Electronic price tag positioning method and device

Abstract

The invention discloses an electronic price tag positioning method and device. The method comprises the following steps: selecting an AOA anchor point based on a map in a to-be-positioned scene and arrival angle positioning results of all electronic price tags; dividing a map in a to-be-positioned scene into a credible area and an uncredible area; all electronic price tag neighbors in the scene to be positioned are positioned based on the AOA anchor point information; carrying out fusion repositioning on the price tags of which the neighbor positioning results are located in the incredible area based on the arrival angle positioning and the neighbor positioning results: positioning the price tags of which the neighbor positioning results are located in the incredible area to the nearest goods shelf according to the position relationship between the arrival angle positioning results of the price tags and the goods shelves; abnormal goods shelves are detected and positioned according to the number of price tags on the goods shelves and the feature information; and adjusting the positioning result of the electronic price tag on the abnormal positioning goods shelf according to the feature information of the price tag on the abnormal positioning goods shelf and the neighbor positioning result. The positioning precision of the electronic price tag can be improved.

Description

Technical Field

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

[0002] This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. No statement herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] Indoor positioning technology has played a significant role in areas such as asset management, cargo tracking, and warehouse management. Accurate location information is crucial for improving user experience. However, due to the diverse layouts of indoor scenarios, the signal propagation environment is relatively complex, and a single technical solution cannot effectively solve positioning problems in all scenarios.

[0004] Existing positioning methods use AOA (Angle of Arrival) information. These methods deploy base stations within a specific area to obtain the azimuth and elevation of the signal source. Using the elevation and azimuth of a single base station and the signal source's altitude, or the combined azimuth information of multiple base stations, they can calculate and locate the target signal source. This positioning method requires direct line of sight between the signal source and the base station, further exacerbating positioning challenges and leading to inaccurate positioning.

[0005] Fingerprint-based positioning methods exist in existing technologies. These methods pre-acquire the location information of a portion of signal sources as anchor points, then collect RSSI (Received Signal Strength) information from each target signal source. This RSSI information is matched with the RSSI information of the anchor points, and the distance relationship is determined based on the similarity, thereby locating the remaining target signal sources. However, this positioning method has a high granularity in the relationship between features such as RSSI information and distance, which can easily introduce large positioning errors.

[0006] Therefore, existing indoor positioning methods have the problem of insufficient positioning accuracy or large positioning error. Summary of the Invention

[0007] An embodiment of the present invention provides a method for positioning an electronic price tag to improve the positioning accuracy of the electronic price tag. The method includes:

[0008] Obtain the map of the scene to be positioned, AOA base station location information, and arrival angle positioning results of all electronic price tags;

[0009] Based on the map of the scene to be positioned and the arrival angle positioning results of all electronic price tags, the electronic price tags with positioning accuracy higher than the preset threshold are selected as AOA anchor points;

[0010] Based on the AOA base station location information in the scene to be positioned, the map of the scene to be positioned is divided into a trusted area and an untrusted area;

[0011] Based on the information of the selected AOA anchor point, all the electronic price tags in the scene to be positioned are positioned, and the neighbor positioning results of all the electronic price tags in the scene to be positioned are obtained;

[0012] For electronic price tags whose neighbor positioning results are located in untrustworthy areas, the following fusion relocation steps are performed based on the arrival angle positioning results and the neighbor positioning results: according to the relationship between the arrival angle positioning results of the electronic price tags and the position of the shelves, the electronic price tags whose neighbor positioning results are located in the untrustworthy areas are positioned to the nearest shelves; according to the number and feature information of the electronic price tags on the shelves, the shelves with abnormal positioning are detected; according to the feature information of the electronic price tags on the shelves with abnormal positioning and the neighbor positioning results, the positioning results of the electronic price tags on the shelves with abnormal positioning are adjusted to obtain the final positioning results of the electronic price tags.

[0013] An embodiment of the present invention further provides a positioning device for an electronic price tag, for improving the positioning accuracy of the electronic price tag, the device comprising:

[0014] An acquisition unit is used to obtain the map of the scene to be positioned, the location information of the AOA base station, and the arrival angle positioning results of all electronic price tags;

[0015] An AOA anchor point determination unit is configured to select an electronic price tag with a positioning accuracy higher than a preset threshold as an AOA anchor point based on a map of the scene to be positioned and the arrival angle positioning results of all electronic price tags;

[0016] A region division unit is used to divide the map of the scene to be positioned into a trusted area and an untrusted area based on the AOA base station location information of the scene to be positioned;

[0017] A neighbor positioning unit is used to locate the neighbors of all electronic price tags in the scene to be positioned based on the information of the selected AOA anchor point, and obtain the neighbor positioning results of all electronic price tags in the scene to be positioned;

[0018] The fusion relocation unit is used to perform the following fusion relocation steps for the electronic price tags whose neighbor positioning results are located in the untrustworthy area based on the arrival angle positioning results and the neighbor positioning results: according to the relationship between the arrival angle positioning results of the electronic price tags and the positions of the shelves, the electronic price tags whose neighbor positioning results are located in the untrustworthy area are positioned to the nearest shelves; according to the number and feature information of the electronic price tags on the shelves, the shelves with abnormal positioning are detected; according to the feature information of the electronic price tags on the shelves with abnormal positioning and the neighbor positioning results, the positioning results of the electronic price tags on the shelves with abnormal positioning are adjusted to obtain the final positioning results of the electronic price tags.

[0019] An embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned electronic price tag positioning method when executing the computer program.

[0020] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the computer program implements the above-mentioned electronic price tag positioning method.

[0021] 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 computer program implements the above-mentioned positioning method of the electronic price tag.

[0022] In the embodiment of the present invention, the positioning solution of the electronic price tag is compared with the technical solutions with insufficient positioning accuracy or large positioning errors in the prior art. The method comprises the following steps: obtaining a map of the scene to be positioned, the location information of the AOA base station, and the arrival angle positioning results of all the electronic price tags; selecting an electronic price tag with a positioning accuracy higher than a preset threshold as an AOA anchor point based on the map of the scene to be positioned and the arrival angle positioning results of all the electronic price tags; dividing the map of the scene to be positioned into a trusted area and an untrusted area based on the location information of the AOA base station in the scene to be positioned; locating the neighbors of all the electronic price tags in the scene to be positioned based on the information of the selected AOA anchor point, and obtaining the neighboring information of all the electronic price tags in the scene to be positioned. The positioning result is obtained; for the electronic price tags whose neighbor positioning results are located in the untrustworthy area, the following fusion repositioning steps are performed based on the arrival angle positioning result and the neighbor positioning result: according to the position relationship between the arrival angle positioning result of the electronic price tag and the shelf, the electronic price tags whose neighbor positioning results are located in the untrustworthy area are positioned to the nearest shelf; according to the number and feature information of the electronic price tags on the shelf, the abnormally positioned shelves are detected; according to the feature information of the electronic price tags on the abnormally positioned shelves and the neighbor positioning results, the positioning results of the electronic price tags on the abnormally positioned shelves are adjusted to obtain the final positioning results of the electronic price tags. This can achieve full-scene high-precision positioning based on the fusion of AOA and neighbor relationship information, thereby improving the positioning accuracy of the electronic price tags. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] 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 the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0024] Figure 1 Schematic diagram of the flow of the positioning method of the electronic price label in an embodiment of the present invention;

[0025] Figure 2 1 is a flow chart of a method for locating an electronic price tag according to another embodiment of the present invention;

[0026] Figure 3 Schematic diagram of the relationship between the stack head and the adjacent shelves in an embodiment of the present invention;

[0027] Figure 4 Schematic diagram of a neighbor relationship weight table in an embodiment of the present invention;

[0028] Figure 5 Schematic diagram of the structure of the positioning device of the electronic price label in an embodiment of the present invention;

[0029] Figure 6 FIG. 1 is a schematic diagram of the structure of a computer device according to an embodiment of the present invention.

[0030] Reference numerals: 500 , computer device; 510 , memory; 520 , processor; 530 , computer program. DETAILED DESCRIPTION

[0031] To make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below with reference to 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.

[0032] The acquisition, storage, use, and processing of data in the technical solution of this application comply with relevant laws and regulations.

[0033] An embodiment of the present invention provides a positioning solution for electronic price tags that implements full-scenario positioning based on the fusion of AOA and neighbor relationship information. This embodiment of the present invention primarily achieves automatic acquisition of anchor points by fusing neighbor relationships and AOA information. It uses AOA information for positioning in areas with good AOA base station coverage, uses neighbor relationships for positioning in uncovered areas, and fuses both information in areas with fuzzy coverage, achieving high-precision positioning in all scenarios. The following is a detailed introduction to the positioning solution for electronic price tags.

