSSI ≥ -65dBm", RSSI weight or other algorithms are used to scan the surrounding ESL for positioning. If the threshold is not met, positioning is not performed. If it is in motion, it is necessary to determine whether it is turning or traveling a long distance (greater than the third preset distance threshold, such as s> 6 meters), then the set of scanned surrounding ESLs needs to be cleared for rescanning, and then the price tag screening strategy is performed at intervals of 5 seconds, 10 seconds, 15 seconds, etc. If the scanned ESL exceeds the threshold (preset price tag number threshold, such as 3) and the signal strength is greater than or equal to the preset price tag signal strength threshold, such as RSSI>=-65 (threshold), RSSI weight or other algorithms are used to scan the surrounding ESL for positioning. If the threshold is not met, positioning is not performed. Finally, the positioning result of scanning the surrounding ESL is input into the map matching module. After completing the path matching and path point matching, the map matching module outputs the positioning result to the shopping cart tablet interface, and returns the positioning result for correcting the inertial navigation.

[0110] Scanning for auxiliary positioning of goods (i.e. scanning for positioning of goods identification). When scanning the identification of goods (e.g. QR code) through the barcode scanner of the shopping cart, determine whether the goods in the shopping cart are scanned for the first time. If it is the first time scanning, record the scanning time and location. If it is not the first time scanning, determine the distance between the location of the currently scanned goods and the location of the last scanned goods. Calculate the speed of the shopping cart by the time interval between the two scans. If the speed is greater than the threshold (preset speed threshold, e.g. 2m / s), do not perform positioning. If the speed is less than or equal to (preset speed threshold, e.g. 2m / s), perform positioning. Then determine whether the goods are bound to multiple price tags. If only one price tag is bound, output the positioning result. If multiple price tags are bound, obtain the previous N times, such as 2 times, and calculate the Euclidean distance with multiple price tags. Select the one with the shortest Euclidean distance as the location of the current electronic price tag, i.e. the location result of the goods as the scanning product identification positioning result of the shopping cart. Finally, the positioning result of the scanned surrounding ESL is input into the map matching module (the function implemented by the map matching module mentioned in the embodiment of the present invention is completed by the second correction positioning unit). After completing the path matching and path point matching, the map matching module outputs the positioning result to the shopping cart tablet interface, and returns the positioning result for correcting the inertial navigation.

[0111] The map matching module obtains the positioning results according to the order of priority. The priority order can be Bluetooth arrival angle positioning results, scanning surrounding ESL positioning results, scanning product positioning results and inertial navigation positioning results. Finally, the corrected positioning results are output to the shopping cart tablet for positioning and navigation display.

[0112] 6. Next, the map matching secondary correction positioning in the embodiment of the present invention, namely the above-mentioned step 106, is introduced.

[0113] Map matching - waypoint matching strategy

[0114] Figure 6This is a schematic diagram of the map matching-path point matching process in an embodiment of the present invention. When a shopping cart moves in a shopping mall, some positioning scenarios need to consider using map matching to solve the problem of positioning deviation. The main scenario considered by map matching is that if the positioning result is located on a shelf, a pile head, a wall or other inaccessible area, it needs to be corrected to a locatable area through map matching. In the pre-stage, path points are automatically generated according to the road network (the set of all channels that the shopping cart can travel in the supermarket scene) and the set line segment threshold, and the path points are adjusted so that the path points coincide with the turning points and intersections. In the initialization stage, the map matching module generates path points and generates each path point set and its neighbor set at the same time. In the secondary correction stage, after the correction positioning result is solved, the map matching stage is entered, and the correction positioning results are merged according to the frequency of the generation of the correction positioning results (taking the average of n points). In the matching phase, the nearest path point is found based on the corrected positioning result, and it is determined whether the path point should be switched. The results of the shopping cart positioning are ultimately aggregated to the path point (path point). For example, the word switch can mean that the last positioning was to path point 1, and the next positioning is to path point 2. If there is no switch, the map matching result is returned directly. If the current path point needs to be switched, it is necessary to first determine whether the switched path point is a neighbor path point of the previous path point. If so, the result of the previous path point is returned. If not, the neighbor path point closest to the previous path point is found, and then the positioning result is returned. For example, Fig. 9 Schematic diagram of switching path points in an embodiment of the present invention. Fig. 9 As shown, yellow is the last positioning result. If the next positioning result is red 1, the nearest path point is still yellow, so do not switch. If the next positioning result is red 2, and the nearest neighbor point (path point) of the last positioning result is green, then switch to the green path point. This method can prevent positioning jumps and optimize positioning effects. From the above, it can be seen that the solutions to further prevent positioning jumps and further optimize positioning effects include:

[0115] As can be seen from the above, in one embodiment, the shopping cart positioning method may further include: when it is determined that the current path point needs to be switched, determining whether the path point to be switched is a neighboring path point of the previous path point;

[0116] When it is determined that the switched path point is not a neighbor path point of the previous path point, the neighbor path point closest to the previous path point is found as the positioning result of the shopping cart optimization.

[0117] It can be seen from the above that, in one embodiment, the shopping cart positioning method may further include: when it is determined that the current path point does not need to be switched, using the map matching result as an optimized positioning result.

[0118] From the above, it can be seen that in one embodiment, the above shopping cart positioning method may further include: when it is determined that the switched path point is a neighbor path point of the previous path point, using the result of the neighbor path point as the optimized correction positioning result.

[0119] During specific implementation, further preventing positioning jumps and optimizing positioning effects can improve user experience and ensure the continuity of shopping cart navigation.

[0120] The present invention also provides a device for locating a shopping cart, as described in the following embodiments. Since the principle of the device to solve the problem is similar to that of the method for locating a shopping cart, the implementation of the device can refer to the implementation of the method for locating a shopping cart, and the repeated parts will not be repeated.

[0121] Fig.10 FIG. 1 is a schematic diagram of the structure of a device for positioning a shopping cart in an embodiment of the present invention. Fig.10 As shown, the device comprises:

[0122] A determination unit 01 is used to determine whether the shopping cart is within the coverage of the current base station;

[0123] The inertial navigation positioning unit 02 is used to locate the shopping cart by using the inertial navigation positioning method when it is determined that the shopping cart is not within the coverage of the current base station, and obtain the inertial navigation positioning result of the shopping cart;

[0124] The electronic price tag positioning unit 03 is used to obtain the signal strength of the surrounding electronic price tags during the inertial navigation positioning process. If the electronic price tag positioning conditions are met, the electronic price tag positioning result of the shopping cart is obtained by signal strength weighting calculation;

[0125] The product identification scanning and positioning unit 04 is used to obtain the product identification scanning and positioning result of the shopping cart by scanning the product identification and positioning the product position if the product identification scanning and positioning condition is met during the inertial navigation positioning process;

[0126] A first correction positioning unit 05 is used to perform position correction processing on the inertial navigation positioning result of the shopping cart based on the positioning result of the electronic price tag of the shopping cart or the positioning result of scanning the product logo, so as to obtain a first correction positioning result of the shopping cart;

[0127] The second correction positioning unit 06 is used to match the position of the path point closest to the first correction positioning result as the second correction positioning result of the shopping cart according to the first correction positioning result and a set of each path point pre-generated based on the supermarket map.

[0128] In one embodiment, the judgment unit is specifically used to:

[0129] If the signal strength of the shopping cart corresponding to the current base station is greater than or equal to the preset base station signal strength threshold, or the distance between the shopping cart location and the current base station location is less than or equal to the first preset distance threshold, it is determined that the shopping cart is within the coverage range of the current base station.

[0130] In one embodiment, the above-mentioned shopping cart positioning device may further include an arrival angle positioning unit, which is used to:

[0131] When it is determined that the shopping cart is within the coverage of the current base station, the state of the shopping cart is determined;

[0132] When it is determined that the shopping cart is in motion, the electronic price tag module of the shopping cart is controlled to send an arrival angle positioning signal to the current base station;

[0133] According to the arrival angle package information obtained based on the arrival angle positioning signal fed back by the base station, the arrival angle position is solved to obtain the arrival angle positioning result;

[0134] If the Euclidean distance between the angle-of-arrival positioning result and the current base station is less than or equal to the second distance threshold, the angle-of-arrival positioning result is used as the shopping cart positioning result.

[0135] In one embodiment, the electronic price label positioning unit is specifically used for:

[0136] Determine whether the current state of the shopping cart is static;

[0137] If the current state of the shopping cart is static, obtain the heartbeat of the scanned surrounding electronic price tags;

[0138] If the number of electronic price tags scanned with heartbeats is greater than or equal to the preset price tag number threshold, and the signal strength is greater than or equal to the preset price tag signal strength threshold, the signal strength weight solution is used to scan the surrounding electronic price tags and locate the electronic price tags of the shopping cart to obtain the positioning result.