[0034] Figure 1 FIG. 1 is a flow chart of a method for locating an electronic price tag according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0035] Step 101: Obtain a map of the scene to be positioned, AOA base station location information, and arrival angle positioning results of all electronic price tags;

[0036] Step 102: Based on the map of the scene to be positioned and the arrival angle positioning results of all electronic price tags, select the electronic price tag with a positioning accuracy higher than a preset threshold as the AOA anchor point;

[0037] Step 103: Based on the AOA base station location information in the scene to be positioned, the map of the scene to be positioned is divided into a trusted area and an untrusted area;

[0038] Step 104: Based on the information of the selected AOA anchor point, all the electronic price tags in the scene to be positioned are positioned, and the neighbor positioning results of all the electronic price tags in the scene to be positioned are obtained;

[0039] Step 105: For the electronic price tags whose neighbor positioning results are located in the untrustworthy area, the following fusion relocation steps are performed based on the arrival angle positioning results and the neighbor positioning results: according to the relationship between the arrival angle positioning results of the electronic price tags and the position of the shelves, the electronic price tags whose neighbor positioning results are located in the untrustworthy area are positioned to the nearest shelves; according to the number and feature information of the electronic price tags on the shelves, the shelves with abnormal positioning are detected; according to the feature information of the electronic price tags on the shelves with abnormal positioning and the neighbor positioning results, the positioning results of the electronic price tags on the shelves with abnormal positioning are adjusted to obtain the final positioning results of the electronic price tags.

[0040] The positioning method of an electronic price tag provided by an embodiment of the present invention, when working: obtains a map of the scene to be positioned, AOA base station location information and arrival angle positioning results of all electronic price tags; based on the map of the scene to be positioned and the arrival angle positioning results of all electronic price tags, selects an electronic price tag with a positioning accuracy higher than a preset threshold as an AOA anchor point; based on the AOA base station location information of the scene to be positioned, divides the map of the scene to be positioned into a trusted area and an untrusted area; based on the information of the selected AOA anchor point, locates the neighbors of all electronic price tags in the scene to be positioned, and obtains the neighbor positioning results of all electronic price tags in the scene to be positioned; For electronic price tags whose neighbor positioning results are located in untrustworthy areas, the following fusion relocation steps are performed based on the arrival angle positioning results and the neighbor positioning results: based on the positional relationship between the arrival angle positioning results of the electronic price tags and the shelves, the electronic price tags whose neighbor positioning results are located in the untrustworthy areas are positioned to the nearest shelves; based on the number and feature information of the electronic price tags on the shelves, the shelves with abnormal positioning are detected; based on the feature information of the electronic price tags on the shelves with abnormal positioning and the neighbor positioning results, the positioning results of the electronic price tags on the shelves with abnormal positioning are adjusted to obtain the final positioning results of the electronic price tags. This can achieve full-scene high-precision positioning based on the fusion of AOA and neighbor relationship information.

[0041] Compared to existing solutions that suffer from insufficient positioning accuracy or large positioning errors, the positioning method for electronic price tags provided by the embodiments of the present invention can achieve high-precision positioning in all scenarios based on the fusion of AOA and neighbor relationship information, thereby improving the positioning accuracy of electronic price tags. The following describes this positioning method for electronic price tags in detail.

[0042] The embodiment of the present invention relates to the field of wireless positioning technology, and relates to a positioning method for electronic price tags, which is a full-scene positioning method based on the fusion of AOA and neighbor information. Figure 2 This is a flow chart of a method for locating an electronic price tag according to another embodiment of the present invention. Figures 2 to 4 The positioning method of the electronic price tag provided by the embodiment of the present invention is described in detail:

[0043] In the embodiment of the present invention, the key shelf may be a preset display location in the scene to be positioned, for example Figure 3 The key coverage area of ​​the base station signal can be: the coverage area within the normal pitch angle range of the base station preset angle, such as the coverage area within the normal pitch angle range of 60 degrees of the base station, for example Figure 3 The circular area is formed with BS as the center and the radius of the key coverage area.

[0044] First, as Figure 2 As shown, a map of the scene to be positioned, AOA base station location information, and arrival angle positioning results for all electronic price tags are obtained. The scene to be positioned can be, for example, a supermarket or pharmacy, or a specific area within a scene, such as the rice, flour, grain, and oil area on the second basement floor of a supermarket or the traditional Chinese medicine area of ​​a pharmacy. The map can include information such as the location and size of all shelves, as well as key shelf identifiers. This step is equivalent to step 101 above.

[0045] Second, based on the map of the scene to be positioned and the arrival angle positioning results of all electronic price tags, such as Figure 2 As shown, the price tag with higher position accuracy is selected as the anchor point through the AOA anchor point selection strategy, that is, the electronic price tag with positioning accuracy higher than the preset threshold is selected as the AOA anchor point, that is, the above step 102.

[0046] In one embodiment, based on a map of the scene to be positioned and the arrival angle positioning results of all electronic price tags, selecting an electronic price tag with a positioning accuracy higher than a preset threshold as an AOA anchor point may include:

[0047] Obtaining historical positioning information of each electronic price tag having an arrival angle positioning result; the historical positioning information of each electronic price tag may be the arrival angle historical positioning information of each electronic price tag. Of course, the historical positioning information may also be positioning information obtained by other means, which is not limited here;

[0048] Calculate the average value of the historical positioning position of each electronic price tag and the variance of the historical positioning position of each electronic price tag based on the historical positioning information of each electronic price tag;

[0049] Determine the minimum distance between the average value of the historical positioning position of each electronic shelf label and any edge position of the nearest key shelf;

[0050] The electronic price tag whose variance of historical positioning position is less than the first preset variance threshold, the number of arrival angle positioning results is greater than the preset value and the minimum distance is less than the preset distance threshold is used as the AOA anchor point.

[0051] During specific implementation, multiple historical positioning information of each electronic price tag with AOA positioning results is obtained. Furthermore, the average position and the variance of the positioning position of each price tag are calculated. According to the average value of the historical positioning position of each price tag, the minimum distance to any edge of the nearest key shelf (which can also be a key shelf with richer AOA positioning results) is calculated. If the average value of the historical positioning position of the price tag falls on the key shelf, the minimum distance between the average value and any side of the key shelf is 0. Set the judgment condition for determining the AOA anchor point: the variance of the price tag position (the sum of the variances of the horizontal and vertical coordinates) needs to be less than the set threshold (preset variance threshold, such as 500cm 2 ), the number of arrival angle positioning results is greater than the preset value, and the aforementioned minimum distance is also less than the corresponding set threshold (preset distance threshold, such as 20cm). This results in the preliminary selection of AOA anchor points, namely the AOA anchor points. This enables automatic, efficient, and high-precision selection of AOA anchor points, further improving the positioning accuracy of electronic price tags. The following describes a further implementation plan for optimizing the selection of the initially selected AOA anchor points.

[0052] In one embodiment, the positioning method of the electronic price tag may further include screening multiple AOA anchor points to obtain an optimized AOA anchor point according to the following method:

[0053] Multiple AOA anchor points are grouped according to shelf information, and the AOA anchor point corresponding to each shelf is each group of AOA anchor points;

[0054] According to the size feature information of the electronic price tag, each group of AOA anchor points is screened, and the AOA anchor points with the same size type and the largest number are obtained as the optimized AOA anchor points.

[0055] During implementation, the preliminary results are grouped according to shelf information and filtered based on feature information such as price tag size, retaining only the size with the highest proportion. This means that each group of AOA anchor points is filtered based on the size feature information of the electronic price tag, and the AOA anchor points with the same size type and the largest number are selected as the optimized AOA anchor points. For example, if a group of AOA anchor points has three 7.2-size types and one 5.4-size type, then the three 7.2-size electronic price tags are selected as the optimized AOA anchor points. If there is one 7.2-size, one 5.4-size, and one 3.3-size, then one size type AOA anchor point is randomly selected as the optimized AOA anchor point. This is not limited to size information; other feature information of the electronic price tag, such as category, can also be used to filter anchor points to obtain optimized AOA anchor points. This can improve the accuracy of AOA anchor selection, and thus further improve the accuracy of electronic price tag positioning.

[0056] In one embodiment, the positioning method of the electronic price tag may further include screening multiple AOA anchor points to obtain an optimized AOA anchor point according to the following method:

[0057] Multiple AOA anchor points are grouped according to shelf information, and the AOA anchor point corresponding to each shelf is each group of AOA anchor points;

[0058] Each group of AOA anchor points is screened based on the variance of the historical positioning positions of the AOA anchor points, and the AOA anchor points in each group whose variance of the historical positioning positions is less than a second preset variance threshold are obtained as optimized AOA anchor points; wherein the second preset variance threshold is less than the first preset variance threshold.

[0059] In specific implementation, the preliminary selection results are grouped according to shelf information. Based on the shelf grouping results, each shelf is a group, and screening is performed according to position variance. In each group, only the top 50% of price tags with smaller variance (less than a second preset variance threshold, which can be dynamically adjusted according to actual conditions) are retained as AOA anchor points. This can improve the selection accuracy of AOA anchor points, and further improve the accuracy of electronic price tag positioning.

[0060] In one embodiment, the positioning method of the electronic price tag may further include screening multiple AOA anchor points to obtain an optimized AOA anchor point according to the following method:

[0061] Multiple AOA anchor points are grouped according to shelf information, and the AOA anchor point corresponding to each shelf is each group of AOA anchor points;

[0062] According to the received signal strength or pseudo signal-to-noise ratio of the electronic price tag, each group of AOA anchor points is screened, and the AOA anchor points in each group whose signal strength is greater than the preset strength threshold or whose pseudo signal-to-noise ratio is less than the preset pseudo signal-to-noise ratio threshold are obtained as the optimized AOA anchor points.

[0063] During specific implementation, the preliminary selection results are grouped according to shelf information and can also be filtered based on characteristic information such as the RSSI (received signal strength) and PSNR (pseudo signal-to-noise ratio) of the price tags. The pseudo signal-to-noise ratio can be obtained by eigendecomposing the covariance matrix of the received signal, and then the corresponding price tag information is output as the AOA anchor point, which can improve the selection accuracy of the AOA anchor point.

[0064] In specific implementation, the embodiment of the present invention can also integrate multiple features (such as the ratio of the electronic price tag size to the shelf area mentioned above, the variance of the historical positioning position of the AOA anchor point, signal strength, pseudo signal-to-noise ratio, etc.) to more accurately select the corresponding anchor point.

[0065] During specific implementation, the embodiment of the present invention can select anchor points with precise positioning positions. Regarding the final selection of anchor points on each shelf, the possible situations are: one situation: there may be anchor points on each shelf, and the number of anchor points on each shelf may be consistent or inconsistent; another situation: not necessarily every shelf has an anchor point, some shelves may have several anchor points, and some shelves may have no anchor point.

[0066] Third, if Figure 2 As shown, based on the AOA base station location information in the scene to be positioned, the map in the scene to be positioned is divided into a trusted area and an untrusted area, that is, the above step 103.

[0067] In the specific implementation, first, based on the AOA base station location information in the scene to be positioned, the corresponding base station coverage area and non-base station coverage area are divided. The base station coverage area is the untrustworthy area, and the non-base station coverage area is the trustworthy area. In order to further improve the positioning accuracy of the electronic price tag, the embodiment of the present invention makes an innovative definition of the trustworthy area and the untrustworthy area. Figure 3 The trusted area and the untrusted area in the embodiment of the present invention are described as an example.

[0068] In one embodiment, the untrusted area can be the key coverage area of ​​the base station signal, the key shelves covered by the base station signal and the adjacent preset number of shelves. In specific implementation, the untrusted area can be divided into two parts, one of which is: the key coverage area of ​​the base station signal. The key coverage area of ​​the base station signal can be: the coverage area within the normal pitch angle range of the preset angle of the AOA base station, for example, the coverage area within the normal pitch angle range of 60 degrees of the base station, that is, Figure 3 As shown, Figure 3 The top view of the positioning scene is shown in Figure 1, where the shelf is located on the ground and the base station BS can be set on the ceiling. The center of the circle is the base station BS, and the radius is The coverage area is as follows: h is the base station height, and the preset angle can also be other angles, such as 50 degrees, 55 degrees, etc. The other part is the key shelves in the non-key coverage area of ​​the base station signal and the adjacent preset number of shelves, for example, Figure 3 The area of ​​the key shelf M and its corresponding one-hop shelf (shelf E, shelf F) and two-hop shelf (shelf G, shelf H) can also include Figure 3 The area shown in Figure 1 is the area of ​​key rack N and its corresponding one-hop racks (rack K, rack L) and two-hop racks (rack O, rack Q). Of course, this section is just an example; the three-hop racks corresponding to the key rack can also be untrusted areas. The specific number of racks adjacent to the key rack can be determined based on actual needs.

[0069] The trusted area can be divided into two parts: one part is the area covered by the base station except for the two parts of the untrusted area mentioned above. The AOA signal in this area is weak and can be directly regarded as a trusted area. The other part is the area not covered by the base station, such as Figure 3 Shelf I, shelf J, shelf R, and shelf S in the trusted area are regarded as trusted electronic price tags, and the positioning position of the trusted electronic price tags adopts the neighbor positioning result.

[0070] During specific implementation, the embodiment of the present invention uses base station location information and map information in combination to perform hierarchical processing on regions, and can perform preliminary classification and reliable location output on price tags to be located.

[0071] Fourth, based on the information of the selected AOA anchor point, all the electronic price tag neighbors in the scene to be positioned are positioned, that is, Figure 2 As shown, the whole scene neighbor positioning is performed based on the anchor point information, that is, the above step 104, and the price tag located in the credible area is a credible price tag, that is, Figure 2 As shown, according to the division of the trusted area, the price tag located in the trusted area after the neighbor positioning is set as the trusted price tag, and its position remains unchanged before the end of the current full-field positioning. That is, in one embodiment, the above-mentioned electronic price tag positioning method can also include: the electronic price tag located in the trusted area after the neighbor positioning result is set as the trusted electronic price tag, the positioning position of the trusted electronic price tag adopts the neighbor positioning result, and the positioning position of the trusted electronic price tag remains unchanged before the end of the current positioning cycle. Of course, in this step 104, the information of the AOA anchor point can also be as follows Figure 2 Anchor point information obtained by manual positioning as described in , or price tag information that has not been moved after initialization of the store.

[0072] When implementing it specifically, Figure 2 As shown, optionally, manual anchor point acquisition can be performed in areas not covered by AOA, or price tags that have not been moved since initialization in the store can be used as anchor points. Therefore, manually acquired anchor point information and AOA anchor point information can be combined to perform full-site neighbor positioning, further improving the accuracy of neighbor positioning and, in turn, the accuracy of electronic price tag positioning.

[0073] Fifth, the electronic price tags whose neighbor positioning results are in untrustworthy areas are relocated, and the neighbor information and AOA information are further combined to achieve high-precision fusion positioning, such as Figure 2 As shown, the price tags in the untrustworthy area are relocated by fusing the AOA and neighbor information, and the full-field positioning result is output, that is, the above-mentioned step 105.

[0074] In a specific implementation, for electronic price tags whose neighbor positioning results are located in an untrusted area, the following steps are performed: First, based on the established relationship between the angle of arrival positioning results and the shelf locations, the electronic price tags with neighbor positioning results in the untrusted area are grouped together on the nearest shelf. Specifically, the electronic price tags with neighbor positioning results in the untrusted area are found. Then, for these electronic price tags, the relationship between each electronic price tag's angle of arrival positioning result and the shelf location is used to locate them on the shelf closest to their angle of arrival positioning. For price tags in this group without an AOA positioning result, their positioning positions, obtained based on the neighbor relationship, are retained until the next neighbor positioning result update, thereby improving the accuracy of electronic price tag positioning. Next, the system processes abnormal situations, such as when an electronic price tag on shelf F is located on a key shelf M, or vice versa. Specifically, the abnormally located shelf can be detected based on the number and characteristic information of the electronic price tags on the shelf. The positioning results of the electronic price tags on the abnormally located shelf are adjusted based on the characteristic information of the electronic price tags on the abnormally located shelf and the neighbor positioning results, to obtain the final positioning results for the electronic price tags. The following is a detailed description of the steps for adjusting the positioning results of the electronic shelf labels on the shelves with abnormal positioning.

[0075] In one embodiment, the positioning result of the electronic price tag on the abnormal shelf is adjusted based on the characteristic information of the electronic price tag on the abnormal shelf and the neighbor positioning results to obtain the final positioning result of the electronic price tag, including:

[0076] Obtain the size information of the electronic price tags on the abnormally located shelf and its preset hop-number shelves (for example, one-hop shelves and two-hop shelves, and of course, three-hop shelves, four-hop shelves, and other multi-hop shelves can also be considered);

[0077] Determine, based on the neighbor positioning result, the neighbor relationship between the electronic price tag on the abnormally positioned shelf and the electronic price tag on a preset hop number shelf from the abnormally positioned shelf where the electronic price tag is located;

[0078] According to the size information and the neighbor relationship, the electronic price tags that should be excluded from the abnormally positioned shelves and the shelves on which the excluded electronic price tags should be placed are determined to obtain a final positioning result of the electronic price tags.

[0079] In specific implementation, regarding the above-mentioned preset hop number shelf, such as Figure 3 As shown, taking the abnormal shelf as the stack head M as an example, the preset jump number shelf can be Figure 3 The stack head M shown corresponds to a one-hop shelf (shelf E, shelf F), a two-hop shelf (shelf G, shelf H), or Figure 3 The stack head N (one-hop shelf) and stack head P (two-hop shelf) shown in Figure 3 As shown, the preset hop count racks of M may include rack E, rack F, rack G, rack H, as well as rack N and rack P. Of course, the preset hop count racks may also include racks Figure 3 The three-hop racks shown in the figure: rack I and rack J can be set according to actual needs. Based on the above, it can be seen that the specific rack is a one-hop rack or a two-hop rack. The judgment method can be: when the center line connecting the two racks has no intersection with any other rack, it is considered a one-hop rack; when the center line connecting the two racks has an intersection with one rack, it is defined as a two-hop rack, and so on. Figure 3 The number of shelves K and L in the stack M can be determined based on the actual placement of the shelves in the scene to be positioned, and whether the center line connecting the two shelves intersects with other shelves and the number of intersections. This will not be described in detail here.