[0139] In one embodiment, the electronic price label positioning unit is also used for:

[0140] If the current state of the shopping cart is a moving state, determining whether the shopping cart has turned or traveled a distance greater than a third preset distance threshold;

[0141] If the collection of scanned surrounding electronic price tags is cleared, the surrounding electronic price tags are rescanned using the preset electronic price tag screening strategy;

[0142] If the number of electronic price tags whose heartbeats are scanned is greater than the preset threshold, and the signal strength is greater than or equal to the preset price tag signal strength threshold, the signal strength weight solution is used to scan the surrounding electronic price tags and locate the electronic price tags of the shopping cart to obtain the positioning result.

[0143] In one embodiment, the above-mentioned commodity identification scanning and positioning unit is specifically used for:

[0144] Determine the current positioning status of the shopping cart;

[0145] If the current positioning state of the shopping cart is not the following: the arrival angle positioning is completed within the preset seconds threshold or within the current base station coverage, the electronic price tag positioning is completed within the preset seconds threshold, or the confidence of the current positioning result is lower than the preset confidence threshold, determine whether the shopping cart is scanning the product identification for the first time;

[0146] If it is not the first time to scan the product identification, determine the distance between the position of the product whose identification is currently scanned and the position of the product whose identification was last scanned;

[0147] Calculate the speed of the shopping cart based on the distance and the time interval between the current scanning of the product identification and the last scanning of the product identification;

[0148] If the speed of the shopping cart is less than or equal to the preset speed threshold, the scanning commodity identification positioning result of the shopping cart is obtained.

[0149] In one embodiment, the above-mentioned commodity identification scanning and positioning unit is also used for:

[0150] If the current product identified by the scan is bound to multiple electronic price tags, determine the sum of the Euclidean distances between the previous N positioning results of the shopping cart and each bound electronic price tag, where N is a positive integer greater than or equal to 2;

[0151] The electronic price tag position with the smallest total Euclidean distance is selected as the scanning product identification positioning result of the shopping cart.

[0152] An embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned shopping cart positioning method when executing the computer program.

[0153] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned shopping cart positioning method is implemented.

[0154] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method for locating a shopping cart is implemented.

[0155] Compared with the shopping cart positioning technical solution with low positioning accuracy in the prior art, the shopping cart positioning solution provided by the embodiment of the present invention has the following beneficial technical effects: the embodiment of the present invention determines whether the shopping cart is within the coverage of the current base station; when it is determined that the shopping cart is not within the coverage of the current base station, the shopping cart is positioned by an inertial navigation positioning method to obtain the inertial navigation positioning result of the shopping cart; in the process of inertial navigation positioning, the signal strength of the surrounding electronic price tags is obtained, and if the electronic price tag positioning condition is met, the electronic price tag positioning result of the shopping cart is obtained by a signal strength weight solution method; in the process of inertial navigation positioning, if the scanning commodity identification positioning condition is met, the commodity position is positioned by scanning the commodity identification to obtain the scanning commodity identification positioning result of the shopping cart; based on the electronic price tag positioning result of the shopping cart or the scanning commodity identification positioning result, the inertial navigation positioning result of the shopping cart is corrected to obtain a first corrected positioning result of the shopping cart; according to the first corrected positioning result and a set of each path point pre-generated based on the supermarket map, the position of the path point closest to the first corrected positioning result is matched as the second corrected positioning result of the shopping cart, which can improve the positioning accuracy of the shopping cart.

[0156] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0157] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0158] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0159] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0160] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for locating a shopping cart, characterized in that: include: Determine whether the shopping cart is within the coverage of the current base station; When it is determined that the shopping cart is not within the coverage of the current base station, the shopping cart is positioned using an inertial navigation positioning method to obtain an inertial navigation positioning result of the shopping cart; During the inertial navigation positioning process, the signal strength of the surrounding electronic price tags is obtained. If the electronic price tag positioning conditions are met, the electronic price tag positioning result of the shopping cart is obtained by solving the signal strength weight. During the inertial navigation positioning process, if the product identification scanning positioning condition is met, the product identification scanning positioning result of the shopping cart is obtained by locating the product position by scanning the product identification; Performing position correction processing on the inertial navigation positioning result of the shopping cart based on the positioning result of the electronic price tag of the shopping cart or the positioning result of the scanned product logo, to obtain a first corrected positioning result of the shopping cart; According to the first corrected positioning result and a set of each path point pre-generated based on the supermarket map, the position of the path point closest to the first corrected positioning result is matched and obtained as the second corrected positioning result of the shopping cart.

2. The method according to claim 1, characterized in that Determine whether the shopping cart is within the coverage of the current base station, including: If the signal strength of the shopping cart corresponding to the current base station is greater than or equal to the preset base station signal strength threshold, or the distance between the shopping cart location and the current base station location is less than or equal to the first preset distance threshold, it is determined that the shopping cart is within the coverage range of the current base station.