[0080] In specific implementation, the abnormal shelf located in the embodiment of the present invention can be any shelf in the scene to be located. The following takes the abnormal shelf located as the stack head as an example to introduce the steps of detecting and locating abnormal shelves in the embodiment of the present invention. Figure 3 This is a schematic diagram of the relationship between the stack head (key shelf) and the adjacent shelves in the embodiment of the present invention. During the AOA positioning process, Figure 3Single-hop and multi-hop shelves in the system also generate AOA positioning results, which may shift toward the channel due to positioning errors. Furthermore, price tags on single-hop or multi-hop shelves may be located on the top of the stack. These price tags typically differ in size and other characteristics, resulting in a mix of different-sized price tags. To address this situation, an abnormality determination is required for the top of the stack. The following two conditions must be met simultaneously: 1. The number of price tags exceeds the theoretical number (which can be converted based on area) by at least two (a preset threshold number of price tags); 2. The presence of price tags of two or more sizes and types on the top of the stack. Specifically, in one embodiment, detecting abnormally located shelves based on the number and feature information of electronic price tags on a shelf may include: determining a shelf as abnormally located when the number of electronic price tags on a shelf exceeds a preset threshold number of theoretical price tags and the number of size types of electronic price tags on the shelf exceeds a preset threshold number of types. This embodiment of the present invention utilizes a shelf abnormality determination method based on the fusion of multiple features, such as size and quantity. This method converts the theoretical number of price tags by shelf area and adds the size number. Based on these two features, thresholds are set for binary classification to determine whether the shelf is abnormal, thereby improving the accuracy of shelf abnormality determination.

[0081] In specific implementation, for a pile head in an abnormal state, it is necessary to exclude the price tags on the pile head that belong to the preset number of shelves of the pile head. For example, Figure 3 As shown, the stack head M contains four electronic price tags A1, A2, B1, and B2. When the theoretical number of price tags (the preset theoretical price tag number threshold) is 2, the number of price tags on the stack head is abnormal. If the query finds a jump shelf (such as Figure 3 If price tags are missing on shelves E and F (as shown in the figure), and the existing price tags on shelves E and F match the size of a price tag on stack M, the electronic price tags on the abnormally positioned shelves can be moved to the next-hop shelf (shelf E and shelf F) and their positions updated. To improve the accuracy of adjusting electronic price tags on abnormally positioned shelves, the present invention takes into account the following considerations when eliminating the problem: first, the size of the electronic price tags on shelves adjacent to the abnormally positioned shelves by a preset number of hops; second, the neighbor relationship between each electronic price tag on the abnormally positioned shelves and the electronic price tags on the shelves adjacent to the abnormally positioned shelves by a preset number of hops. Specifically:

[0082] 1. The size of price tags on pre-set shelves. When considering rejection based on price tag size information, the size of electronic price tags on pre-set shelves within the key shelf where the price tag is located should be calculated to determine which size of price tags should be rejected. Note that the size feature here can also be equivalently replaced with other features such as category, and falls within the scope of protection of the embodiments of this invention.

[0083] 2. The neighbor relationship between the electronic price tag and the electronic price tags on the preset hop number shelves of the key shelf where the electronic price tag is located.

[0084] In one embodiment, based on the size information and the neighbor relationship, determining an electronic price tag that should be excluded from the abnormally positioned shelf and the shelf on which the excluded electronic price tag should be placed, and obtaining a final positioning result of the electronic price tag includes:

[0085] According to the size information of the electronic price tags on the shelves with abnormal positioning, the electronic price tags on the shelves with abnormal positioning are grouped by size type, for example Figure 4 As shown, the abnormal positioning shelf includes two size groups: one group is the 10.2 size type electronic price tags: A1 and A2; the other group is the 5.8 size type electronic price tags: B1 and B2;

[0086] Based on the size type grouping information and the neighbor relationship, a neighbor relationship weight table is established for each electronic price tag on the abnormal shelf with respect to all electronic price tags on the preset hop number shelf, such as Figure 4 As shown (theoretically, we also need to establish: "the relationship between A1 and shelves G and H", "the relationship between A2 and shelves E and F", "the relationship between B1 and shelves G and H", "the relationship between B2 and shelves E and F", for the convenience of expression, Figure 4 This is just an example. The neighbor relationship weight table includes the total weight corresponding to each size type group on the abnormal shelf (for example Figure 4 10.2 The total weight of the size type grouping is 0.9) and the total weight of each shelf in the preset number of hops corresponding to each electronic shelf tag on the abnormal shelf; Among them, the total weight corresponding to each size type grouping (such as Figure 4 0.9 in the figure) is calculated based on the location of each electronic price tag on the abnormal shelf, and the corresponding value for each shelf in the preset number of hops (e.g. Figure 4 The total weight of the shelf ID-E in the one-hop shelf corresponding to the electronic price tag A1 (for example Figure 4 The ID-E of the middle shelf is 0.3) and can also be calculated based on Figure 4 The average total weight of each electronic shelf label shown in FIG1 corresponds to each shelf in the preset number of hops (eg Figure 4 Shelf ID - total weight / number of price tags: 0.3 / 4 = 0.075), or the total weight corresponding to each size type group, calculate the average weight corresponding to each size type group (such as Figure 4 Shelf ID - total weight / total number of price tags: 0.9 / 8 / 2). The average weight can also be used to determine the ESLs that should be excluded from the abnormally positioned shelves and the shelves where the excluded ESLs should be placed.

[0087] Determine the electronic price tags that should be excluded from the abnormally positioned shelves based on the size information of the electronic price tags on the shelves with the preset number of hops and the total weight corresponding to each size type group on the abnormally positioned shelves;

[0088] According to the total shelf weight of each shelf in the preset hop number shelf corresponding to each electronic price tag on the abnormally positioned shelf, the shelf where the excluded electronic price tag should be placed is determined to obtain the final positioning result of the electronic price tag.

[0089] In specific implementation, the electronic price tags on the abnormally located shelves are grouped according to size information to obtain multiple groups of electronic price tags. The size types of the electronic price tags in each group are the same. Based on the size type grouping information and the neighbor relationship, a neighbor relationship weight table is established for each electronic price tag on the abnormally located shelves. First, determine which size should be eliminated, and then determine which shelf each eliminated price tag should be placed on. That is, determine the electronic price tags that should be excluded from the abnormally located shelves and the shelf the excluded electronic price tags should be placed on. For example, the theoretical number of price tags on a certain pile is 2, but there are 4 price tags on it at this time, and there are price tags of 2 sizes, so it is determined to be an abnormal shelf, and the electronic price tags on it are grouped and the neighbor relationship weight table is established, such as Figure 4 As shown, Figure 4 Schematic diagram of a neighbor relationship weight table in an embodiment of the present invention.

[0090] In specific implementations, the neighbor weights can be calculated based on the received neighbor signal strengths. This embodiment of the present invention dynamically establishes a neighbor relationship weight table, which can quickly determine the price tags that should be removed and the target locations where they should be placed after removal, thereby improving the accuracy of electronic price tag positioning.

[0091] The specific method for determining the size group to be excluded and the re-placement of the price tags (i.e., determining the electronic price tags to be excluded from the shelves with abnormal positioning and the shelves on which the electronic price tags to be excluded from the shelves with abnormal positioning should be placed according to the neighbor relationship weight table) is as follows: Figure 4As shown, for each price tag on the stack head (in this case, the stack head is the abnormal shelf), a neighbor relationship table is established with all price tags on the preset hop-count shelves, and the total weight or average weight of each shelf is calculated for each price tag. At the same time, the total weight or average weight corresponding to each size type group is calculated according to the size (the average weight also needs to consider the number of price tags of each size in the size group to prevent misjudgment due to the large number of price tags in a certain group). First, determine which size of price tags should be eliminated based on the size ratio and the total weight of the size category (the total weight corresponding to the size type group) or the average weight. For example, the preset hop-count shelves include one-hop and two-hop shelves for the abnormal shelf. Among all the price tags on the one-hop and two-hop shelves, if the proportion of price tags of the size type 5.8 is above the first preset proportion (for example, 80%), then the entire group of price tags of 5.8 will be directly eliminated. If the proportion of price tags of the size type 5.8 is between the second preset proportion (for example, 50%) and the first preset proportion (for example, 80%), it is necessary to further compare the total weight or average weight of the size category (corresponding to the size type group). As shown Figure 4 As shown in , if the price tags of size 5.8 on the one-hop and two-hop shelves account for 60% at this time, and the total weight (1.9) or average weight corresponding to the size type group of 5.8 is the largest, as shown in Figure 4 As shown in the red area, the price tag of 5.8 can be eliminated at this time. Then, for each price tag of 5.8, determine which shelf it is located on. That is, according to the total shelf weight of each electronic price tag on the abnormal shelf for each shelf in the preset hop number shelf, determine the shelf where the electronic price tag of the excluded size type should be located, and locate the electronic price tag of the determined excluded size type on the shelf where it should be located. For example, Figure 4 In the example, the total weight (0.7) or average weight of the 5.8-size B2 price tag and shelf H is the largest, which means that B2 is closest to shelf H and has the closest neighbor relationship with shelf H. Therefore, the B2 price tag needs to be located on shelf H. The same applies to the B1 price tag.

[0092] As can be seen from the above, in one embodiment, based on the size information of the electronic price tags on the shelves with a preset hop count and the total weight corresponding to each size type group on the shelves with abnormal positioning, determining that the electronic price tags should be excluded from the shelves with abnormal positioning includes: determining, based on the size information of the electronic price tags on the shelves with a preset hop count, that the size types of the electronic price tags on the shelves with a preset hop count that are lower than a first preset ratio and higher than a second preset ratio are all the same size type on the shelves with abnormal positioning, and determining, based on the neighbor relationship weight table, that the total weight corresponding to the same size type group on the shelves with abnormal positioning is the largest, determining that the electronic price tags of the same size type should be excluded from the shelves with abnormal positioning; wherein the first preset ratio is greater than the second preset ratio;

[0093] According to the total shelf weight of each shelf in the preset hop number shelf corresponding to each electronic price tag on the abnormally positioned shelf, determine the shelf on which the excluded electronic price tag should be placed, including: adjusting the positioning of the excluded electronic price tag to the shelf with the largest total shelf weight corresponding to it.

[0094] As can be seen from the above, in one embodiment, based on the size information and the neighbor relationship, determining the electronic price tags that should be excluded from the abnormally positioned shelf and the shelf where the excluded electronic price tags should be placed, and obtaining the final positioning result of the electronic price tags includes:

[0095] According to the size information of the electronic price tags on the shelves with abnormal positioning, the electronic price tags on the shelves with abnormal positioning are grouped by size type;

[0096] Based on the size type grouping information and the neighbor relationship, a neighbor relationship weight table is established for each electronic price tag on the abnormally located shelf with respect to all electronic price tags on the shelves with a preset hop count; the neighbor relationship weight table includes a total shelf weight for each electronic price tag on the abnormally located shelf with respect to each shelf in the shelves with a preset hop count;

[0097] According to the size information of the electronic price tags on the shelves with a preset number of jumps, determine the electronic price tags that should be excluded from the shelves with abnormal positioning;

[0098] According to the total shelf weight of each shelf in the preset hop number shelf corresponding to each electronic price tag on the abnormally positioned shelf, the shelf where the excluded electronic price tag should be placed is determined to obtain the final positioning result of the electronic price tag.

[0099] As can be seen from the above, in one embodiment, determining the electronic price tags that should be excluded from the abnormally positioned shelves based on the size information of the electronic price tags on the shelves with a preset number of hops includes:

[0100] When it is determined based on the size information of the electronic price tags on the shelves with a preset hop count that the size types of the electronic price tags exceeding a first preset ratio on the shelves with a preset hop count are all the same size type as on the shelves with abnormal positioning, the electronic price tags of the same size type are excluded from the shelves with abnormal positioning;

[0101] According to the total shelf weight of each shelf in the preset hop number shelf corresponding to each electronic price tag on the abnormally positioned shelf, determine the shelf on which the excluded electronic price tag should be placed, including: adjusting the positioning of the excluded electronic price tag to the shelf with the largest total shelf weight corresponding to it.

[0102] In one embodiment, the electronic price tag location method may further include: adjusting the electronic price tag clustering result on the key shelf using the characteristic information of the shelf according to the following method:

[0103] Detect whether there are abnormal situations of extra electronic price tags on key shelves;

[0104] For key shelves with abnormal conditions, check whether other key shelves within one hop range are missing electronic price tags;

[0105] If there is, for each extra price tag, find the target shelf that is closest to the corrected location and lacks electronic price tags;

[0106] Detecting whether there is an electronic price tag with the same size as the extra electronic price tag on the target key shelf;

[0107] If so, move the extra electronic shelf labels to the target shelf.

[0108] During specific implementation, characteristic information such as the area of ​​the shelf is then used to adjust the results of the price tag aggregation on the focused shelves. Check whether there is an abnormal number of price tags on the focused shelves, that is, the number of price tags exceeds the theoretical number of price tags by 2 or more (adjustable). For such stacks, query whether the other focused shelves within its one-hop range are missing price tags (that is, fewer than the theoretical number of price tags). If so, for each extra price tag, find the stack that is closest (closest to the edge) to its corrected position (or original AOA positioning position) and lacks a price tag. At the same time, check whether there is a price tag of the same size on the target stack. If so, move it to the stack to achieve the purpose of evenly placing the price tags on the focused shelves. Therefore, the embodiment of the present invention dynamically and evenly adjusts the price tag positions based on the remaining number of price tags after regionalization and the availability of shelves in the area.

[0109] In a further preferred embodiment of the present invention, taking into account the dynamic characteristics of positioning in actual scenarios and the high efficiency requirements of system operation, a preferred step is to relocate only the electronic price tags whose neighbor positioning results are in untrustworthy areas and whose positions have moved.

[0110] In one embodiment, after performing neighbor positioning of all electronic price tags in the scene to be positioned based on the information of the selected AOA anchor point and obtaining neighbor positioning results of all electronic price tags in the scene to be positioned, the method further includes:

[0111] Conduct periodic monitoring of all electronic shelf labels;

[0112] Determine whether the position of the electronic price tag has moved based on the changes in the neighbor relationship of the entire venue;

[0113] For the electronic price tag whose neighbor positioning result is located in the untrustworthy area, the following fusion relocation steps are performed based on the arrival angle positioning result and the neighbor positioning result, including: for the electronic price tag whose neighbor positioning result is located in the untrustworthy area and whose position has moved, the following fusion relocation steps are performed based on the arrival angle positioning result and the neighbor positioning result.

[0114] During the specific implementation, taking into account the dynamic characteristics of positioning in actual scenarios and the high efficiency requirements of system operation, after obtaining the initial full-field neighbor positioning results, neighbor positioning and AOA positioning will be performed periodically. In the fusion positioning stage, only the electronic price tags that may have moved need to be re-positioned. For the price tags that have not moved, the last full-field positioning result will be retained as the current positioning result, which improves the efficiency of electronic price tag positioning.

[0115] In addition, in one embodiment, when an electronic price tag on a shelf with non-abnormal positioning in an untrustworthy area is less than or equal to a preset distance from an AOA anchor point, the angle of arrival positioning result is used as the positioning result of the electronic price tag. That is, in an untrustworthy area, when the electronic price tag is less than or equal to the preset distance from the AOA anchor point, it is determined that the area less than the preset distance from the AOA anchor point is an area with good AOA base station coverage. AOA information is used for positioning in this area with good AOA base station coverage, and it is considered that there is no positioning deviation for the electronic price tag in this area with good AOA base station coverage. The angle of arrival positioning result is used as the positioning result for the electronic price tag in this area with good AOA base station coverage, thereby improving the positioning accuracy of the electronic price tag.

[0116] In addition, in one embodiment, when an electronic price tag located on a non-abnormally positioned shelf in an untrustworthy area is greater than a preset distance from an AOA anchor point, a neighbor positioning result is used as the positioning result of the electronic price tag.

[0117] In specific implementation, for electronic price tags that are grouped on non-positioning abnormal shelves and are farther away from the AOA anchor point than a preset distance, it is necessary to regress the positioning results of their neighbors, that is, use the positioning results of the neighbors as the positioning results of the electronic price tags.

[0118] In one embodiment, the above-mentioned method for locating electronic price tags may further include: in an untrustworthy area, electronic price tags that are grouped on non-key shelves according to the AOA positioning results are positioned using the positioning results of their neighbors as their own positioning results.

[0119] In specific implementation, electronic price tags that are grouped on non-key shelves according to AOA positioning results in an untrustworthy area can use their neighbor positioning results as their positioning results, thereby improving the positioning accuracy of the electronic price tags.

[0120] To sum up, the positioning method of electronic price tags provided by the embodiment of the present invention is a full-scene positioning method for electronic price tags. This method combines the positioning results of the electronic price tags' neighbor relationships in the local area and the AOA positioning results in the local area to ultimately obtain the positioning results of the electronic price tags in the full scene. The positioning results of different positioning methods in multiple scenes complement each other, and ultimately achieve fusion positioning in the full scene, thereby improving the positioning accuracy of the electronic price tags.