3. The method according to claim 2, characterized in that Also includes: When it is determined that the shopping cart is within the coverage of the current base station, the state of the shopping cart is determined; When it is determined that the shopping cart is in motion, the electronic price tag module of the shopping cart is controlled to send an arrival angle positioning signal to the current base station; According to the arrival angle package information obtained based on the arrival angle positioning signal fed back by the base station, the arrival angle position is solved to obtain the arrival angle positioning result; If the Euclidean distance between the arrival angle positioning result and the current base station is less than or equal to the second preset distance threshold, the arrival angle positioning result is used as the shopping cart positioning result.

4. The method according to claim 1, characterized in that During the inertial navigation positioning process, the signal strength of the surrounding electronic price tags is obtained. If the electronic price tag positioning conditions are met, the electronic price tag positioning result of the shopping cart is obtained by signal strength weighting, including: Determine whether the current state of the shopping cart is static; If the current state of the shopping cart is static, obtain the heartbeat of the scanned surrounding electronic price tags; If the number of electronic price tags scanned with heartbeats is greater than or equal to the preset price tag number threshold, and the signal strength is greater than or equal to the preset price tag signal strength threshold, the signal strength weight solution is used to scan the surrounding electronic price tags and locate the electronic price tags of the shopping cart to obtain the positioning result.

5. The method according to claim 4, characterized in that Also includes: If the current state of the shopping cart is a moving state, determining whether the shopping cart has turned or traveled a distance greater than a third preset distance threshold; If the collection of scanned surrounding electronic price tags is cleared, the surrounding electronic price tags are rescanned using the preset electronic price tag screening strategy; If the number of electronic price tags whose heartbeats are scanned is greater than the preset threshold, and the signal strength is greater than or equal to the preset price tag signal strength threshold, the signal strength weight solution is used to scan the surrounding electronic price tags and locate the electronic price tags of the shopping cart to obtain the positioning result.

6. The method according to claim 1, characterized in that During the inertial navigation positioning process, if the product identification scanning positioning conditions are met, the product identification scanning positioning result of the shopping cart is obtained by locating the product position by scanning the product identification, including: Determine the current positioning status of the shopping cart; If the current positioning state of the shopping cart is not the following: the arrival angle positioning is completed within the preset second threshold range or within the current base station coverage range, the electronic price tag positioning is completed within the preset second threshold range, or the confidence of the current positioning result is lower than the preset confidence threshold, determine whether the shopping cart is scanning the product identification for the first time; If it is not the first time to scan the product identification, determine the distance between the position of the product whose identification is currently scanned and the position of the product whose identification was last scanned; Calculate the speed of the shopping cart based on the distance and the time interval between the current scanning of the product identification and the last scanning of the product identification; If the speed of the shopping cart is less than or equal to the preset speed threshold, the scanning commodity identification positioning result of the shopping cart is obtained.

7. The method according to claim 6, characterized in that Also includes: If the current product identified by the scan is bound to multiple electronic price tags, determine the sum of the Euclidean distances between the previous N positioning results of the shopping cart and each bound electronic price tag, where N is a positive integer greater than or equal to 2; The electronic price tag position with the smallest total Euclidean distance is selected as the scanning product identification positioning result of the shopping cart.

8. A device for positioning a shopping cart, characterized in that: include: A determination unit, used to determine whether the shopping cart is within the coverage of the current base station; The inertial navigation positioning unit is used to locate the shopping cart by using the inertial navigation positioning method when it is determined that the shopping cart is not within the coverage of the current base station, and obtain the inertial navigation positioning result of the shopping cart; The electronic price tag positioning unit is used to obtain the signal strength of the surrounding electronic price tags during the inertial navigation positioning process. If the electronic price tag positioning conditions are met, the electronic price tag positioning result of the shopping cart is obtained by signal strength weighting calculation; The product identification scanning and positioning unit is used to obtain the product identification scanning and positioning result of the shopping cart by scanning the product identification and locating the product position if the product identification scanning and positioning conditions are met during the inertial navigation positioning process; A first correction positioning unit is used to perform position correction processing on the inertial navigation positioning result of the shopping cart based on the positioning result of the electronic price tag of the shopping cart or the positioning result of scanning the product logo, so as to obtain a first correction positioning result of the shopping cart; The second correction positioning unit is used to match the position of the path point closest to the first correction positioning result as the second correction positioning result of the shopping cart based on the first correction positioning result and a set of each path point pre-generated based on the supermarket map.

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

10. 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 method according to any one of claims 1 to 7 is implemented.

11. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images