[0121] The present invention also provides an electronic price tag positioning device, as described in the following embodiments. Since the principle of the device to solve the problem is similar to the electronic price tag positioning method, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0122] Figure 5 FIG. 1 is a schematic diagram of the structure of the positioning device of the electronic price label according to an embodiment of the present invention. Figure 5 As shown, the device includes:

[0123] Acquisition unit 01 is used to obtain the map of the scene to be positioned, the location information of the AOA base station and the arrival angle positioning results of all electronic price tags;

[0124] An AOA anchor point determination unit 02 is configured to select an electronic price tag with a positioning accuracy higher than a preset threshold as an AOA anchor point based on the map of the scene to be positioned and the arrival angle positioning results of all electronic price tags;

[0125] The area division unit 03 is used to divide the map of the scene to be positioned into a trusted area and an untrusted area based on the AOA base station location information of the scene to be positioned;

[0126] The neighbor positioning unit 04 is used to perform neighbor positioning of all electronic price tags in the scene to be positioned based on the information of the selected AOA anchor point, and obtain neighbor positioning results of all electronic price tags in the scene to be positioned;

[0127] The fusion relocation unit 05 is used to perform the following fusion relocation steps for the electronic price tag whose neighbor positioning result is located in the untrustworthy area based on the arrival angle positioning result and the neighbor positioning result: according to the relationship between the arrival angle positioning result of the electronic price tag and the position of the shelf, the electronic price tag whose neighbor positioning result is located in the untrustworthy area is positioned to the nearest shelf; according to the number and characteristic information of the electronic price tags on the shelf, the abnormally positioned shelf is detected; according to the characteristic information of the electronic price tag on the abnormally positioned shelf and the neighbor positioning result, the positioning result of the electronic price tag on the abnormally positioned shelf is adjusted to obtain the final positioning result of the electronic price tag.

[0128] In one embodiment, the AOA anchor point determination unit is specifically configured to:

[0129] Obtain historical positioning information of each electronic price tag with arrival angle positioning results;

[0130] Calculate the average value of the historical positioning position of each electronic price tag and the variance of the historical positioning position of each electronic price tag based on the historical positioning information of each electronic price tag;

[0131] Determine the minimum distance between the average value of the historical positioning position of each electronic shelf label and any edge position of the nearest key shelf;

[0132] The electronic price tag whose variance of historical positioning position is less than the first preset variance threshold, the number of arrival angle positioning results is greater than the preset value and the minimum distance is less than the preset distance threshold is used as the AOA anchor point.

[0133] In one embodiment, the positioning method of the electronic price label may further include an optimization unit configured to filter the multiple AOA anchor points according to the following method to obtain an optimized AOA anchor point:

[0134] Multiple AOA anchor points are grouped according to shelf information, and the AOA anchor point corresponding to each shelf is each group of AOA anchor points;

[0135] According to the size feature information of the electronic price tag, each group of AOA anchor points is screened, and the AOA anchor points with the same size type and the largest number are obtained as the optimized AOA anchor points.

[0136] In one embodiment, the positioning method of the electronic price label may further include an optimization unit configured to filter the multiple AOA anchor points according to the following method to obtain an optimized AOA anchor point:

[0137] Multiple AOA anchor points are grouped according to shelf information, and the AOA anchor point corresponding to each shelf is each group of AOA anchor points;

[0138] Each group of AOA anchor points is screened based on the variance of the historical positioning positions of the AOA anchor points, and the AOA anchor points in each group whose variance of the historical positioning positions is less than a second preset variance threshold are obtained as optimized AOA anchor points; wherein the second preset variance threshold is less than the first preset variance threshold.

[0139] In one embodiment, the positioning method of the electronic price label may further include an optimization unit configured to filter the multiple AOA anchor points according to the following method to obtain an optimized AOA anchor point:

[0140] Multiple AOA anchor points are grouped according to shelf information, and the AOA anchor point corresponding to each shelf is each group of AOA anchor points;

[0141] According to the received signal strength or pseudo signal-to-noise ratio of the electronic price tag, each group of AOA anchor points is screened, and the AOA anchor points in each group whose signal strength is greater than the preset strength threshold or whose pseudo signal-to-noise ratio is less than the preset pseudo signal-to-noise ratio threshold are obtained as the optimized AOA anchor points.

[0142] In one embodiment, detecting and locating abnormal shelves based on the number and characteristic information of electronic price tags on the shelves includes:

[0143] When the number of electronic price tags on a shelf exceeds a preset theoretical price tag number threshold, and the number of size types of electronic price tags on the shelf exceeds a preset type number threshold, the shelf is determined to be an abnormally positioned shelf.

[0144] In one embodiment, the positioning result of the electronic price tag on the abnormal shelf is adjusted based on the characteristic information of the electronic price tag on the abnormal shelf and the neighbor positioning results to obtain the final positioning result of the electronic price tag, including:

[0145] Obtain the size information of the electronic price tags on the abnormally located shelf and the preset number of shelves;

[0146] Determine, based on the neighbor positioning result, the neighbor relationship between the electronic price tag on the abnormally positioned shelf and the electronic price tag on a preset hop number shelf from the abnormally positioned shelf where the electronic price tag is located;

[0147] According to the size information and the neighbor relationship, the electronic price tags that should be excluded from the abnormally positioned shelves and the shelves on which the excluded electronic price tags should be placed are determined to obtain a final positioning result of the electronic price tags.

[0148] In one embodiment, based on the size information and the neighbor relationship, determining an electronic price tag that should be excluded from the abnormally positioned shelf and the shelf on which the excluded electronic price tag should be placed, and obtaining a final positioning result of the electronic price tag includes:

[0149] According to the size information of the electronic price tags on the shelves with abnormal positioning, the electronic price tags on the shelves with abnormal positioning are grouped by size type;

[0150] Based on the size type grouping information and the neighbor relationship, a neighbor relationship weight table is established for each electronic price tag on the abnormally located shelf with respect to all electronic price tags on the shelves with a preset hop count; the neighbor relationship weight table includes the total weight corresponding to each size type group on the abnormally located shelf and the total shelf weight corresponding to each electronic price tag on the abnormally located shelf with respect to each shelf in the shelves with a preset hop count;

[0151] Determine the electronic price tags that should be excluded from the abnormally positioned shelves based on the size information of the electronic price tags on the shelves with the preset number of hops and the total weight corresponding to each size type group on the abnormally positioned shelves;

[0152] According to the total shelf weight of each shelf in the preset hop number shelf corresponding to each electronic price tag on the abnormally positioned shelf, the shelf where the excluded electronic price tag should be placed is determined to obtain the final positioning result of the electronic price tag.

[0153] In one embodiment, based on the size information of the electronic price tags on the shelves with a preset hop count and the total weight corresponding to each size type group on the shelves with abnormal positioning, determining that the electronic price tags should be excluded from the shelves with abnormal positioning includes: determining, based on the size information of the electronic price tags on the shelves with a preset hop count, that the size types of the electronic price tags on the shelves with a preset hop count that are lower than a first preset ratio and higher than a second preset ratio are all the same size type on the shelves with abnormal positioning, and determining, based on the neighbor relationship weight table, that the total weight corresponding to the same size type group on the shelves with abnormal positioning is the largest, determining that the electronic price tags of the same size type should be excluded from the shelves with abnormal positioning; wherein the first preset ratio is greater than the second preset ratio;

[0154] According to the total shelf weight of each shelf in the preset hop number shelf corresponding to each electronic price tag on the abnormally positioned shelf, determine the shelf on which the excluded electronic price tag should be placed, including: adjusting the positioning of the excluded electronic price tag to the shelf with the largest total shelf weight corresponding to it.

[0155] In one embodiment, based on the size information and the neighbor relationship, determining an electronic price tag that should be excluded from the abnormally positioned shelf and the shelf on which the excluded electronic price tag should be placed, and obtaining a final positioning result of the electronic price tag includes:

[0156] According to the size information of the electronic price tags on the shelves with abnormal positioning, the electronic price tags on the shelves with abnormal positioning are grouped by size type;

[0157] Based on the size type grouping information and the neighbor relationship, a neighbor relationship weight table is established for each electronic price tag on the abnormally located shelf with respect to all electronic price tags on the shelves with a preset hop count; the neighbor relationship weight table includes a total shelf weight for each electronic price tag on the abnormally located shelf with respect to each shelf in the shelves with a preset hop count;

[0158] According to the size information of the electronic price tags on the shelves with a preset number of jumps, determine the electronic price tags that should be excluded from the shelves with abnormal positioning;

[0159] According to the total shelf weight of each shelf in the preset hop number shelf corresponding to each electronic price tag on the abnormally positioned shelf, the shelf where the excluded electronic price tag should be placed is determined to obtain the final positioning result of the electronic price tag.

[0160] In one embodiment, determining electronic price tags that should be excluded from shelves with abnormal positioning based on size information of electronic price tags on shelves with a preset number of hops may include:

[0161] When it is determined based on the size information of the electronic price tags on the shelves with a preset hop count that the size types of the electronic price tags exceeding a first preset ratio on the shelves with a preset hop count are all the same size type as on the shelves with abnormal positioning, the electronic price tags of the same size type are excluded from the shelves with abnormal positioning;

[0162] According to the total shelf weight of each shelf in the preset hop number shelf corresponding to each electronic price tag on the abnormally positioned shelf, determine the shelf on which the excluded electronic price tag should be placed, including: adjusting the positioning of the excluded electronic price tag to the shelf with the largest total shelf weight corresponding to it.

[0163] In one embodiment, the electronic price tag positioning device may further include: a homogenization processing unit configured to adjust the electronic price tag aggregation result on the key shelves using the characteristic information of the shelves:

[0164] Detect whether there are abnormal situations of extra electronic price tags on key shelves;

[0165] For key shelves with abnormal conditions, check whether other key shelves within one hop range are missing electronic price tags;

[0166] If there is, for each extra price tag, find the target shelf that is closest to the corrected location and lacks electronic price tags;

[0167] Detecting whether there is an electronic price tag with the same size as the extra electronic price tag on the target key shelf;

[0168] If so, move the extra electronic shelf labels to the target shelf.

[0169] In one embodiment, the untrustworthy area is the key coverage area of ​​the base station signal, the key shelves covered by the base station signal and the adjacent shelf areas of a preset number of sections.

[0170] In one embodiment, the key coverage area is a coverage area within a range of a preset angle normal pitch angle of the AOA base station.

[0171] In one embodiment, the positioning unit is further used to use the electronic price tag whose neighbor positioning result is located within the trusted area as a trusted electronic price tag. The positioning position of the trusted electronic price tag adopts the neighbor positioning result, and the positioning position of the trusted electronic price tag remains unchanged before the end of this positioning cycle.

[0172] In one embodiment, the fusion relocation unit is further used to: when the distance between the electronic price tag on the non-positioning abnormal shelf in the untrustworthy area and the AOA anchor point is less than or equal to a preset distance, use the arrival angle positioning result as the positioning result of the electronic price tag.

[0173] In one embodiment, the fusion relocation unit is further configured to: when an electronic price tag located on a non-abnormally positioned shelf in an untrustworthy area is greater than a preset distance from an AOA anchor point, use a neighbor positioning result as the positioning result of the electronic price tag.

[0174] In one embodiment, the fusion relocation unit is further configured to: in an untrustworthy area, for electronic price tags that are grouped on non-key shelves according to the AOA positioning results, use the positioning results of their neighbors as their own positioning results.

[0175] In one embodiment, the positioning device for the electronic price tag may further include: a monitoring unit configured to locate all neighbors of the electronic price tags in the scene to be positioned based on the information of the selected AOA anchor point, and periodically monitor all the electronic price tags after obtaining the neighbor positioning results of all the electronic price tags in the scene to be positioned;

[0176] The motion detection unit is used to determine whether the position of the electronic price tag has moved according to the changes in the neighbor relationship of the entire venue;

[0177] For electronic price tags whose neighbor positioning results are located in an untrustworthy area, the following steps of fusion relocation are performed based on the arrival angle positioning results and the neighbor positioning results. This may include: for electronic price tags whose neighbor positioning results are located in an untrustworthy area and whose position has moved, the following steps of fusion relocation are performed based on the arrival angle positioning results and the neighbor positioning results.

[0178] Based on the above invention concept, Figure 6 As shown, the present invention also proposes a computer device 500, including a memory 510, a processor 520 and a computer program 530 stored in the memory 510 and executable on the processor 520, wherein the processor 520 implements the aforementioned electronic price tag positioning method when executing the computer program 530.

[0179] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the computer program implements the above-mentioned electronic price tag positioning method.

[0180] 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 computer program implements the above-mentioned positioning method of the electronic price tag.

[0181] In the embodiment of the present invention, the positioning solution of the electronic price tag is compared with the technical solutions with insufficient positioning accuracy or large positioning errors in the prior art. The method comprises the following steps: obtaining a map of the scene to be positioned, the location information of the AOA base station, and the arrival angle positioning results of all the electronic price tags; selecting an electronic price tag with a positioning accuracy higher than a preset threshold as an AOA anchor point based on the map of the scene to be positioned and the arrival angle positioning results of all the electronic price tags; dividing the map of the scene to be positioned into a trusted area and an untrusted area based on the location information of the AOA base station in the scene to be positioned; locating the neighbors of all the electronic price tags in the scene to be positioned based on the information of the selected AOA anchor point, and obtaining the neighboring information of all the electronic price tags in the scene to be positioned. The positioning result is obtained; for the electronic price tags whose neighbor positioning results are located in the untrustworthy area, the following fusion repositioning steps are performed based on the arrival angle positioning result and the neighbor positioning result: according to the position relationship between the arrival angle positioning result of the electronic price tag and the shelf, the electronic price tags whose neighbor positioning results are located in the untrustworthy area are positioned to the nearest shelf; according to the number and feature information of the electronic price tags on the shelf, the abnormally positioned shelves are detected; according to the feature information of the electronic price tags on the abnormally positioned shelves and the neighbor positioning results, the positioning results of the electronic price tags on the abnormally positioned shelves are adjusted to obtain the final positioning results of the electronic price tags, which can realize full-scene high-precision positioning based on the fusion of AOA and neighbor relationship information, and improve the positioning accuracy of the electronic price tags.

[0182] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. 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 magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0183] 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 flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, 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 produce 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 flowcharts and / or block diagrams. 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.

[0184] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0185] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0186] 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 positioning method for an electronic price label, characterized in that: include: Obtain the map of the scene to be positioned, AOA base station location information, and arrival angle positioning results of all electronic price tags; Based on the map of the scene to be positioned and the arrival angle positioning results of all electronic price tags, the electronic price tags with positioning accuracy higher than the preset threshold are selected as AOA anchor points; Based on the AOA base station location information in the scene to be positioned, the map of the scene to be positioned is divided into a trusted area and an untrusted area; Based on the information of the selected AOA anchor point, all the electronic price tags in the scene to be positioned are positioned, and the neighbor positioning results of all the electronic price tags in the scene to be positioned are obtained; For electronic price tags whose neighbor positioning results are located in untrustworthy areas, the following fusion relocation steps are performed based on the arrival angle positioning results and the neighbor positioning results: according to the relationship between the arrival angle positioning results of the electronic price tags and the position of the shelves, the electronic price tags whose neighbor positioning results are located in the untrustworthy areas are positioned to the nearest shelves; according to the number and feature information of the electronic price tags on the shelves, the shelves with abnormal positioning are detected; according to the feature information of the electronic price tags on the shelves with abnormal positioning and the neighbor positioning results, the positioning results of the electronic price tags on the shelves with abnormal positioning are adjusted to obtain the final positioning results of the electronic price tags.

2. The method according to claim 1, wherein Based on the map of the scene to be positioned and the arrival angle positioning results of all electronic price tags, electronic price tags with positioning accuracy higher than the preset threshold are selected as AOA anchor points, including: Obtain historical positioning information of each electronic price tag with arrival angle positioning results; Calculate the average value of the historical positioning position of each electronic price tag and the variance of the historical positioning position of each electronic price tag based on the historical positioning information of each electronic price tag; Determine the minimum distance between the average value of the historical positioning position of each electronic shelf label and any edge position of the nearest key shelf; The electronic price tag whose variance of the historical positioning position is less than the first preset variance threshold, the number of arrival angle positioning results is greater than the preset value, and the minimum distance is less than the preset distance threshold is used as the AOA anchor point.

3. The method according to claim 2, wherein The method further includes screening multiple AOA anchor points according to the following method to obtain an optimized AOA anchor point: Multiple AOA anchor points are grouped according to shelf information, and the AOA anchor point corresponding to each shelf is each group of AOA anchor points; According to the size feature information of the electronic price tag, each group of AOA anchor points is screened, and the AOA anchor points with the same size type and the largest number are obtained as the optimized AOA anchor points.

4. The method according to claim 2, wherein The method further includes screening multiple AOA anchor points according to the following method to obtain an optimized AOA anchor point: Multiple AOA anchor points are grouped according to shelf information, and the AOA anchor point corresponding to each shelf is each group of AOA anchor points; Each group of AOA anchor points is screened based on the variance of the historical positioning positions of the AOA anchor points, and the AOA anchor points in each group whose variance of the historical positioning positions is less than a second preset variance threshold are obtained as optimized AOA anchor points; wherein the second preset variance threshold is less than the first preset variance threshold.

5. The method according to claim 2, wherein The method further includes screening multiple AOA anchor points according to the following method to obtain an optimized AOA anchor point: Multiple AOA anchor points are grouped according to shelf information, and the AOA anchor point corresponding to each shelf is each group of AOA anchor points; According to the received signal strength or pseudo signal-to-noise ratio of the electronic price tag, each group of AOA anchor points is screened, and the AOA anchor points in each group whose signal strength is greater than the preset strength threshold or whose pseudo signal-to-noise ratio is less than the preset pseudo signal-to-noise ratio threshold are obtained as the optimized AOA anchor points.

6. The method according to claim 1, wherein Detect and locate abnormal shelves based on the number and feature information of electronic price tags on the shelves, including: When the number of electronic price tags on a shelf exceeds a preset theoretical price tag number threshold, and the number of size types of electronic price tags on the shelf exceeds a preset type number threshold, the shelf is determined to be an abnormally positioned shelf.

7. The method according to claim 1, wherein Based on the characteristic information of the electronic price tag on the abnormal shelf and the neighbor positioning results, the positioning result of the electronic price tag on the abnormal shelf is adjusted to obtain the final positioning result of the electronic price tag, including: Obtain the size information of the electronic price tags on the abnormally located shelf and the preset number of shelves; Determine, based on the neighbor positioning result, the neighbor relationship between the electronic price tag on the abnormally positioned shelf and the electronic price tag on a preset hop number shelf from the abnormally positioned shelf where the electronic price tag is located; According to the size information and the neighbor relationship, the electronic price tags that should be excluded from the abnormally positioned shelves and the shelves on which the excluded electronic price tags should be placed are determined to obtain a final positioning result of the electronic price tags.

8. The method according to claim 7, wherein Determining, based on the size information and the neighbor relationship, an electronic price tag that should be excluded from the abnormally positioned shelf and the shelf on which the excluded electronic price tag should be placed, and obtaining a final positioning result of the electronic price tag, including: According to the size information of the electronic price tags on the shelves with abnormal positioning, the electronic price tags on the shelves with abnormal positioning are grouped by size type; Based on the size type grouping information and the neighbor relationship, a neighbor relationship weight table is established for each electronic price tag on the abnormally located shelf with respect to all electronic price tags on the shelves with a preset hop count; the neighbor relationship weight table includes the total weight corresponding to each size type group on the abnormally located shelf and the total shelf weight corresponding to each electronic price tag on the abnormally located shelf with respect to each shelf in the shelves with a preset hop count; Determine the electronic price tags that should be excluded from the abnormally positioned shelves based on the size information of the electronic price tags on the shelves with the preset number of hops and the total weight corresponding to each size type group on the abnormally positioned shelves; According to the total shelf weight of each shelf in the preset hop number shelf corresponding to each electronic price tag on the abnormally positioned shelf, the shelf where the excluded electronic price tag should be placed is determined to obtain the final positioning result of the electronic price tag.

9. The method according to claim 8, wherein Determining, based on the size information of the electronic price tags on the shelves with a preset hop count and the total weight corresponding to each size type group on the shelves with abnormal positioning, that the electronic price tags should be excluded from the shelves with abnormal positioning, including: determining, based on the size information of the electronic price tags on the shelves with a preset hop count, that the size types of the electronic price tags on the shelves with a preset hop count that are lower than a first preset ratio and higher than a second preset ratio are all the same size type on the shelves with abnormal positioning, and determining, based on the neighbor relationship weight table, that the total weight corresponding to the same size type group on the shelves with abnormal positioning is the largest, determining that the electronic price tags of the same size type should be excluded from the shelves with abnormal positioning; wherein the first preset ratio is greater than the second preset ratio; According to the total shelf weight of each shelf in the preset hop number shelf corresponding to each electronic price tag on the abnormally positioned shelf, determine the shelf on which the excluded electronic price tag should be placed, including: adjusting the positioning of the excluded electronic price tag to the shelf with the largest total shelf weight corresponding to it.

10. The method according to claim 7, wherein: Determining, based on the size information and the neighbor relationship, an electronic price tag that should be excluded from the abnormally positioned shelf and the shelf on which the excluded electronic price tag should be placed, and obtaining a final positioning result of the electronic price tag, including: According to the size information of the electronic price tags on the shelves with abnormal positioning, the electronic price tags on the shelves with abnormal positioning are grouped by size type; Based on the size type grouping information and the neighbor relationship, a neighbor relationship weight table is established for each electronic price tag on the abnormally located shelf with respect to all electronic price tags on the shelves with a preset hop count; the neighbor relationship weight table includes a total shelf weight for each electronic price tag on the abnormally located shelf with respect to each shelf in the shelves with a preset hop count; According to the size information of the electronic price tags on the shelves with a preset number of jumps, determine the electronic price tags that should be excluded from the shelves with abnormal positioning; According to the total shelf weight of each shelf in the preset hop number shelf corresponding to each electronic price tag on the abnormally positioned shelf, the shelf where the excluded electronic price tag should be placed is determined to obtain the final positioning result of the electronic price tag.

11. The method according to claim 10, wherein Based on the size information of the electronic shelf labels on the preset hop number shelves, determine the electronic shelf labels that should be excluded from the shelves with abnormal positioning, including: When it is determined based on the size information of the electronic price tags on the shelves with a preset hop count that the size types of the electronic price tags exceeding a first preset ratio on the shelves with a preset hop count are all the same size type as on the shelves with abnormal positioning, the electronic price tags of the same size type are excluded from the shelves with abnormal positioning; According to the total shelf weight of each shelf in the preset hop number shelf corresponding to each electronic price tag on the abnormally positioned shelf, determine the shelf on which the excluded electronic price tag should be placed, including: adjusting the positioning of the excluded electronic price tag to the shelf with the largest total shelf weight corresponding to it.

12. The method according to claim 1, wherein The untrustworthy area is the key coverage area of ​​the base station signal, the key shelves covered by the base station signal and the adjacent shelf areas of a preset number of sections.

13. The method according to claim 12, wherein: The key coverage area is the coverage area within the range of the AOA base station preset angle normal pitch angle.

14. The method according to claim 1, wherein Also includes: The electronic price tag whose neighbor positioning result is within the trusted area is regarded as a trusted electronic price tag. The positioning position of the trusted electronic price tag adopts the neighbor positioning result. Before the end of this positioning cycle, the positioning position of the trusted electronic price tag remains unchanged.

15. The method according to claim 1, wherein Also includes: When the distance between the electronic shelf tag on the non-positioning abnormal shelf in the untrustworthy area and the AOA anchor point is less than or equal to the preset distance, the arrival angle positioning result is used as the positioning result of the electronic shelf tag.

16. The method according to claim 1, wherein Also includes: When the distance between an ESL located on a shelf with abnormal positioning in an untrustworthy area and the AOA anchor point is greater than the preset distance, the neighbor positioning result is used as the positioning result of the ESL.

17. The method according to claim 1, wherein Also includes: In the untrustworthy area, the electronic price tags on non-key shelves are grouped according to the AOA positioning results, and the positioning results of their neighbors are used as their own positioning results.

18. The method according to claim 1, wherein After positioning all the neighbors of the electronic price tags in the scene to be positioned based on the information of the selected AOA anchor point and obtaining the neighbor positioning results of all the electronic price tags in the scene to be positioned, the method further includes: Conduct periodic monitoring of all electronic shelf labels; Determine whether the position of the electronic price tag has moved based on the changes in the neighbor relationship of the entire venue; For the electronic price tag whose neighbor positioning result is located in the untrustworthy area, the following fusion relocation steps are performed based on the arrival angle positioning result and the neighbor positioning result, including: for the electronic price tag whose neighbor positioning result is located in the untrustworthy area and whose position has moved, the following fusion relocation steps are performed based on the arrival angle positioning result and the neighbor positioning result.

19. A positioning device for an electronic price label, characterized in that: include: An acquisition unit is used to obtain the map of the scene to be positioned, the location information of the AOA base station, and the arrival angle positioning results of all electronic price tags; An AOA anchor point determination unit is configured to select an electronic price tag with a positioning accuracy higher than a preset threshold as an AOA anchor point based on a map of the scene to be positioned and the arrival angle positioning results of all electronic price tags; A region division unit is used to divide the map of the scene to be positioned into a trusted area and an untrusted area based on the AOA base station location information of the scene to be positioned; A neighbor positioning unit is used to locate the neighbors of all electronic price tags in the scene to be positioned based on the information of the selected AOA anchor point, and obtain the neighbor positioning results of all electronic price tags in the scene to be positioned; The fusion relocation unit is used to perform the following fusion relocation steps for the electronic price tags whose neighbor positioning results are located in the untrustworthy area based on the arrival angle positioning results and the neighbor positioning results: according to the relationship between the arrival angle positioning results of the electronic price tags and the positions of the shelves, the electronic price tags whose neighbor positioning results are located in the untrustworthy area are positioned to the nearest shelves; according to the number and feature information of the electronic price tags on the shelves, the shelves with abnormal positioning are detected; according to the feature information of the electronic price tags on the shelves with abnormal positioning and the neighbor positioning results, the positioning results of the electronic price tags on the shelves with abnormal positioning are adjusted to obtain the final positioning results of the electronic price tags.

20. A computer device comprising a memory (510), a processor (520), and a computer program (530) stored in the memory (510) and executable on the processor (520), characterized in that: When the processor (520) executes the computer program (530), the method according to any one of claims 1 to 18 is implemented.

21. 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 18 is implemented.

22. 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 18 is implemented.

Images